{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 12032,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008311170212765958,
      "grad_norm": 401.13100015843634,
      "learning_rate": 3.3195020746887967e-09,
      "loss": 1.3266,
      "step": 5,
      "success_rate.epoch.env.logic": 0.0,
      "success_rate.epoch.env.science": 0.75,
      "success_rate.epoch.env_macro_mean": 0.375,
      "success_rate.epoch.global": 0.6,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9984581497797357,
      "tokens_p.mean_in_band": 0.5880748820754716,
      "tokens_rate.above_band": 0.9553872053872053,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04461279461279461
    },
    {
      "epoch": 0.0016622340425531915,
      "grad_norm": 187.50685532828885,
      "learning_rate": 7.468879668049792e-09,
      "loss": 1.3018,
      "step": 10,
      "success_rate.epoch.env.logic": 0.0,
      "success_rate.epoch.env.science": 0.5,
      "success_rate.epoch.env_macro_mean": 0.25,
      "success_rate.epoch.global": 0.4,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.125,
      "success_rate.window.global": 0.2,
      "tokens_p.mean_above_band": 0.9980440320232896,
      "tokens_p.mean_below_band": 8.585629984736443e-10,
      "tokens_p.mean_in_band": 0.5657913773148148,
      "tokens_rate.above_band": 0.9258760107816711,
      "tokens_rate.below_band": 0.0013477088948787063,
      "tokens_rate.in_band": 0.07277628032345014
    },
    {
      "epoch": 0.0024933510638297874,
      "grad_norm": 2423.9894087591297,
      "learning_rate": 1.1618257261410788e-08,
      "loss": 1.184,
      "step": 15,
      "success_rate.epoch.env.logic": 0.2,
      "success_rate.epoch.env.science": 0.52,
      "success_rate.epoch.env_macro_mean": 0.36,
      "success_rate.epoch.global": 0.4666666666666667,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.99170197740113,
      "tokens_p.mean_below_band": 8.585629984736443e-10,
      "tokens_p.mean_in_band": 0.6497112771739131,
      "tokens_rate.above_band": 0.8805970149253731,
      "tokens_rate.below_band": 0.004975124378109453,
      "tokens_rate.in_band": 0.11442786069651742
    },
    {
      "epoch": 0.003324468085106383,
      "grad_norm": 238.72394610631142,
      "learning_rate": 1.5767634854771783e-08,
      "loss": 1.1159,
      "step": 20,
      "success_rate.epoch.env.logic": 0.2,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.5625,
      "success_rate.epoch.env_macro_mean": 0.440625,
      "success_rate.epoch.global": 0.525,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9904801324503312,
      "tokens_p.mean_in_band": 0.6736010174418605,
      "tokens_rate.above_band": 0.7783505154639175,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.22164948453608246
    },
    {
      "epoch": 0.004155585106382979,
      "grad_norm": 400.3309500951242,
      "learning_rate": 1.991701244813278e-08,
      "loss": 1.5418,
      "step": 25,
      "success_rate.epoch.env.ded": 1.0,
      "success_rate.epoch.env.logic": 0.16666666666666666,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5333333333333333,
      "success_rate.epoch.global": 0.5,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.16666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666667,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9953038674033149,
      "tokens_p.mean_in_band": 0.5205592105263158,
      "tokens_rate.above_band": 0.9407484407484408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.059251559251559255
    },
    {
      "epoch": 0.004986702127659575,
      "grad_norm": 319.49929599700613,
      "learning_rate": 2.4066390041493776e-08,
      "loss": 1.2687,
      "step": 30,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.16666666666666666,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.5555555555555556,
      "success_rate.epoch.env_macro_mean": 0.47777777777777775,
      "success_rate.epoch.global": 0.5333333333333333,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9868908898305084,
      "tokens_p.mean_in_band": 0.6214446107784432,
      "tokens_rate.above_band": 0.7386541471048513,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.26134585289514867
    },
    {
      "epoch": 0.00581781914893617,
      "grad_norm": 228.4919815949419,
      "learning_rate": 2.821576763485477e-08,
      "loss": 1.3086,
      "step": 35,
      "success_rate.epoch.env.agentgym:alfworld": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.14285714285714285,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.5686274509803921,
      "success_rate.epoch.env_macro_mean": 0.5769140989729226,
      "success_rate.epoch.global": 0.5571428571428572,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9984144542772861,
      "tokens_p.mean_in_band": 0.5356794084821429,
      "tokens_rate.above_band": 0.9680182752712736,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03198172472872644
    },
    {
      "epoch": 0.006648936170212766,
      "grad_norm": 308.61285894032443,
      "learning_rate": 3.2365145228215765e-08,
      "loss": 1.5794,
      "step": 40,
      "success_rate.epoch.env.agentgym:alfworld": 1.0,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.125,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.5789473684210527,
      "success_rate.epoch.env_macro_mean": 0.6838972431077694,
      "success_rate.epoch.global": 0.575,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973583633093526,
      "tokens_p.mean_in_band": 0.6287878787878788,
      "tokens_rate.above_band": 0.9439728353140917,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05602716468590832
    },
    {
      "epoch": 0.007480053191489362,
      "grad_norm": 566.7855176847529,
      "learning_rate": 3.651452282157676e-08,
      "loss": 1.4112,
      "step": 45,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.1111111111111111,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.59375,
      "success_rate.epoch.env_macro_mean": 0.6364087301587301,
      "success_rate.epoch.global": 0.5777777777777777,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9972698252688172,
      "tokens_p.mean_in_band": 0.6447531960227273,
      "tokens_rate.above_band": 0.9441624365482234,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05583756345177665
    },
    {
      "epoch": 0.008311170212765957,
      "grad_norm": 499.637516240341,
      "learning_rate": 4.066390041493776e-08,
      "loss": 1.329,
      "step": 50,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.1111111111111111,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.6231884057971014,
      "success_rate.epoch.env_macro_mean": 0.6406142167011731,
      "success_rate.epoch.global": 0.6161616161616161,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9166666666666667,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9896941489361702,
      "tokens_p.mean_in_band": 0.6927490234375,
      "tokens_rate.above_band": 0.746031746031746,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.25396825396825395
    },
    {
      "epoch": 0.009142287234042553,
      "grad_norm": 163.52332864641429,
      "learning_rate": 4.4813278008298754e-08,
      "loss": 1.2468,
      "step": 55,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.1,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.6103896103896104,
      "success_rate.epoch.env_macro_mean": 0.6371985157699444,
      "success_rate.epoch.global": 0.6055045871559633,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9889583333333334,
      "tokens_p.mean_in_band": 0.5577256944444444,
      "tokens_rate.above_band": 0.7352941176470589,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2647058823529412
    },
    {
      "epoch": 0.00997340425531915,
      "grad_norm": 397.74951402324774,
      "learning_rate": 4.8962655601659744e-08,
      "loss": 1.2968,
      "step": 60,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.18181818181818182,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.2,
      "success_rate.epoch.env.science": 0.6024096385542169,
      "success_rate.epoch.env_macro_mean": 0.6286992124341522,
      "success_rate.epoch.global": 0.5966386554621849,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9947509765625,
      "tokens_p.mean_in_band": 0.705577761627907,
      "tokens_rate.above_band": 0.8561872909698997,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14381270903010032
    },
    {
      "epoch": 0.010804521276595746,
      "grad_norm": 293.6381642270671,
      "learning_rate": 5.3112033195020747e-08,
      "loss": 1.2173,
      "step": 65,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.8,
      "success_rate.epoch.env.logic": 0.18181818181818182,
      "success_rate.epoch.env.math": 0.9285714285714286,
      "success_rate.epoch.env.sat": 0.2,
      "success_rate.epoch.env.science": 0.6,
      "success_rate.epoch.env_macro_mean": 0.6252937538651823,
      "success_rate.epoch.global": 0.5968992248062015,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6904761904761904,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9917561349693251,
      "tokens_p.mean_in_band": 0.627734375,
      "tokens_rate.above_band": 0.844559585492228,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15544041450777202
    },
    {
      "epoch": 0.01163563829787234,
      "grad_norm": 461.24478905392465,
      "learning_rate": 5.7261410788381736e-08,
      "loss": 1.2202,
      "step": 70,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.8,
      "success_rate.epoch.env.logic": 0.15384615384615385,
      "success_rate.epoch.env.math": 0.9333333333333333,
      "success_rate.epoch.env.sat": 0.2,
      "success_rate.epoch.env.science": 0.5979381443298969,
      "success_rate.epoch.env_macro_mean": 0.6216834711680074,
      "success_rate.epoch.global": 0.5899280575539568,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.5238095238095238,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9981339126559715,
      "tokens_p.mean_in_band": 0.4951171875,
      "tokens_rate.above_band": 0.9342214820982515,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06577851790174855
    },
    {
      "epoch": 0.012466755319148936,
      "grad_norm": 547.4042947917907,
      "learning_rate": 6.141078838174275e-08,
      "loss": 1.506,
      "step": 75,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.8,
      "success_rate.epoch.env.logic": 0.13333333333333333,
      "success_rate.epoch.env.math": 0.9333333333333333,
      "success_rate.epoch.env.sat": 0.16666666666666666,
      "success_rate.epoch.env.science": 0.6153846153846154,
      "success_rate.epoch.env_macro_mean": 0.6164835164835166,
      "success_rate.epoch.global": 0.5906040268456376,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.996728650137741,
      "tokens_p.mean_in_band": 0.6344747340425532,
      "tokens_rate.above_band": 0.9391979301423027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06080206985769728
    },
    {
      "epoch": 0.013297872340425532,
      "grad_norm": 157.51357010421583,
      "learning_rate": 6.556016597510374e-08,
      "loss": 1.0704,
      "step": 80,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.13333333333333333,
      "success_rate.epoch.env.math": 0.9444444444444444,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.5925925925925926,
      "success_rate.epoch.env_macro_mean": 0.592365835222978,
      "success_rate.epoch.global": 0.5759493670886076,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9880798969072165,
      "tokens_p.mean_in_band": 0.6870028409090909,
      "tokens_rate.above_band": 0.8605830164765526,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1394169835234474
    },
    {
      "epoch": 0.014128989361702128,
      "grad_norm": 561.2238683461217,
      "learning_rate": 6.970954356846473e-08,
      "loss": 1.3092,
      "step": 85,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.1111111111111111,
      "success_rate.epoch.env.math": 0.8947368421052632,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.6017699115044248,
      "success_rate.epoch.env_macro_mean": 0.5595916677492297,
      "success_rate.epoch.global": 0.5654761904761905,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.2,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9983031674208145,
      "tokens_p.mean_in_band": 0.5675838694852942,
      "tokens_rate.above_band": 0.9629629629629629,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037037037037037035
    },
    {
      "epoch": 0.014960106382978724,
      "grad_norm": 280.93420534873474,
      "learning_rate": 7.385892116182573e-08,
      "loss": 1.2831,
      "step": 90,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.15789473684210525,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.6101694915254238,
      "success_rate.epoch.env_macro_mean": 0.5096985047364173,
      "success_rate.epoch.global": 0.5730337078651685,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.76,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.99908447265625,
      "tokens_p.mean_below_band": 5.617039278149605e-09,
      "tokens_p.mean_in_band": 0.2380484271523179,
      "tokens_rate.above_band": 0.8711186729051468,
      "tokens_rate.below_band": 0.0004253509145044662,
      "tokens_rate.in_band": 0.1284559761803488
    },
    {
      "epoch": 0.01579122340425532,
      "grad_norm": 351.01882732407955,
      "learning_rate": 7.800829875518672e-08,
      "loss": 1.6298,
      "step": 95,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.15789473684210525,
      "success_rate.epoch.env.math": 0.9090909090909091,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.6111111111111112,
      "success_rate.epoch.env_macro_mean": 0.5109525708209919,
      "success_rate.epoch.global": 0.5797872340425532,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.8125,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9855587121212122,
      "tokens_p.mean_in_band": 0.6205800374348959,
      "tokens_rate.above_band": 0.88,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12
    },
    {
      "epoch": 0.016622340425531915,
      "grad_norm": 402.86886331260774,
      "learning_rate": 8.215767634854771e-08,
      "loss": 1.5518,
      "step": 100,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.15,
      "success_rate.epoch.env.math": 0.9090909090909091,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.6194029850746269,
      "success_rate.epoch.env_macro_mean": 0.4990974510564063,
      "success_rate.epoch.global": 0.5808080808080808,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9950442950490073,
      "tokens_p.mean_in_band": 0.5289463141025641,
      "tokens_rate.above_band": 0.9026769509981851,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09732304900181488
    },
    {
      "epoch": 0.01745345744680851,
      "grad_norm": 452.85894919436043,
      "learning_rate": 8.630705394190871e-08,
      "loss": 1.1647,
      "step": 105,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.19047619047619047,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.6,
      "success_rate.epoch.env_macro_mean": 0.49374999999999997,
      "success_rate.epoch.global": 0.5721153846153846,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.16666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666667,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9875739644970414,
      "tokens_p.mean_in_band": 0.6503106725146199,
      "tokens_rate.above_band": 0.8316929133858267,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16830708661417323
    },
    {
      "epoch": 0.018284574468085107,
      "grad_norm": 214.39100868957553,
      "learning_rate": 9.04564315352697e-08,
      "loss": 1.2129,
      "step": 110,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.18181818181818182,
      "success_rate.epoch.env.math": 0.92,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.6095890410958904,
      "success_rate.epoch.env_macro_mean": 0.4942830457214019,
      "success_rate.epoch.global": 0.5779816513761468,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9930876655836041,
      "tokens_p.mean_in_band": 0.5333141321044547,
      "tokens_rate.above_band": 0.8600601891659502,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13993981083404988
    },
    {
      "epoch": 0.0191156914893617,
      "grad_norm": 622.4085970133178,
      "learning_rate": 9.46058091286307e-08,
      "loss": 1.5336,
      "step": 115,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.21739130434782608,
      "success_rate.epoch.env.math": 0.92,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.6103896103896104,
      "success_rate.epoch.env_macro_mean": 0.4965976143421796,
      "success_rate.epoch.global": 0.5789473684210527,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.990244708994709,
      "tokens_p.mean_in_band": 0.634046052631579,
      "tokens_rate.above_band": 0.8325991189427313,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16740088105726872
    },
    {
      "epoch": 0.0199468085106383,
      "grad_norm": 221.59897774532945,
      "learning_rate": 9.87551867219917e-08,
      "loss": 1.241,
      "step": 120,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.21739130434782608,
      "success_rate.epoch.env.math": 0.92,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.5975609756097561,
      "success_rate.epoch.env_macro_mean": 0.4949940349946978,
      "success_rate.epoch.global": 0.5714285714285714,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9883130081300813,
      "tokens_p.mean_below_band": 3.688037395477295e-07,
      "tokens_p.mean_in_band": 0.5776154891304348,
      "tokens_rate.above_band": 0.8367346938775511,
      "tokens_rate.below_band": 0.006802721088435374,
      "tokens_rate.in_band": 0.1564625850340136
    },
    {
      "epoch": 0.020777925531914893,
      "grad_norm": 180.77640150723752,
      "learning_rate": 1.0290456431535268e-07,
      "loss": 1.2421,
      "step": 125,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.6,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.9230769230769231,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5882352941176471,
      "success_rate.epoch.env_macro_mean": 0.4951640271493213,
      "success_rate.epoch.global": 0.5645161290322581,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9948089700996677,
      "tokens_p.mean_in_band": 0.5564692982456141,
      "tokens_rate.above_band": 0.840782122905028,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15921787709497207
    },
    {
      "epoch": 0.02160904255319149,
      "grad_norm": 335.97680274772983,
      "learning_rate": 1.0705394190871369e-07,
      "loss": 1.2298,
      "step": 130,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.24,
      "success_rate.epoch.env.math": 0.9230769230769231,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5795454545454546,
      "success_rate.epoch.env_macro_mean": 0.4892563686313687,
      "success_rate.epoch.global": 0.556420233463035,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.2857142857142857,
      "success_rate.window.env_macro_mean": 0.2619047619047619,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9968717750257998,
      "tokens_p.mean_in_band": 0.58953857421875,
      "tokens_rate.above_band": 0.968031968031968,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03196803196803197
    },
    {
      "epoch": 0.022440159574468085,
      "grad_norm": 667.7031214506737,
      "learning_rate": 1.1120331950207469e-07,
      "loss": 1.4165,
      "step": 135,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.2692307692307692,
      "success_rate.epoch.env.math": 0.9230769230769231,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.5769230769230769,
      "success_rate.epoch.env_macro_mean": 0.4981424825174825,
      "success_rate.epoch.global": 0.556390977443609,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9942434210526315,
      "tokens_p.mean_in_band": 0.6302400914634146,
      "tokens_rate.above_band": 0.9026128266033254,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09738717339667459
    },
    {
      "epoch": 0.02327127659574468,
      "grad_norm": 631.8988811708475,
      "learning_rate": 1.1535269709543567e-07,
      "loss": 1.4654,
      "step": 140,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.9259259259259259,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.5873015873015873,
      "success_rate.epoch.env_macro_mean": 0.49739207551707554,
      "success_rate.epoch.global": 0.5615942028985508,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9972662141779789,
      "tokens_p.mean_in_band": 0.5901772103658537,
      "tokens_rate.above_band": 0.9417613636363636,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05823863636363636
    },
    {
      "epoch": 0.024102393617021278,
      "grad_norm": 215.22841132298794,
      "learning_rate": 1.1950207468879667e-07,
      "loss": 1.1381,
      "step": 145,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.9285714285714286,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.5757575757575758,
      "success_rate.epoch.env_macro_mean": 0.4962797619047619,
      "success_rate.epoch.global": 0.5559440559440559,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9858630952380952,
      "tokens_p.mean_in_band": 0.6131184895833334,
      "tokens_rate.above_band": 0.7241379310344828,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.27586206896551724
    },
    {
      "epoch": 0.024933510638297872,
      "grad_norm": 551.1213200679001,
      "learning_rate": 1.2365145228215768e-07,
      "loss": 1.1888,
      "step": 150,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.2413793103448276,
      "success_rate.epoch.env.math": 0.9333333333333333,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.5882352941176471,
      "success_rate.epoch.env_macro_mean": 0.4973571285881124,
      "success_rate.epoch.global": 0.5661016949152542,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9991122159090909,
      "tokens_p.mean_in_band": 0.5625500801282052,
      "tokens_rate.above_band": 0.9475100942126514,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.052489905787348586
    },
    {
      "epoch": 0.02576462765957447,
      "grad_norm": 195.0533745906051,
      "learning_rate": 1.2780082987551865e-07,
      "loss": 1.2998,
      "step": 155,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.23333333333333334,
      "success_rate.epoch.env.math": 0.9333333333333333,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5924170616113744,
      "success_rate.epoch.env_macro_mean": 0.50160895088324,
      "success_rate.epoch.global": 0.5672131147540984,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9867738589211619,
      "tokens_p.mean_in_band": 0.6559836647727273,
      "tokens_rate.above_band": 0.8456140350877193,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1543859649122807
    },
    {
      "epoch": 0.026595744680851064,
      "grad_norm": 460.42342424184585,
      "learning_rate": 1.3195020746887966e-07,
      "loss": 1.2685,
      "step": 160,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.23333333333333334,
      "success_rate.epoch.env.math": 0.9090909090909091,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5898617511520737,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.554008208040466,
      "success_rate.epoch.global": 0.5682539682539682,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9964561855670103,
      "tokens_p.mean_in_band": 0.6408305921052632,
      "tokens_rate.above_band": 0.9387096774193548,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06129032258064516
    },
    {
      "epoch": 0.02742686170212766,
      "grad_norm": 414.22033111665974,
      "learning_rate": 1.3609958506224065e-07,
      "loss": 1.5084,
      "step": 165,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.25806451612903225,
      "success_rate.epoch.env.math": 0.9117647058823529,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5829596412556054,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5562863046727632,
      "success_rate.epoch.global": 0.5648148148148148,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.2857142857142857,
      "success_rate.window.env_macro_mean": 0.5714285714285714,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.991386217948718,
      "tokens_p.mean_in_band": 0.46859019886363634,
      "tokens_rate.above_band": 0.5864661654135338,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.41353383458646614
    },
    {
      "epoch": 0.028257978723404256,
      "grad_norm": 430.396377901239,
      "learning_rate": 1.4024896265560164e-07,
      "loss": 1.257,
      "step": 170,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.9142857142857143,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5851528384279476,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.555201797232365,
      "success_rate.epoch.global": 0.5645645645645646,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.39285714285714285,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9998577389984825,
      "tokens_p.mean_in_band": 0.5501185825892857,
      "tokens_rate.above_band": 0.9216783216783216,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07832167832167833
    },
    {
      "epoch": 0.02908909574468085,
      "grad_norm": 187.00444692959334,
      "learning_rate": 1.4439834024896266e-07,
      "loss": 1.3097,
      "step": 175,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.24242424242424243,
      "success_rate.epoch.env.math": 0.9142857142857143,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.5864978902953587,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5538989959876035,
      "success_rate.epoch.global": 0.5626822157434402,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.20833333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9946296296296296,
      "tokens_p.mean_below_band": 1.6391277313232422e-07,
      "tokens_p.mean_in_band": 0.5329137731481481,
      "tokens_rate.above_band": 0.9246575342465754,
      "tokens_rate.below_band": 0.0013698630136986301,
      "tokens_rate.in_band": 0.07397260273972603
    },
    {
      "epoch": 0.02992021276595745,
      "grad_norm": 573.263562105385,
      "learning_rate": 1.4854771784232365e-07,
      "loss": 1.4987,
      "step": 180,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.2571428571428571,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.5819672131147541,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5552955393119328,
      "success_rate.epoch.global": 0.5609065155807366,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.6428571428571429,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9948074018126888,
      "tokens_p.mean_in_band": 0.6211734693877551,
      "tokens_rate.above_band": 0.9310829817158931,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06891701828410689
    },
    {
      "epoch": 0.030751329787234043,
      "grad_norm": 426.9656445191381,
      "learning_rate": 1.5269709543568464e-07,
      "loss": 1.4918,
      "step": 185,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.24324324324324326,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.588,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5467053980387314,
      "success_rate.epoch.global": 0.5607734806629834,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9993459302325581,
      "tokens_p.mean_in_band": 0.6091392780172413,
      "tokens_rate.above_band": 0.956973293768546,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04302670623145401
    },
    {
      "epoch": 0.03158244680851064,
      "grad_norm": 593.9932514366184,
      "learning_rate": 1.5684647302904563e-07,
      "loss": 1.2742,
      "step": 190,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.23076923076923078,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.5836575875486382,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5443078058512559,
      "success_rate.epoch.global": 0.553763440860215,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.14285714285714285,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9953314266487214,
      "tokens_p.mean_in_band": 0.5749399038461539,
      "tokens_rate.above_band": 0.9195544554455446,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08044554455445545
    },
    {
      "epoch": 0.03241356382978723,
      "grad_norm": 237.91590431618616,
      "learning_rate": 1.6099585062240665e-07,
      "loss": 1.3347,
      "step": 195,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.21951219512195122,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.5795454545454546,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5426001204456489,
      "success_rate.epoch.global": 0.5485564304461942,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9949776785714286,
      "tokens_p.mean_below_band": 8.585629984736443e-10,
      "tokens_p.mean_in_band": 0.5992647058823529,
      "tokens_rate.above_band": 0.9134253450439147,
      "tokens_rate.below_band": 0.0012547051442910915,
      "tokens_rate.in_band": 0.08531994981179424
    },
    {
      "epoch": 0.03324468085106383,
      "grad_norm": 344.97766277721,
      "learning_rate": 1.651452282157676e-07,
      "loss": 1.3244,
      "step": 200,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.23809523809523808,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.5845588235294118,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5447589810334909,
      "success_rate.epoch.global": 0.5524296675191815,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9910102739726028,
      "tokens_p.mean_in_band": 0.7010789903856459,
      "tokens_rate.above_band": 0.8390804597701149,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16091954022988506
    },
    {
      "epoch": 0.03407579787234043,
      "grad_norm": 285.6487390063705,
      "learning_rate": 1.6929460580912862e-07,
      "loss": 1.1814,
      "step": 205,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.9166666666666666,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.5827338129496403,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5458789534029341,
      "success_rate.epoch.global": 0.5513784461152882,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9866513437057991,
      "tokens_p.mean_in_band": 0.7105287063953488,
      "tokens_rate.above_band": 0.8915510718789408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10844892812105927
    },
    {
      "epoch": 0.03490691489361702,
      "grad_norm": 418.8657321104007,
      "learning_rate": 1.7344398340248961e-07,
      "loss": 1.2693,
      "step": 210,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.918918918918919,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.5824561403508772,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5456898544101846,
      "success_rate.epoch.global": 0.5514705882352942,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9955065359477124,
      "tokens_p.mean_in_band": 0.5977038871951219,
      "tokens_rate.above_band": 0.8818443804034583,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11815561959654179
    },
    {
      "epoch": 0.035738031914893616,
      "grad_norm": 287.1345069856305,
      "learning_rate": 1.775933609958506e-07,
      "loss": 1.2884,
      "step": 215,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.2391304347826087,
      "success_rate.epoch.env.math": 0.9230769230769231,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.584192439862543,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5451370475715489,
      "success_rate.epoch.global": 0.5526315789473685,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9946584791386271,
      "tokens_p.mean_in_band": 0.6318359375,
      "tokens_rate.above_band": 0.925280199252802,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.074719800747198
    },
    {
      "epoch": 0.036569148936170214,
      "grad_norm": 386.6212346601495,
      "learning_rate": 1.8174273858921162e-07,
      "loss": 1.2632,
      "step": 220,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.2391304347826087,
      "success_rate.epoch.env.math": 0.925,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.5824915824915825,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5389888991267224,
      "success_rate.epoch.global": 0.550351288056206,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9949178200692042,
      "tokens_p.mean_below_band": 2.455635694786906e-10,
      "tokens_p.mean_in_band": 0.505401611328125,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.0032679738562091504,
      "tokens_rate.in_band": 0.05228758169934641
    },
    {
      "epoch": 0.03740026595744681,
      "grad_norm": 260.928410841472,
      "learning_rate": 1.858921161825726e-07,
      "loss": 1.2045,
      "step": 225,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.2708333333333333,
      "success_rate.epoch.env.math": 0.9285714285714286,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.5761589403973509,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5472551469581075,
      "success_rate.epoch.global": 0.551487414187643,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.2,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9945282101167315,
      "tokens_p.mean_in_band": 0.5966796875,
      "tokens_rate.above_band": 0.9413919413919414,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05860805860805861
    },
    {
      "epoch": 0.0382313829787234,
      "grad_norm": 275.0008213682556,
      "learning_rate": 1.900414937759336e-07,
      "loss": 1.1255,
      "step": 230,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.2653061224489796,
      "success_rate.epoch.env.math": 0.9302325581395349,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.5732899022801303,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5542768081243968,
      "success_rate.epoch.global": 0.5515695067264574,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0001378307939053,
      "tokens_p.mean_in_band": 0.6113489029255319,
      "tokens_rate.above_band": 0.9815033451397088,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018496654860291225
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 568.8843764892392,
      "learning_rate": 1.941908713692946e-07,
      "loss": 1.242,
      "step": 235,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.2549019607843137,
      "success_rate.epoch.env.math": 0.9130434782608695,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.572347266881029,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5511061551307931,
      "success_rate.epoch.global": 0.5494505494505495,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.38888888888888884,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9971608231707317,
      "tokens_p.mean_in_band": 0.5733072916666667,
      "tokens_rate.above_band": 0.956268221574344,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043731778425655975
    },
    {
      "epoch": 0.0398936170212766,
      "grad_norm": 344.86458523370806,
      "learning_rate": 1.983402489626556e-07,
      "loss": 1.4863,
      "step": 240,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.2549019607843137,
      "success_rate.epoch.env.math": 0.9148936170212766,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.5759493670886076,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5420248419303145,
      "success_rate.epoch.global": 0.5495689655172413,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9974385245901639,
      "tokens_p.mean_in_band": 0.5966145833333333,
      "tokens_rate.above_band": 0.9312977099236641,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06870229007633588
    },
    {
      "epoch": 0.04072473404255319,
      "grad_norm": 185.59145960225354,
      "learning_rate": 1.9999999361088134e-07,
      "loss": 1.4664,
      "step": 245,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.24528301886792453,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.5736677115987461,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5350598170411204,
      "success_rate.epoch.global": 0.5443037974683544,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.2,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9974609375,
      "tokens_p.mean_in_band": 0.5228515625,
      "tokens_rate.above_band": 0.9411764705882353,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.058823529411764705
    },
    {
      "epoch": 0.041555851063829786,
      "grad_norm": 455.47015837406633,
      "learning_rate": 1.999999545662822e-07,
      "loss": 1.351,
      "step": 250,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.23636363636363636,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.047619047619047616,
      "success_rate.epoch.env.science": 0.5679012345679012,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5296965037705779,
      "success_rate.epoch.global": 0.5351239669421488,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.2,
      "success_rate.window.env_macro_mean": 0.05,
      "success_rate.window.global": 0.1,
      "tokens_p.mean_above_band": 0.9975178207739308,
      "tokens_p.mean_below_band": 6.693881005048752e-10,
      "tokens_p.mean_in_band": 0.5587733477011494,
      "tokens_rate.above_band": 0.9436258808456118,
      "tokens_rate.below_band": 0.0006406149903907751,
      "tokens_rate.in_band": 0.05573350416399744
    },
    {
      "epoch": 0.042386968085106384,
      "grad_norm": 461.8860860264364,
      "learning_rate": 1.9999988002666344e-07,
      "loss": 1.2482,
      "step": 255,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.375,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.25,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.047619047619047616,
      "success_rate.epoch.env.science": 0.5709969788519638,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5287778490950696,
      "success_rate.epoch.global": 0.537525354969574,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.995,
      "tokens_p.mean_in_band": 0.6566540948275862,
      "tokens_rate.above_band": 0.9476534296028881,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.052346570397111915
    },
    {
      "epoch": 0.04321808510638298,
      "grad_norm": 277.7702413417161,
      "learning_rate": 1.999997699921574e-07,
      "loss": 1.2997,
      "step": 260,
      "success_rate.epoch.env.abd": 0.0,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.2631578947368421,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.047619047619047616,
      "success_rate.epoch.env.science": 0.5722713864306784,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.534466405561504,
      "success_rate.epoch.global": 0.5407554671968191,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9955787781350482,
      "tokens_p.mean_below_band": 2.7284841053187847e-12,
      "tokens_p.mean_in_band": 0.5538793103448276,
      "tokens_rate.above_band": 0.9120234604105572,
      "tokens_rate.below_band": 0.002932551319648094,
      "tokens_rate.in_band": 0.08504398826979472
    },
    {
      "epoch": 0.04404920212765957,
      "grad_norm": 455.8428416990228,
      "learning_rate": 1.9999962446295936e-07,
      "loss": 1.5878,
      "step": 265,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.27586206896551724,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.045454545454545456,
      "success_rate.epoch.env.science": 0.5780346820809249,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.558500068640884,
      "success_rate.epoch.global": 0.5458089668615984,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9926075268817204,
      "tokens_p.mean_in_band": 0.7098214285714286,
      "tokens_rate.above_band": 0.850609756097561,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14939024390243902
    },
    {
      "epoch": 0.04488031914893617,
      "grad_norm": 357.26486693076953,
      "learning_rate": 1.9999944343932754e-07,
      "loss": 1.5464,
      "step": 270,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.29508196721311475,
      "success_rate.epoch.env.math": 0.9038461538461539,
      "success_rate.epoch.env.sat": 0.045454545454545456,
      "success_rate.epoch.env.science": 0.58,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5057257764200869,
      "success_rate.epoch.global": 0.5487571701720841,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6041666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9938058035714286,
      "tokens_p.mean_in_band": 0.6649682971014492,
      "tokens_rate.above_band": 0.890302066772655,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10969793322734499
    },
    {
      "epoch": 0.04571143617021277,
      "grad_norm": 549.8655835803091,
      "learning_rate": 1.999992269215833e-07,
      "loss": 1.4171,
      "step": 275,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.3064516129032258,
      "success_rate.epoch.env.math": 0.9056603773584906,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5786516853932584,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5112495922505863,
      "success_rate.epoch.global": 0.549718574108818,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9925223214285714,
      "tokens_p.mean_below_band": 7.566995918750763e-10,
      "tokens_p.mean_in_band": 0.6725694444444444,
      "tokens_rate.above_band": 0.8588957055214724,
      "tokens_rate.below_band": 0.003067484662576687,
      "tokens_rate.in_band": 0.13803680981595093
    },
    {
      "epoch": 0.04654255319148936,
      "grad_norm": 395.91521245328533,
      "learning_rate": 1.9999897491011083e-07,
      "loss": 1.2034,
      "step": 280,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.31746031746031744,
      "success_rate.epoch.env.math": 0.9056603773584906,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5741758241758241,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5070914588487655,
      "success_rate.epoch.global": 0.5469613259668509,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.375,
      "success_rate.window.env_macro_mean": 0.4583333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.992175702204772,
      "tokens_p.mean_below_band": 4.842877388000488e-07,
      "tokens_p.mean_in_band": 0.5022039592352092,
      "tokens_rate.above_band": 0.826510234648028,
      "tokens_rate.below_band": 0.0004992511233150275,
      "tokens_rate.in_band": 0.17299051422865702
    },
    {
      "epoch": 0.04737367021276596,
      "grad_norm": 223.10287870494537,
      "learning_rate": 1.9999868740535746e-07,
      "loss": 1.2274,
      "step": 285,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3230769230769231,
      "success_rate.epoch.env.math": 0.9074074074074074,
      "success_rate.epoch.env.sat": 0.08,
      "success_rate.epoch.env.science": 0.5760869565217391,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5009770565809214,
      "success_rate.epoch.global": 0.546112115732369,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9928622412562456,
      "tokens_p.mean_in_band": 0.6591036676646707,
      "tokens_rate.above_band": 0.8934948979591837,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10650510204081633
    },
    {
      "epoch": 0.048204787234042555,
      "grad_norm": 191.06301969150624,
      "learning_rate": 1.9999836440783338e-07,
      "loss": 1.3325,
      "step": 290,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3283582089552239,
      "success_rate.epoch.env.math": 0.9074074074074074,
      "success_rate.epoch.env.sat": 0.08,
      "success_rate.epoch.env.science": 0.574468085106383,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5013839915212485,
      "success_rate.epoch.global": 0.5452930728241563,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9963715529753265,
      "tokens_p.mean_in_band": 0.5697443181818181,
      "tokens_rate.above_band": 0.9260752688172043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0739247311827957
    },
    {
      "epoch": 0.049035904255319146,
      "grad_norm": 375.5001620168459,
      "learning_rate": 1.9999800591811186e-07,
      "loss": 1.1717,
      "step": 295,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3382352941176471,
      "success_rate.epoch.env.math": 0.9090909090909091,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.577023498694517,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5026105556720414,
      "success_rate.epoch.global": 0.5479930191972077,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9929872047244095,
      "tokens_p.mean_in_band": 0.6797022964015151,
      "tokens_rate.above_band": 0.8850174216027874,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11498257839721254
    },
    {
      "epoch": 0.049867021276595744,
      "grad_norm": 393.881222663392,
      "learning_rate": 1.999976119368291e-07,
      "loss": 1.2225,
      "step": 300,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3333333333333333,
      "success_rate.epoch.env.math": 0.8793103448275862,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5732647814910026,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4983393065330246,
      "success_rate.epoch.global": 0.5437392795883362,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.3333333333333333,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.2222222222222222,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.990234375,
      "tokens_p.mean_in_band": 0.5426897321428571,
      "tokens_rate.above_band": 0.8372093023255814,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16279069767441862
    },
    {
      "epoch": 0.05069813829787234,
      "grad_norm": 207.28229588926519,
      "learning_rate": 1.9999718246468435e-07,
      "loss": 0.9999,
      "step": 305,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.32857142857142857,
      "success_rate.epoch.env.math": 0.8793103448275862,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5778894472361809,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4983240577533883,
      "success_rate.epoch.global": 0.5463743676222597,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9986795774647887,
      "tokens_p.mean_in_band": 0.5867745535714286,
      "tokens_rate.above_band": 0.9287790697674418,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07122093023255814
    },
    {
      "epoch": 0.05152925531914894,
      "grad_norm": 236.4680773613799,
      "learning_rate": 1.9999671750243982e-07,
      "loss": 1.0784,
      "step": 310,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.32857142857142857,
      "success_rate.epoch.env.math": 0.8833333333333333,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.583743842364532,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4994215448238436,
      "success_rate.epoch.global": 0.5522388059701493,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9877232142857143,
      "tokens_p.mean_in_band": 0.7590169270833333,
      "tokens_rate.above_band": 0.8818897637795275,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11811023622047244
    },
    {
      "epoch": 0.05236037234042553,
      "grad_norm": 320.03233321273206,
      "learning_rate": 1.9999621705092072e-07,
      "loss": 1.4287,
      "step": 315,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.32432432432432434,
      "success_rate.epoch.env.math": 0.8852459016393442,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5878048780487805,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4996133781286387,
      "success_rate.epoch.global": 0.553921568627451,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9957317073170732,
      "tokens_p.mean_in_band": 0.6130514705882353,
      "tokens_rate.above_band": 0.9731012658227848,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02689873417721519
    },
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 367.52734006325716,
      "learning_rate": 1.999956811110152e-07,
      "loss": 1.6472,
      "step": 320,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3116883116883117,
      "success_rate.epoch.env.math": 0.8852459016393442,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5875299760191847,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4981788320546823,
      "success_rate.epoch.global": 0.5514469453376206,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9966280798640612,
      "tokens_p.mean_in_band": 0.529296875,
      "tokens_rate.above_band": 0.9453815261044177,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05461847389558233
    },
    {
      "epoch": 0.054022606382978726,
      "grad_norm": 421.4314992788045,
      "learning_rate": 1.9999510968367442e-07,
      "loss": 1.0747,
      "step": 325,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3037974683544304,
      "success_rate.epoch.env.math": 0.873015873015873,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5843230403800475,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.446028168089565,
      "success_rate.epoch.global": 0.5467511885895404,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.1875,
      "success_rate.window.global": 0.2,
      "tokens_p.mean_above_band": 1.000200491873396,
      "tokens_p.mean_below_band": 4.922640073345974e-10,
      "tokens_p.mean_in_band": 0.5323585304054054,
      "tokens_rate.above_band": 0.9685169842584921,
      "tokens_rate.below_band": 0.0008285004142502071,
      "tokens_rate.in_band": 0.030654515327257662
    },
    {
      "epoch": 0.05485372340425532,
      "grad_norm": 296.71467421076136,
      "learning_rate": 1.999945027699125e-07,
      "loss": 1.0972,
      "step": 330,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.30120481927710846,
      "success_rate.epoch.env.math": 0.8769230769230769,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5811764705882353,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.445844966593372,
      "success_rate.epoch.global": 0.5444617784711389,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9984885126964933,
      "tokens_p.mean_in_band": 0.6131036931818182,
      "tokens_rate.above_band": 0.9494833524684271,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0505166475315729
    },
    {
      "epoch": 0.055684840425531915,
      "grad_norm": 215.43312239144745,
      "learning_rate": 1.9999386037080662e-07,
      "loss": 1.2842,
      "step": 335,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.30120481927710846,
      "success_rate.epoch.env.math": 0.8676470588235294,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5787037037037037,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.444670088094964,
      "success_rate.epoch.global": 0.543778801843318,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.5476190476190476,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.986328125,
      "tokens_p.mean_in_band": 0.6127232142857143,
      "tokens_rate.above_band": 0.7619047619047619,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.23809523809523808
    },
    {
      "epoch": 0.05651595744680851,
      "grad_norm": 199.4685504028312,
      "learning_rate": 1.9999318248749688e-07,
      "loss": 1.1739,
      "step": 340,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.30120481927710846,
      "success_rate.epoch.env.math": 0.8714285714285714,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.5740318906605922,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4479998614699605,
      "success_rate.epoch.global": 0.5431164901664145,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.2857142857142857,
      "success_rate.window.env_macro_mean": 0.7619047619047619,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9866573033707865,
      "tokens_p.mean_below_band": 1.9190338207408786e-10,
      "tokens_p.mean_in_band": 0.5721153846153846,
      "tokens_rate.above_band": 0.8682926829268293,
      "tokens_rate.below_band": 0.004878048780487805,
      "tokens_rate.in_band": 0.12682926829268293
    },
    {
      "epoch": 0.0573470744680851,
      "grad_norm": 356.2683257848366,
      "learning_rate": 1.9999246912118632e-07,
      "loss": 1.2012,
      "step": 345,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5625,
      "success_rate.epoch.env.logic": 0.30120481927710846,
      "success_rate.epoch.env.math": 0.8611111111111112,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.5717488789237668,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.44965648093119864,
      "success_rate.epoch.global": 0.5424739195230999,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.6428571428571429,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.98296875,
      "tokens_p.mean_below_band": 2.6756374893466273e-14,
      "tokens_p.mean_in_band": 0.5924161585365854,
      "tokens_rate.above_band": 0.9049773755656109,
      "tokens_rate.below_band": 0.0022624434389140274,
      "tokens_rate.in_band": 0.09276018099547512
    },
    {
      "epoch": 0.0581781914893617,
      "grad_norm": 175.17612522561566,
      "learning_rate": 1.99991720273141e-07,
      "loss": 1.2566,
      "step": 350,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.29069767441860467,
      "success_rate.epoch.env.math": 0.8611111111111112,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.5698447893569845,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.45098888690043476,
      "success_rate.epoch.global": 0.5397058823529411,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.35,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9938968428781204,
      "tokens_p.mean_in_band": 0.5026939655172413,
      "tokens_rate.above_band": 0.9399585921325052,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.060041407867494824
    },
    {
      "epoch": 0.0590093085106383,
      "grad_norm": 461.050063676608,
      "learning_rate": 1.9999093594468995e-07,
      "loss": 1.2682,
      "step": 355,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.2840909090909091,
      "success_rate.epoch.env.math": 0.8611111111111112,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.5689277899343544,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4477929014028458,
      "success_rate.epoch.global": 0.5362318840579711,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.125,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9958196271929824,
      "tokens_p.mean_in_band": 0.538671875,
      "tokens_rate.above_band": 0.9334698055271239,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06653019447287616
    },
    {
      "epoch": 0.0598404255319149,
      "grad_norm": 297.2931214793317,
      "learning_rate": 1.9999011613722514e-07,
      "loss": 1.0666,
      "step": 360,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.2808988764044944,
      "success_rate.epoch.env.math": 0.8611111111111112,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.572961373390558,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4478770564798246,
      "success_rate.epoch.global": 0.5385714285714286,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9959612277867528,
      "tokens_p.mean_in_band": 0.5782596982758621,
      "tokens_rate.above_band": 0.9552469135802469,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044753086419753084
    },
    {
      "epoch": 0.06067154255319149,
      "grad_norm": 294.8580182370888,
      "learning_rate": 1.9998926085220154e-07,
      "loss": 1.2332,
      "step": 365,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.2808988764044944,
      "success_rate.epoch.env.math": 0.8648648648648649,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.5759493670886076,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.44855123122500495,
      "success_rate.epoch.global": 0.5422535211267606,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9869237588652482,
      "tokens_p.mean_below_band": 4.3655745685100555e-09,
      "tokens_p.mean_in_band": 0.735,
      "tokens_rate.above_band": 0.844311377245509,
      "tokens_rate.below_band": 0.005988023952095809,
      "tokens_rate.in_band": 0.1497005988023952
    },
    {
      "epoch": 0.061502659574468085,
      "grad_norm": 172.51017172216643,
      "learning_rate": 1.999883700911371e-07,
      "loss": 1.3382,
      "step": 370,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.38095238095238093,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.28888888888888886,
      "success_rate.epoch.env.math": 0.8666666666666667,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.5744234800838575,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4469935248009419,
      "success_rate.epoch.global": 0.541029207232267,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.4583333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9888229927007299,
      "tokens_p.mean_in_band": 0.4854712701612903,
      "tokens_rate.above_band": 0.6734550561797753,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.3265449438202247
    },
    {
      "epoch": 0.06233377659574468,
      "grad_norm": 604.1278280415459,
      "learning_rate": 1.9998744385561267e-07,
      "loss": 1.5613,
      "step": 375,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.38095238095238093,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.2967032967032967,
      "success_rate.epoch.env.math": 0.868421052631579,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.5743801652892562,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4479460726994137,
      "success_rate.epoch.global": 0.5425824175824175,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9900873655913979,
      "tokens_p.mean_in_band": 0.6736727627840909,
      "tokens_rate.above_band": 0.8942307692307693,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10576923076923077
    },
    {
      "epoch": 0.06316489361702128,
      "grad_norm": 229.6209398930736,
      "learning_rate": 1.9998648214727209e-07,
      "loss": 1.0662,
      "step": 380,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.29347826086956524,
      "success_rate.epoch.env.math": 0.8734177215189873,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.5766871165644172,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.45116778394615037,
      "success_rate.epoch.global": 0.5460704607046071,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0001265182186234,
      "tokens_p.mean_in_band": 0.5583298141891891,
      "tokens_rate.above_band": 0.9639024390243902,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03609756097560975
    },
    {
      "epoch": 0.06399601063829788,
      "grad_norm": 265.1657256856042,
      "learning_rate": 1.9998548496782216e-07,
      "loss": 1.1013,
      "step": 385,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.2872340425531915,
      "success_rate.epoch.env.math": 0.875,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.5757575757575758,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4506086358819301,
      "success_rate.epoch.global": 0.5448460508701473,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.5238095238095238,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.998913421418637,
      "tokens_p.mean_in_band": 0.5935763888888889,
      "tokens_rate.above_band": 0.9410994764397905,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.058900523560209424
    },
    {
      "epoch": 0.06482712765957446,
      "grad_norm": 172.95453270951595,
      "learning_rate": 1.9998445231903263e-07,
      "loss": 1.4177,
      "step": 390,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5789473684210527,
      "success_rate.epoch.env.logic": 0.28421052631578947,
      "success_rate.epoch.env.math": 0.875,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5756972111553785,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.452294601498313,
      "success_rate.epoch.global": 0.5442536327608983,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.39285714285714285,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9935334158415842,
      "tokens_p.mean_below_band": 3.342393029015511e-11,
      "tokens_p.mean_in_band": 0.5884811046511628,
      "tokens_rate.above_band": 0.9582542694497154,
      "tokens_rate.below_band": 0.0009487666034155598,
      "tokens_rate.in_band": 0.04079696394686907
    },
    {
      "epoch": 0.06565824468085106,
      "grad_norm": 357.3514810176116,
      "learning_rate": 1.999833842027362e-07,
      "loss": 1.0726,
      "step": 395,
      "success_rate.epoch.env.abd": 0.2,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5789473684210527,
      "success_rate.epoch.env.logic": 0.27835051546391754,
      "success_rate.epoch.env.math": 0.875,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5725490196078431,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4513937812583723,
      "success_rate.epoch.global": 0.5410691003911343,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.375,
      "success_rate.window.env_macro_mean": 0.1875,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9976134726224783,
      "tokens_p.mean_in_band": 0.5455923507462687,
      "tokens_rate.above_band": 0.911957950065703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08804204993429698
    },
    {
      "epoch": 0.06648936170212766,
      "grad_norm": 278.3049999132479,
      "learning_rate": 1.9998228062082854e-07,
      "loss": 1.2295,
      "step": 400,
      "success_rate.epoch.env.abd": 0.16666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.55,
      "success_rate.epoch.env.logic": 0.27835051546391754,
      "success_rate.epoch.env.math": 0.875,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.5689320388349515,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4473040130056445,
      "success_rate.epoch.global": 0.5373711340206185,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.3333333333333333,
      "success_rate.window.env.science": 0.2,
      "success_rate.window.env_macro_mean": 0.13333333333333333,
      "success_rate.window.global": 0.2,
      "tokens_p.mean_above_band": 0.993797195253506,
      "tokens_p.mean_in_band": 0.5444269825918762,
      "tokens_rate.above_band": 0.8776331360946745,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12236686390532545
    },
    {
      "epoch": 0.06732047872340426,
      "grad_norm": 327.2404418386426,
      "learning_rate": 1.999811415752682e-07,
      "loss": 1.2184,
      "step": 405,
      "success_rate.epoch.env.abd": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.55,
      "success_rate.epoch.env.logic": 0.29292929292929293,
      "success_rate.epoch.env.math": 0.875,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.5747126436781609,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4612447131412648,
      "success_rate.epoch.global": 0.5432569974554707,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9920774647887324,
      "tokens_p.mean_in_band": 0.7473958333333334,
      "tokens_rate.above_band": 0.9403973509933775,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.059602649006622516
    },
    {
      "epoch": 0.06815159574468085,
      "grad_norm": 649.8902582794741,
      "learning_rate": 1.999799670680767e-07,
      "loss": 1.2794,
      "step": 410,
      "success_rate.epoch.env.abd": 0.25,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3,
      "success_rate.epoch.env.math": 0.8765432098765432,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.5768500948766604,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.46051249064848054,
      "success_rate.epoch.global": 0.5452261306532663,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9873650637880275,
      "tokens_p.mean_in_band": 0.24865540679039952,
      "tokens_rate.above_band": 0.2330208095129202,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.7669791904870799
    },
    {
      "epoch": 0.06898271276595745,
      "grad_norm": 441.26911688802744,
      "learning_rate": 1.9997875710133858e-07,
      "loss": 1.1711,
      "step": 415,
      "success_rate.epoch.env.abd": 0.25,
      "success_rate.epoch.env.agentgym:alfworld": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3,
      "success_rate.epoch.env.math": 0.8690476190476191,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.5778611632270169,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.46243320836109814,
      "success_rate.epoch.global": 0.5471464019851117,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973591549295775,
      "tokens_p.mean_below_band": 1.4342367882225204e-07,
      "tokens_p.mean_in_band": 0.6630345394736842,
      "tokens_rate.above_band": 0.9311475409836065,
      "tokens_rate.below_band": 0.006557377049180328,
      "tokens_rate.in_band": 0.06229508196721312
    },
    {
      "epoch": 0.06981382978723404,
      "grad_norm": 496.73959779342533,
      "learning_rate": 1.9997751167720117e-07,
      "loss": 1.3355,
      "step": 420,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3,
      "success_rate.epoch.env.math": 0.8705882352941177,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.5767097966728281,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.45969435555255134,
      "success_rate.epoch.global": 0.5465686274509803,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9919117647058824,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_p.mean_in_band": 0.6492745535714286,
      "tokens_rate.above_band": 0.918918918918919,
      "tokens_rate.below_band": 0.005405405405405406,
      "tokens_rate.in_band": 0.07567567567567568
    },
    {
      "epoch": 0.07064494680851063,
      "grad_norm": 628.2080255418654,
      "learning_rate": 1.9997623079787476e-07,
      "loss": 1.1262,
      "step": 425,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3,
      "success_rate.epoch.env.math": 0.8620689655172413,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.5766423357664233,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4570240882813247,
      "success_rate.epoch.global": 0.5460048426150121,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9963908450704225,
      "tokens_p.mean_in_band": 0.6424479166666667,
      "tokens_rate.above_band": 0.922077922077922,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07792207792207792
    },
    {
      "epoch": 0.07147606382978723,
      "grad_norm": 231.12520962533006,
      "learning_rate": 1.9997491446563267e-07,
      "loss": 1.1231,
      "step": 430,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3,
      "success_rate.epoch.env.math": 0.8636363636363636,
      "success_rate.epoch.env.sat": 0.14705882352941177,
      "success_rate.epoch.env.science": 0.5801801801801801,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.462452616099675,
      "success_rate.epoch.global": 0.5502392344497608,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9642857142857143,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964330024813896,
      "tokens_p.mean_in_band": 0.63916015625,
      "tokens_rate.above_band": 0.9710843373493976,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02891566265060241
    },
    {
      "epoch": 0.07230718085106383,
      "grad_norm": 297.4473271435285,
      "learning_rate": 1.99973562682811e-07,
      "loss": 0.9839,
      "step": 435,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3137254901960784,
      "success_rate.epoch.env.math": 0.8539325842696629,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.5796064400715564,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.4606849374122158,
      "success_rate.epoch.global": 0.5491124260355029,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.3,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9964139344262295,
      "tokens_p.mean_below_band": 4.192202140984591e-13,
      "tokens_p.mean_in_band": 0.5060221354166666,
      "tokens_rate.above_band": 0.9512670565302144,
      "tokens_rate.below_band": 0.001949317738791423,
      "tokens_rate.in_band": 0.04678362573099415
    },
    {
      "epoch": 0.07313829787234043,
      "grad_norm": 175.33723100290754,
      "learning_rate": 1.9997217545180892e-07,
      "loss": 1.2852,
      "step": 440,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.32038834951456313,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.5780141843971631,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5104663864217674,
      "success_rate.epoch.global": 0.550351288056206,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9927273882113821,
      "tokens_p.mean_in_band": 0.671875,
      "tokens_rate.above_band": 0.9389312977099237,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061068702290076333
    },
    {
      "epoch": 0.07396941489361702,
      "grad_norm": 406.97798204714803,
      "learning_rate": 1.9997075277508834e-07,
      "loss": 1.3382,
      "step": 445,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.32038834951456313,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.5741710296684118,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5118879650355646,
      "success_rate.epoch.global": 0.5486111111111112,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9934440559440559,
      "tokens_p.mean_below_band": 3.774403012357652e-11,
      "tokens_p.mean_in_band": 0.5091959635416666,
      "tokens_rate.above_band": 0.9196141479099679,
      "tokens_rate.below_band": 0.003215434083601286,
      "tokens_rate.in_band": 0.07717041800643087
    },
    {
      "epoch": 0.07480053191489362,
      "grad_norm": 334.93766256356366,
      "learning_rate": 1.999692946551742e-07,
      "loss": 1.4068,
      "step": 450,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.3238095238095238,
      "success_rate.epoch.env.math": 0.8586956521739131,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.5729166666666666,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5122261110650439,
      "success_rate.epoch.global": 0.5482758620689655,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9946907600596125,
      "tokens_p.mean_below_band": 4.6629367034256575e-15,
      "tokens_p.mean_in_band": 0.6300698138297872,
      "tokens_rate.above_band": 0.933240611961057,
      "tokens_rate.below_band": 0.0013908205841446453,
      "tokens_rate.in_band": 0.06536856745479833
    },
    {
      "epoch": 0.0756316489361702,
      "grad_norm": 683.6804685688163,
      "learning_rate": 1.9996780109465432e-07,
      "loss": 1.186,
      "step": 455,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.3238095238095238,
      "success_rate.epoch.env.math": 0.8602150537634409,
      "success_rate.epoch.env.sat": 0.1388888888888889,
      "success_rate.epoch.env.science": 0.5711835334476844,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5118459305561612,
      "success_rate.epoch.global": 0.5472127417519909,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.375,
      "success_rate.window.env_macro_mean": 0.4583333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9900914634146342,
      "tokens_p.mean_in_band": 0.5889811197916667,
      "tokens_rate.above_band": 0.7321428571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.26785714285714285
    },
    {
      "epoch": 0.0764627659574468,
      "grad_norm": 155.9163180652835,
      "learning_rate": 1.9996627209617939e-07,
      "loss": 1.1827,
      "step": 460,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.32710280373831774,
      "success_rate.epoch.env.math": 0.8617021276595744,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.5738539898132428,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5121820265958642,
      "success_rate.epoch.global": 0.5489313835770528,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977647867950481,
      "tokens_p.mean_in_band": 0.6150323275862069,
      "tokens_rate.above_band": 0.9261146496815287,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07388535031847134
    },
    {
      "epoch": 0.0772938829787234,
      "grad_norm": 263.62560819462385,
      "learning_rate": 1.9996470766246299e-07,
      "loss": 1.3302,
      "step": 465,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6086956521739131,
      "success_rate.epoch.env.logic": 0.32727272727272727,
      "success_rate.epoch.env.math": 0.8617021276595744,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.5733558178752108,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5142686464463828,
      "success_rate.epoch.global": 0.5483870967741935,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9964634773662552,
      "tokens_p.mean_in_band": 0.6992017663043478,
      "tokens_rate.above_band": 0.9441476444876153,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.055852355512384655
    },
    {
      "epoch": 0.078125,
      "grad_norm": 425.7380637797864,
      "learning_rate": 1.999631077962816e-07,
      "loss": 1.1097,
      "step": 470,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.41379310344827586,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6086956521739131,
      "success_rate.epoch.env.logic": 0.32727272727272727,
      "success_rate.epoch.env.math": 0.8556701030927835,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.5742904841402338,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5124617661350265,
      "success_rate.epoch.global": 0.5489548954895489,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9961666666666666,
      "tokens_p.mean_in_band": 0.60198974609375,
      "tokens_rate.above_band": 0.959079283887468,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04092071611253197
    },
    {
      "epoch": 0.0789561170212766,
      "grad_norm": 257.61330518805875,
      "learning_rate": 1.9996147250047465e-07,
      "loss": 1.2895,
      "step": 475,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.41379310344827586,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6,
      "success_rate.epoch.env.logic": 0.33035714285714285,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.5745033112582781,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5121048883694465,
      "success_rate.epoch.global": 0.5495103373231773,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.65,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9957741171403962,
      "tokens_p.mean_below_band": 8.866190910339355e-07,
      "tokens_p.mean_in_band": 0.49592791863207547,
      "tokens_rate.above_band": 0.9561457689932057,
      "tokens_rate.below_band": 0.00020588840848260242,
      "tokens_rate.in_band": 0.04364834259831171
    },
    {
      "epoch": 0.0797872340425532,
      "grad_norm": 646.3933282739685,
      "learning_rate": 1.9995980177794433e-07,
      "loss": 1.5417,
      "step": 480,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6,
      "success_rate.epoch.env.logic": 0.33035714285714285,
      "success_rate.epoch.env.math": 0.8484848484848485,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.5721311475409836,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5249997420824545,
      "success_rate.epoch.global": 0.5474137931034483,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9934895833333334,
      "tokens_p.mean_in_band": 0.5028545673076923,
      "tokens_rate.above_band": 0.9509433962264151,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04905660377358491
    },
    {
      "epoch": 0.0806183510638298,
      "grad_norm": 486.91008628123825,
      "learning_rate": 1.9995809563165579e-07,
      "loss": 1.1777,
      "step": 485,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6,
      "success_rate.epoch.env.logic": 0.33035714285714285,
      "success_rate.epoch.env.math": 0.8431372549019608,
      "success_rate.epoch.env.sat": 0.13157894736842105,
      "success_rate.epoch.env.science": 0.5762987012987013,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5245691759377377,
      "success_rate.epoch.global": 0.5501066098081023,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9915149006622517,
      "tokens_p.mean_in_band": 0.5921630859375,
      "tokens_rate.above_band": 0.825136612021858,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17486338797814208
    },
    {
      "epoch": 0.08144946808510638,
      "grad_norm": 324.6965320642356,
      "learning_rate": 1.99956354064637e-07,
      "loss": 1.0392,
      "step": 490,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.33035714285714285,
      "success_rate.epoch.env.math": 0.8490566037735849,
      "success_rate.epoch.env.sat": 0.13157894736842105,
      "success_rate.epoch.env.science": 0.5751211631663974,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5263988510399137,
      "success_rate.epoch.global": 0.5517970401691332,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.2,
      "success_rate.window.env_macro_mean": 0.7333333333333334,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9870379876796714,
      "tokens_p.mean_in_band": 0.7021033653846154,
      "tokens_rate.above_band": 0.8822463768115942,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11775362318840579
    },
    {
      "epoch": 0.08228058510638298,
      "grad_norm": 479.0166035790374,
      "learning_rate": 1.9995457707997888e-07,
      "loss": 1.4344,
      "step": 495,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.3870967741935484,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5925925925925926,
      "success_rate.epoch.env.logic": 0.3274336283185841,
      "success_rate.epoch.env.math": 0.8504672897196262,
      "success_rate.epoch.env.sat": 0.1282051282051282,
      "success_rate.epoch.env.science": 0.5737179487179487,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5225820227851198,
      "success_rate.epoch.global": 0.549163179916318,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.2333333333333333,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9933845766129032,
      "tokens_p.mean_below_band": 7.82310962677002e-07,
      "tokens_p.mean_in_band": 0.35601395730706076,
      "tokens_rate.above_band": 0.7092469018112488,
      "tokens_rate.below_band": 0.00047664442326024784,
      "tokens_rate.in_band": 0.29027645376549094
    },
    {
      "epoch": 0.08311170212765957,
      "grad_norm": 382.2248088044927,
      "learning_rate": 1.9995276468083503e-07,
      "loss": 1.0168,
      "step": 500,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.3870967741935484,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.32456140350877194,
      "success_rate.epoch.env.math": 0.8518518518518519,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.5777777777777777,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5206004788772192,
      "success_rate.epoch.global": 0.5507246376811594,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9930854386451972,
      "tokens_p.mean_below_band": 7.82310962677002e-07,
      "tokens_p.mean_in_band": 0.5431722005208334,
      "tokens_rate.above_band": 0.8821944648542738,
      "tokens_rate.below_band": 0.0002449179524859172,
      "tokens_rate.in_band": 0.11756061719324026
    },
    {
      "epoch": 0.08394281914893617,
      "grad_norm": 354.1107390334492,
      "learning_rate": 1.9995091687042212e-07,
      "loss": 1.2537,
      "step": 505,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.3870967741935484,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3162393162393162,
      "success_rate.epoch.env.math": 0.8518518518518519,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.5770440251572327,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5197772207054009,
      "success_rate.epoch.global": 0.5487179487179488,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9984090909090909,
      "tokens_p.mean_below_band": 7.048583938740194e-11,
      "tokens_p.mean_in_band": 0.6290646114864865,
      "tokens_rate.above_band": 0.9166666666666666,
      "tokens_rate.below_band": 0.0011111111111111111,
      "tokens_rate.in_band": 0.08222222222222222
    },
    {
      "epoch": 0.08477393617021277,
      "grad_norm": 230.07439759570912,
      "learning_rate": 1.999490336520195e-07,
      "loss": 0.8621,
      "step": 510,
      "success_rate.epoch.env.abd": 0.2222222222222222,
      "success_rate.epoch.env.agentgym:alfworld": 0.3870967741935484,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.3135593220338983,
      "success_rate.epoch.env.math": 0.8518518518518519,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.577639751552795,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5195877418135958,
      "success_rate.epoch.global": 0.5487804878048781,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.20833333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9926061678463094,
      "tokens_p.mean_below_band": 7.338821887969971e-07,
      "tokens_p.mean_in_band": 0.5253504372427984,
      "tokens_rate.above_band": 0.8903893765473779,
      "tokens_rate.below_band": 0.00022507314877335134,
      "tokens_rate.in_band": 0.10938555030384875
    },
    {
      "epoch": 0.08560505319148937,
      "grad_norm": 427.0258546865168,
      "learning_rate": 1.9994711502896943e-07,
      "loss": 1.1471,
      "step": 515,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.40625,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.31666666666666665,
      "success_rate.epoch.env.math": 0.8518518518518519,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.5784615384615385,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5287568450068449,
      "success_rate.epoch.global": 0.5503018108651911,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7916666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9949675324675324,
      "tokens_p.mean_in_band": 0.6814135174418605,
      "tokens_rate.above_band": 0.8995327102803738,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10046728971962617
    },
    {
      "epoch": 0.08643617021276596,
      "grad_norm": 803.1597369271358,
      "learning_rate": 1.9994516100467703e-07,
      "loss": 1.1766,
      "step": 520,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.31666666666666665,
      "success_rate.epoch.env.math": 0.8532110091743119,
      "success_rate.epoch.env.sat": 0.12195121951219512,
      "success_rate.epoch.env.science": 0.5792682926829268,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5303122591248876,
      "success_rate.epoch.global": 0.551345962113659,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9968072755417957,
      "tokens_p.mean_in_band": 0.526171875,
      "tokens_rate.above_band": 0.8433420365535248,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1566579634464752
    },
    {
      "epoch": 0.08726728723404255,
      "grad_norm": 174.46731622162167,
      "learning_rate": 1.999431715826102e-07,
      "loss": 1.1731,
      "step": 525,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.319672131147541,
      "success_rate.epoch.env.math": 0.8532110091743119,
      "success_rate.epoch.env.sat": 0.11904761904761904,
      "success_rate.epoch.env.science": 0.579185520361991,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5303139947335569,
      "success_rate.epoch.global": 0.5508390918065152,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9907882462686567,
      "tokens_p.mean_in_band": 0.5906982421875,
      "tokens_rate.above_band": 0.8933333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10666666666666667
    },
    {
      "epoch": 0.08809840425531915,
      "grad_norm": 283.8067170785908,
      "learning_rate": 1.9994114676629962e-07,
      "loss": 1.1053,
      "step": 530,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3225806451612903,
      "success_rate.epoch.env.math": 0.8532110091743119,
      "success_rate.epoch.env.sat": 0.11904761904761904,
      "success_rate.epoch.env.science": 0.5799701046337817,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5277240807724597,
      "success_rate.epoch.global": 0.5503421309872922,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.29166666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.993408677184466,
      "tokens_p.mean_below_band": 2.568121999502182e-07,
      "tokens_p.mean_in_band": 0.5207973073122529,
      "tokens_rate.above_band": 0.8900410455821992,
      "tokens_rate.below_band": 0.0006480881399870382,
      "tokens_rate.in_band": 0.10931086627781378
    },
    {
      "epoch": 0.08892952127659574,
      "grad_norm": 400.74709719437845,
      "learning_rate": 1.9993908655933894e-07,
      "loss": 1.1141,
      "step": 535,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3225806451612903,
      "success_rate.epoch.env.math": 0.8545454545454545,
      "success_rate.epoch.env.sat": 0.11904761904761904,
      "success_rate.epoch.env.science": 0.5828402366863905,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5281063150837099,
      "success_rate.epoch.global": 0.5528612997090203,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9890752032520326,
      "tokens_p.mean_below_band": 6.693881005048752e-10,
      "tokens_p.mean_in_band": 0.7046130952380952,
      "tokens_rate.above_band": 0.8482758620689655,
      "tokens_rate.below_band": 0.006896551724137931,
      "tokens_rate.in_band": 0.14482758620689656
    },
    {
      "epoch": 0.08976063829787234,
      "grad_norm": 365.3966680271899,
      "learning_rate": 1.9993699096538443e-07,
      "loss": 1.1627,
      "step": 540,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.3888888888888889,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.32,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.11627906976744186,
      "success_rate.epoch.env.science": 0.5823529411764706,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5257322328703053,
      "success_rate.epoch.global": 0.5513928914505284,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.3,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9979963442069741,
      "tokens_p.mean_in_band": 0.5530711206896551,
      "tokens_rate.above_band": 0.938753959873284,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061246040126715945
    },
    {
      "epoch": 0.09059175531914894,
      "grad_norm": 329.1499487681222,
      "learning_rate": 1.9993485998815532e-07,
      "loss": 1.118,
      "step": 545,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.3783783783783784,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.31496062992125984,
      "success_rate.epoch.env.math": 0.8584070796460177,
      "success_rate.epoch.env.sat": 0.11627906976744186,
      "success_rate.epoch.env.science": 0.583941605839416,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5321537183166861,
      "success_rate.epoch.global": 0.5518553758325404,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9974304583624912,
      "tokens_p.mean_in_band": 0.5894681490384616,
      "tokens_rate.above_band": 0.9648885887913572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.035111411208642807
    },
    {
      "epoch": 0.09142287234042554,
      "grad_norm": 180.2068274951857,
      "learning_rate": 1.9993269363143354e-07,
      "loss": 1.07,
      "step": 550,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.3783783783783784,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3125,
      "success_rate.epoch.env.math": 0.8584070796460177,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.5875542691751086,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5317886342037863,
      "success_rate.epoch.global": 0.5528301886792453,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9967641843971631,
      "tokens_p.mean_in_band": 0.6424231150793651,
      "tokens_rate.above_band": 0.91796875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08203125
    },
    {
      "epoch": 0.09225398936170212,
      "grad_norm": 98.47914100347661,
      "learning_rate": 1.9993049189906385e-07,
      "loss": 1.077,
      "step": 555,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3125,
      "success_rate.epoch.env.math": 0.8584070796460177,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.5884892086330935,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5282981357289277,
      "success_rate.epoch.global": 0.5509822263797942,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9981767794632439,
      "tokens_p.mean_in_band": 0.7005642361111111,
      "tokens_rate.above_band": 0.950110864745011,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04988913525498891
    },
    {
      "epoch": 0.09308510638297872,
      "grad_norm": 226.43247644121573,
      "learning_rate": 1.999282547949538e-07,
      "loss": 1.0796,
      "step": 560,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3153846153846154,
      "success_rate.epoch.env.math": 0.8521739130434782,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.5894134477825465,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.528077743722703,
      "success_rate.epoch.global": 0.5515320334261838,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9987796373779637,
      "tokens_p.mean_in_band": 0.5765772405660378,
      "tokens_rate.above_band": 0.9311688311688312,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06883116883116883
    },
    {
      "epoch": 0.09391622340425532,
      "grad_norm": 365.66409248976464,
      "learning_rate": 1.9992598232307372e-07,
      "loss": 1.2875,
      "step": 565,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3153846153846154,
      "success_rate.epoch.env.math": 0.8521739130434782,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.5892351274787535,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5280615327859945,
      "success_rate.epoch.global": 0.551660516605166,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9895104895104895,
      "tokens_p.mean_in_band": 0.6145241477272727,
      "tokens_rate.above_band": 0.7647058823529411,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.23529411764705882
    },
    {
      "epoch": 0.09474734042553191,
      "grad_norm": 435.6573483721362,
      "learning_rate": 1.9992367448745663e-07,
      "loss": 1.1268,
      "step": 570,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.3153846153846154,
      "success_rate.epoch.env.math": 0.853448275862069,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.5902097902097903,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5282659896541425,
      "success_rate.epoch.global": 0.553016453382084,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9854484732824428,
      "tokens_p.mean_in_band": 0.5512152777777778,
      "tokens_rate.above_band": 0.7443181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2556818181818182
    },
    {
      "epoch": 0.09557845744680851,
      "grad_norm": 553.93686230331,
      "learning_rate": 1.999213312921984e-07,
      "loss": 0.9857,
      "step": 575,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.31297709923664124,
      "success_rate.epoch.env.math": 0.853448275862069,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.5922330097087378,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5282310535951402,
      "success_rate.epoch.global": 0.5540417801998183,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.996368501529052,
      "tokens_p.mean_in_band": 0.6546585648148148,
      "tokens_rate.above_band": 0.960352422907489,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039647577092511016
    },
    {
      "epoch": 0.09640957446808511,
      "grad_norm": 277.3004653277527,
      "learning_rate": 1.999189527414576e-07,
      "loss": 1.0519,
      "step": 580,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.31343283582089554,
      "success_rate.epoch.env.math": 0.8547008547008547,
      "success_rate.epoch.env.sat": 0.10638297872340426,
      "success_rate.epoch.env.science": 0.5939226519337016,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5266578244678487,
      "success_rate.epoch.global": 0.5540540540540541,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9953516902944384,
      "tokens_p.mean_in_band": 0.5635202891791045,
      "tokens_rate.above_band": 0.8953329427846124,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10466705721538762
    },
    {
      "epoch": 0.09724069148936171,
      "grad_norm": 260.95538144569673,
      "learning_rate": 1.9991653883945568e-07,
      "loss": 0.9493,
      "step": 585,
      "success_rate.epoch.env.abd": 0.3,
      "success_rate.epoch.env.agentgym:alfworld": 0.34146341463414637,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3161764705882353,
      "success_rate.epoch.env.math": 0.85,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.5961538461538461,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5264812483069298,
      "success_rate.epoch.global": 0.5553571428571429,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9984065155807366,
      "tokens_p.mean_below_band": 1.6555645743210334e-12,
      "tokens_p.mean_in_band": 0.5758539244186046,
      "tokens_rate.above_band": 0.9413333333333334,
      "tokens_rate.below_band": 0.0013333333333333333,
      "tokens_rate.in_band": 0.05733333333333333
    },
    {
      "epoch": 0.09807180851063829,
      "grad_norm": 371.6161150140347,
      "learning_rate": 1.999140895904766e-07,
      "loss": 1.0071,
      "step": 590,
      "success_rate.epoch.env.abd": 0.36363636363636365,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.3161764705882353,
      "success_rate.epoch.env.math": 0.8512396694214877,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.5953678474114441,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5315685167628058,
      "success_rate.epoch.global": 0.5553587245349867,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9971897482014388,
      "tokens_p.mean_below_band": 1.1874362826347351e-08,
      "tokens_p.mean_in_band": 0.5916466346153846,
      "tokens_rate.above_band": 0.952054794520548,
      "tokens_rate.below_band": 0.003424657534246575,
      "tokens_rate.in_band": 0.04452054794520548
    },
    {
      "epoch": 0.09890292553191489,
      "grad_norm": 310.7065388890588,
      "learning_rate": 1.9991160499886725e-07,
      "loss": 1.0951,
      "step": 595,
      "success_rate.epoch.env.abd": 0.36363636363636365,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.31386861313868614,
      "success_rate.epoch.env.math": 0.8467741935483871,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.5926928281461434,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5291455482479678,
      "success_rate.epoch.global": 0.553116769095698,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.2,
      "success_rate.window.env_macro_mean": 0.21666666666666667,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9921995130702204,
      "tokens_p.mean_below_band": 1.195439836010337e-07,
      "tokens_p.mean_in_band": 0.5019733297413793,
      "tokens_rate.above_band": 0.8702051739518287,
      "tokens_rate.below_band": 0.00044603033006244426,
      "tokens_rate.in_band": 0.12934879571810884
    },
    {
      "epoch": 0.09973404255319149,
      "grad_norm": 258.0866267581683,
      "learning_rate": 1.9990908506903711e-07,
      "loss": 1.1214,
      "step": 600,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.30714285714285716,
      "success_rate.epoch.env.math": 0.8333333333333334,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.5929919137466307,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.531967086618856,
      "success_rate.epoch.global": 0.5509138381201044,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9963216145833333,
      "tokens_p.mean_below_band": 8.334609447047114e-09,
      "tokens_p.mean_in_band": 0.5324629934210526,
      "tokens_rate.above_band": 0.9082308420056765,
      "tokens_rate.below_band": 0.001892147587511826,
      "tokens_rate.in_band": 0.08987701040681173
    },
    {
      "epoch": 0.10056515957446809,
      "grad_norm": 245.00206467563692,
      "learning_rate": 1.9990652980545854e-07,
      "loss": 1.1973,
      "step": 605,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.30714285714285716,
      "success_rate.epoch.env.math": 0.8372093023255814,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.5909090909090909,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5321300999056476,
      "success_rate.epoch.global": 0.5509499136442142,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.2857142857142857,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9851804123711341,
      "tokens_p.mean_in_band": 0.6308159722222222,
      "tokens_rate.above_band": 0.6830985915492958,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.31690140845070425
    },
    {
      "epoch": 0.10139627659574468,
      "grad_norm": 392.3265895886073,
      "learning_rate": 1.9990393921266642e-07,
      "loss": 1.1094,
      "step": 610,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.3125,
      "success_rate.epoch.env.math": 0.8307692307692308,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.589095744680851,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.577321347639516,
      "success_rate.epoch.global": 0.5496575342465754,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9981095967139656,
      "tokens_p.mean_below_band": 3.268496584496461e-13,
      "tokens_p.mean_in_band": 0.5858808876811594,
      "tokens_rate.above_band": 0.950319375443577,
      "tokens_rate.below_band": 0.0007097232079489,
      "tokens_rate.in_band": 0.048970901348474094
    },
    {
      "epoch": 0.10222739361702128,
      "grad_norm": 196.3933602505688,
      "learning_rate": 1.999013132952584e-07,
      "loss": 1.3064,
      "step": 615,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.3082191780821918,
      "success_rate.epoch.env.math": 0.8307692307692308,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.5910290237467019,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5771079346529745,
      "success_rate.epoch.global": 0.5501700680272109,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.99125,
      "tokens_p.mean_in_band": 0.6725431743421053,
      "tokens_rate.above_band": 0.8555133079847909,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1444866920152091
    },
    {
      "epoch": 0.10305851063829788,
      "grad_norm": 253.0735143574712,
      "learning_rate": 1.9989865205789493e-07,
      "loss": 1.3374,
      "step": 620,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.30612244897959184,
      "success_rate.epoch.env.math": 0.8257575757575758,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5910878112712975,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5762815334787755,
      "success_rate.epoch.global": 0.549367088607595,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9961053412462908,
      "tokens_p.mean_below_band": 2.455635694786906e-10,
      "tokens_p.mean_in_band": 0.5500600961538461,
      "tokens_rate.above_band": 0.9108108108108108,
      "tokens_rate.below_band": 0.0013513513513513514,
      "tokens_rate.in_band": 0.08783783783783784
    },
    {
      "epoch": 0.10388962765957446,
      "grad_norm": 328.8627665120471,
      "learning_rate": 1.99895955505299e-07,
      "loss": 1.0881,
      "step": 625,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.3087248322147651,
      "success_rate.epoch.env.math": 0.8270676691729323,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5903771131339401,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5765726042527002,
      "success_rate.epoch.global": 0.5494137353433836,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.611111111111111,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9981276747503567,
      "tokens_p.mean_in_band": 0.5607540246212122,
      "tokens_rate.above_band": 0.9550408719346049,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04495912806539509
    },
    {
      "epoch": 0.10472074468085106,
      "grad_norm": 788.3542226077053,
      "learning_rate": 1.9989322364225632e-07,
      "loss": 1.0327,
      "step": 630,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.3087248322147651,
      "success_rate.epoch.env.math": 0.8235294117647058,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5891472868217055,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.562502778459931,
      "success_rate.epoch.global": 0.5486284289276808,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.38888888888888884,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9920990566037736,
      "tokens_p.mean_in_band": 0.55828125,
      "tokens_rate.above_band": 0.9137931034482759,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08620689655172414
    },
    {
      "epoch": 0.10555186170212766,
      "grad_norm": 166.99230029427298,
      "learning_rate": 1.998904564736153e-07,
      "loss": 1.0952,
      "step": 635,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3488372093023256,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.30666666666666664,
      "success_rate.epoch.env.math": 0.8260869565217391,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.5879332477535302,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5638472526517266,
      "success_rate.epoch.global": 0.5486798679867987,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9992690058479532,
      "tokens_p.mean_in_band": 0.4449677900834517,
      "tokens_rate.above_band": 0.9283387622149837,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07166123778501629
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 412.1973337202069,
      "learning_rate": 1.99887654004287e-07,
      "loss": 1.4361,
      "step": 640,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3488372093023256,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.30666666666666664,
      "success_rate.epoch.env.math": 0.8297872340425532,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5867346938775511,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.563725031724334,
      "success_rate.epoch.global": 0.5482815057283142,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.4666666666666666,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.99375,
      "tokens_p.mean_in_band": 0.64046875,
      "tokens_rate.above_band": 0.8113207547169812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18867924528301888
    },
    {
      "epoch": 0.10721409574468085,
      "grad_norm": 667.891341906257,
      "learning_rate": 1.9988481623924508e-07,
      "loss": 1.3169,
      "step": 645,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.3488372093023256,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.30666666666666664,
      "success_rate.epoch.env.math": 0.8251748251748252,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5848101265822785,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5631307611640612,
      "success_rate.epoch.global": 0.5471544715447154,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.30952380952380953,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9875,
      "tokens_p.mean_in_band": 0.6109470274390244,
      "tokens_rate.above_band": 0.7602339181286549,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.23976608187134502
    },
    {
      "epoch": 0.10804521276595745,
      "grad_norm": 206.94143675927717,
      "learning_rate": 1.9988194318352588e-07,
      "loss": 1.1671,
      "step": 650,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.36363636363636365,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.31125827814569534,
      "success_rate.epoch.env.math": 0.8251748251748252,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5846925972396487,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5648828735704646,
      "success_rate.epoch.global": 0.5480225988700564,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6904761904761904,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9978407663316583,
      "tokens_p.mean_in_band": 0.5024801587301587,
      "tokens_rate.above_band": 0.9266589057043073,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07334109429569266
    },
    {
      "epoch": 0.10887632978723404,
      "grad_norm": 298.63004928229986,
      "learning_rate": 1.9987903484222842e-07,
      "loss": 1.0999,
      "step": 655,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.37777777777777777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.31125827814569534,
      "success_rate.epoch.env.math": 0.8251748251748252,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5856079404466501,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5662516696930479,
      "success_rate.epoch.global": 0.5492393915132106,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9943862275449101,
      "tokens_p.mean_in_band": 0.53623046875,
      "tokens_rate.above_band": 0.893048128342246,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10695187165775401
    },
    {
      "epoch": 0.10970744680851063,
      "grad_norm": 216.32593376010945,
      "learning_rate": 1.9987609122051422e-07,
      "loss": 1.4122,
      "step": 660,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.37777777777777777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.3157894736842105,
      "success_rate.epoch.env.math": 0.8275862068965517,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5862068965517241,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5669372636353492,
      "success_rate.epoch.global": 0.5508744038155803,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.8571428571428571,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.98875,
      "tokens_p.mean_in_band": 0.6669100806826637,
      "tokens_rate.above_band": 0.8928571428571429,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10714285714285714
    },
    {
      "epoch": 0.11053856382978723,
      "grad_norm": 282.3076004392478,
      "learning_rate": 1.9987311232360755e-07,
      "loss": 1.0588,
      "step": 665,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.37777777777777777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.3137254901960784,
      "success_rate.epoch.env.math": 0.8299319727891157,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5845588235294118,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5668130553973602,
      "success_rate.epoch.global": 0.5501976284584981,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.4761904761904762,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.99935413354531,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.54482421875,
      "tokens_rate.above_band": 0.9388059701492537,
      "tokens_rate.below_band": 0.0014925373134328358,
      "tokens_rate.in_band": 0.05970149253731343
    },
    {
      "epoch": 0.11136968085106383,
      "grad_norm": 125.76401939853064,
      "learning_rate": 1.9987009815679518e-07,
      "loss": 0.9728,
      "step": 670,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.37777777777777777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.31210191082802546,
      "success_rate.epoch.env.math": 0.831081081081081,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.5848595848595849,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.566797263602277,
      "success_rate.epoch.global": 0.5498821681068342,
      "success_rate.window.env.logic": 0.2,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.65,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 1.0005815932818882,
      "tokens_p.mean_in_band": 0.5477594339622641,
      "tokens_rate.above_band": 0.9540926808142053,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.045907319185794715
    },
    {
      "epoch": 0.11220079787234043,
      "grad_norm": 484.3191205688296,
      "learning_rate": 1.9986704872542656e-07,
      "loss": 1.1652,
      "step": 675,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.310126582278481,
      "success_rate.epoch.env.math": 0.831081081081081,
      "success_rate.epoch.env.sat": 0.09433962264150944,
      "success_rate.epoch.env.science": 0.5861650485436893,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5663348499125013,
      "success_rate.epoch.global": 0.5499219968798752,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.3666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9940380921895007,
      "tokens_p.mean_in_band": 0.6952123397435898,
      "tokens_rate.above_band": 0.9524390243902439,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0475609756097561
    },
    {
      "epoch": 0.11303191489361702,
      "grad_norm": 406.6131034139839,
      "learning_rate": 1.9986396403491364e-07,
      "loss": 1.0301,
      "step": 680,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.3167701863354037,
      "success_rate.epoch.env.math": 0.8322147651006712,
      "success_rate.epoch.env.sat": 0.09433962264150944,
      "success_rate.epoch.env.science": 0.586248492159228,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5684268723528255,
      "success_rate.epoch.global": 0.5510835913312694,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.8166666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.994873046875,
      "tokens_p.mean_in_band": 0.6511627906976745,
      "tokens_rate.above_band": 0.965845909451946,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03415409054805401
    },
    {
      "epoch": 0.11386303191489362,
      "grad_norm": 573.8555410692554,
      "learning_rate": 1.99860844090731e-07,
      "loss": 1.1237,
      "step": 685,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.3148148148148148,
      "success_rate.epoch.env.math": 0.8266666666666667,
      "success_rate.epoch.env.sat": 0.09433962264150944,
      "success_rate.epoch.env.science": 0.5885167464114832,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5665735331842934,
      "success_rate.epoch.global": 0.5514592933947773,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.21428571428571427,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9940596562184024,
      "tokens_p.mean_below_band": 1.2945383787155151e-07,
      "tokens_p.mean_in_band": 0.5166233519269777,
      "tokens_rate.above_band": 0.8887890361716468,
      "tokens_rate.below_band": 0.00044933722758930576,
      "tokens_rate.in_band": 0.11076162660076387
    },
    {
      "epoch": 0.1146941489361702,
      "grad_norm": 318.3039503873906,
      "learning_rate": 1.9985768889841581e-07,
      "loss": 1.1151,
      "step": 690,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.3148148148148148,
      "success_rate.epoch.env.math": 0.8157894736842105,
      "success_rate.epoch.env.sat": 0.09259259259259259,
      "success_rate.epoch.env.science": 0.5890736342042755,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5641778014093575,
      "success_rate.epoch.global": 0.5503048780487805,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.16666666666666666,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9870037807183365,
      "tokens_p.mean_in_band": 0.5964645127118644,
      "tokens_rate.above_band": 0.6915032679738562,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.3084967320261438
    },
    {
      "epoch": 0.1155252659574468,
      "grad_norm": 263.34531958739285,
      "learning_rate": 1.9985449846356773e-07,
      "loss": 1.1111,
      "step": 695,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.3148148148148148,
      "success_rate.epoch.env.math": 0.8181818181818182,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.589622641509434,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5642921514201997,
      "success_rate.epoch.global": 0.5510976532929599,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9908088235294118,
      "tokens_p.mean_in_band": 0.5995762711864406,
      "tokens_rate.above_band": 0.7216981132075472,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2783018867924528
    },
    {
      "epoch": 0.1163563829787234,
      "grad_norm": 165.3867424905044,
      "learning_rate": 1.99851272791849e-07,
      "loss": 1.0931,
      "step": 700,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.31901840490797545,
      "success_rate.epoch.env.math": 0.8181818181818182,
      "success_rate.epoch.env.sat": 0.08928571428571429,
      "success_rate.epoch.env.science": 0.5876168224299065,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5643443690920412,
      "success_rate.epoch.global": 0.549962434259955,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.375,
      "success_rate.window.env_macro_mean": 0.4583333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9897959183673469,
      "tokens_p.mean_in_band": 0.5998391544117647,
      "tokens_rate.above_band": 0.7424242424242424,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.25757575757575757
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 184.36476903608798,
      "learning_rate": 1.9984801188898444e-07,
      "loss": 0.9731,
      "step": 705,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.391304347826087,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.31901840490797545,
      "success_rate.epoch.env.math": 0.8141025641025641,
      "success_rate.epoch.env.sat": 0.08928571428571429,
      "success_rate.epoch.env.science": 0.5879629629629629,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5640049951332959,
      "success_rate.epoch.global": 0.5503355704697986,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_below_band": 5.029141902923584e-07,
      "tokens_p.mean_in_band": 0.677734375,
      "tokens_rate.above_band": 0.7194244604316546,
      "tokens_rate.below_band": 0.007194244604316547,
      "tokens_rate.in_band": 0.2733812949640288
    },
    {
      "epoch": 0.1180186170212766,
      "grad_norm": 303.5670290657248,
      "learning_rate": 1.9984471576076126e-07,
      "loss": 1.1558,
      "step": 710,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4722222222222222,
      "success_rate.epoch.env.logic": 0.3170731707317073,
      "success_rate.epoch.env.math": 0.8141025641025641,
      "success_rate.epoch.env.sat": 0.08771929824561403,
      "success_rate.epoch.env.science": 0.5873563218390805,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5635814148142537,
      "success_rate.epoch.global": 0.5492227979274611,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.3,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9923387096774193,
      "tokens_p.mean_in_band": 0.561494140625,
      "tokens_rate.above_band": 0.8559423769507803,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14405762304921968
    },
    {
      "epoch": 0.1188497340425532,
      "grad_norm": 130.78914744203175,
      "learning_rate": 1.9984138441302937e-07,
      "loss": 1.1692,
      "step": 715,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4722222222222222,
      "success_rate.epoch.env.logic": 0.3170731707317073,
      "success_rate.epoch.env.math": 0.8164556962025317,
      "success_rate.epoch.env.sat": 0.08771929824561403,
      "success_rate.epoch.env.science": 0.5892448512585813,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5639670204069327,
      "success_rate.epoch.global": 0.5512159174649963,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9988790463692039,
      "tokens_p.mean_in_band": 0.5020616319444444,
      "tokens_rate.above_band": 0.9407407407407408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05925925925925926
    },
    {
      "epoch": 0.1196808510638298,
      "grad_norm": 332.3820616116317,
      "learning_rate": 1.9983801785170108e-07,
      "loss": 1.0918,
      "step": 720,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.32335329341317365,
      "success_rate.epoch.env.math": 0.8113207547169812,
      "success_rate.epoch.env.sat": 0.08771929824561403,
      "success_rate.epoch.env.science": 0.5899772209567198,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.565434458148598,
      "success_rate.epoch.global": 0.5519765739385066,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9972903437705277,
      "tokens_p.mean_below_band": 2.1736923372372985e-10,
      "tokens_p.mean_in_band": 0.653169014084507,
      "tokens_rate.above_band": 0.9844794136667385,
      "tokens_rate.below_band": 0.0002155636990730761,
      "tokens_rate.in_band": 0.015305022634188403
    },
    {
      "epoch": 0.12051196808510638,
      "grad_norm": 187.4079827073579,
      "learning_rate": 1.9983461608275117e-07,
      "loss": 1.472,
      "step": 725,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.32142857142857145,
      "success_rate.epoch.env.math": 0.8125,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.5898305084745763,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5652158589779056,
      "success_rate.epoch.global": 0.5515988372093024,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.39285714285714285,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.99375,
      "tokens_p.mean_in_band": 0.6453269675925926,
      "tokens_rate.above_band": 0.8280254777070064,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17197452229299362
    },
    {
      "epoch": 0.12134308510638298,
      "grad_norm": 173.24380997138368,
      "learning_rate": 1.9983117911221701e-07,
      "loss": 1.0742,
      "step": 730,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.3235294117647059,
      "success_rate.epoch.env.math": 0.8136645962732919,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.5898876404494382,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5503663955158712,
      "success_rate.epoch.global": 0.551624548736462,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9964918759231906,
      "tokens_p.mean_in_band": 0.6041434151785714,
      "tokens_rate.above_band": 0.9602836879432625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03971631205673759
    },
    {
      "epoch": 0.12217420212765957,
      "grad_norm": 1180.96945143047,
      "learning_rate": 1.9982770694619835e-07,
      "loss": 1.0098,
      "step": 735,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.3216374269005848,
      "success_rate.epoch.env.math": 0.8136645962732919,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.5886287625418061,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5500799534457118,
      "success_rate.epoch.global": 0.5506101938262742,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.4444444444444444,
      "tokens_p.mean_above_band": 0.9984152139461173,
      "tokens_p.mean_below_band": 1.5688783605583012e-11,
      "tokens_p.mean_in_band": 0.5814416273584906,
      "tokens_rate.above_band": 0.9211678832116789,
      "tokens_rate.below_band": 0.00145985401459854,
      "tokens_rate.in_band": 0.07737226277372262
    },
    {
      "epoch": 0.12300531914893617,
      "grad_norm": 310.7366634118928,
      "learning_rate": 1.998241995908574e-07,
      "loss": 1.0865,
      "step": 740,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.3236994219653179,
      "success_rate.epoch.env.math": 0.8148148148148148,
      "success_rate.epoch.env.sat": 0.0847457627118644,
      "success_rate.epoch.env.science": 0.5893451720310766,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5503042706507725,
      "success_rate.epoch.global": 0.5510349750178444,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9961260330578512,
      "tokens_p.mean_in_band": 0.60375,
      "tokens_rate.above_band": 0.9355670103092784,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06443298969072164
    },
    {
      "epoch": 0.12383643617021277,
      "grad_norm": 143.88637664778358,
      "learning_rate": 1.9982065705241887e-07,
      "loss": 0.9834,
      "step": 745,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.3236994219653179,
      "success_rate.epoch.env.math": 0.8181818181818182,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5900552486187846,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5505465116122433,
      "success_rate.epoch.global": 0.5521646557842441,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9922399328859061,
      "tokens_p.mean_in_band": 0.5324622844827587,
      "tokens_rate.above_band": 0.8370786516853933,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16292134831460675
    },
    {
      "epoch": 0.12466755319148937,
      "grad_norm": 250.25555079610672,
      "learning_rate": 1.9981707933716993e-07,
      "loss": 1.2934,
      "step": 750,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.3218390804597701,
      "success_rate.epoch.env.math": 0.8192771084337349,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.5866228070175439,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.504710375898164,
      "success_rate.epoch.global": 0.5496828752642706,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.14285714285714285,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.2,
      "tokens_p.mean_above_band": 0.9961927020506635,
      "tokens_p.mean_in_band": 0.5739683493589743,
      "tokens_rate.above_band": 0.9140022050716649,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08599779492833518
    },
    {
      "epoch": 0.12549867021276595,
      "grad_norm": 441.32161997729486,
      "learning_rate": 1.9981346645146013e-07,
      "loss": 1.0241,
      "step": 755,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.40425531914893614,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.32571428571428573,
      "success_rate.epoch.env.math": 0.8214285714285714,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.5860566448801743,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5050825927975644,
      "success_rate.epoch.global": 0.5500349895031491,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9923155737704918,
      "tokens_p.mean_in_band": 0.6250831117021277,
      "tokens_rate.above_band": 0.8384879725085911,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16151202749140894
    },
    {
      "epoch": 0.12632978723404256,
      "grad_norm": 476.299462569904,
      "learning_rate": 1.9980981840170147e-07,
      "loss": 1.0682,
      "step": 760,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.32954545454545453,
      "success_rate.epoch.env.math": 0.8224852071005917,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.5865800865800865,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5067028285903672,
      "success_rate.epoch.global": 0.5514603616133519,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.8928571428571428,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942307692307693,
      "tokens_p.mean_in_band": 0.7045641447368421,
      "tokens_rate.above_band": 0.9647495361781077,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03525046382189239
    },
    {
      "epoch": 0.12716090425531915,
      "grad_norm": 336.57319710425196,
      "learning_rate": 1.9980613519436833e-07,
      "loss": 1.1062,
      "step": 765,
      "success_rate.epoch.env.abd": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.327683615819209,
      "success_rate.epoch.env.math": 0.8245614035087719,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.5862068965517241,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5066883892861465,
      "success_rate.epoch.global": 0.5515570934256055,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.6333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9925204918032787,
      "tokens_p.mean_in_band": 0.6488850911458334,
      "tokens_rate.above_band": 0.8640226628895185,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1359773371104816
    },
    {
      "epoch": 0.12799202127659576,
      "grad_norm": 211.09462540375193,
      "learning_rate": 1.998024168359975e-07,
      "loss": 1.0549,
      "step": 770,
      "success_rate.epoch.env.abd": 0.38461538461538464,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.327683615819209,
      "success_rate.epoch.env.math": 0.8245614035087719,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.5859124866595518,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5037478718367416,
      "success_rate.epoch.global": 0.5512027491408935,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.2777777777777778,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9906496062992126,
      "tokens_p.mean_below_band": 4.843059286940843e-11,
      "tokens_p.mean_in_band": 0.33334294280442806,
      "tokens_rate.above_band": 0.5834609494640123,
      "tokens_rate.below_band": 0.0015313935681470138,
      "tokens_rate.in_band": 0.41500765696784075
    },
    {
      "epoch": 0.12882313829787234,
      "grad_norm": 248.41363173656077,
      "learning_rate": 1.9979866333318816e-07,
      "loss": 1.1377,
      "step": 775,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4864864864864865,
      "success_rate.epoch.env.logic": 0.3258426966292135,
      "success_rate.epoch.env.math": 0.8197674418604651,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.5881104033970276,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5007268224369429,
      "success_rate.epoch.global": 0.5512295081967213,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.16666666666666669,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9977104755784062,
      "tokens_p.mean_in_band": 0.3172961353550296,
      "tokens_rate.above_band": 0.6971326164874552,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.30286738351254483
    },
    {
      "epoch": 0.12965425531914893,
      "grad_norm": 259.3579126149414,
      "learning_rate": 1.9979487469260186e-07,
      "loss": 0.8702,
      "step": 780,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47368421052631576,
      "success_rate.epoch.env.logic": 0.3258426966292135,
      "success_rate.epoch.env.math": 0.8218390804597702,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.5848261327713382,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49945273989271066,
      "success_rate.epoch.global": 0.5495251017639078,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.14285714285714285,
      "success_rate.window.env_macro_mean": 0.38095238095238093,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9923336988304093,
      "tokens_p.mean_below_band": 1.525040715932846e-08,
      "tokens_p.mean_in_band": 0.5209904813218391,
      "tokens_rate.above_band": 0.8673598782652803,
      "tokens_rate.below_band": 0.000253613999492772,
      "tokens_rate.in_band": 0.13238650773522698
    },
    {
      "epoch": 0.13048537234042554,
      "grad_norm": 458.49301481412226,
      "learning_rate": 1.997910509209625e-07,
      "loss": 1.2074,
      "step": 785,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47368421052631576,
      "success_rate.epoch.env.logic": 0.3258426966292135,
      "success_rate.epoch.env.math": 0.8228571428571428,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.5851619644723093,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4995758211743783,
      "success_rate.epoch.global": 0.550236008091706,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9866504854368932,
      "tokens_p.mean_in_band": 0.5775240384615384,
      "tokens_rate.above_band": 0.7984496124031008,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.20155038759689922
    },
    {
      "epoch": 0.13131648936170212,
      "grad_norm": 384.2247557940492,
      "learning_rate": 1.9978719202505634e-07,
      "loss": 1.3276,
      "step": 790,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47368421052631576,
      "success_rate.epoch.env.logic": 0.329608938547486,
      "success_rate.epoch.env.math": 0.8202247191011236,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.5848074921956296,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4996466708003395,
      "success_rate.epoch.global": 0.5506371562709591,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.7833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9902777777777778,
      "tokens_p.mean_in_band": 0.5003255208333334,
      "tokens_rate.above_band": 0.8823529411764706,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11764705882352941
    },
    {
      "epoch": 0.13214760638297873,
      "grad_norm": 263.13375618019256,
      "learning_rate": 1.9978329801173197e-07,
      "loss": 0.9061,
      "step": 795,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47368421052631576,
      "success_rate.epoch.env.logic": 0.32967032967032966,
      "success_rate.epoch.env.math": 0.8222222222222222,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.5865284974093264,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4998739269396482,
      "success_rate.epoch.global": 0.5516322451698867,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9979990118577076,
      "tokens_p.mean_in_band": 0.6232142857142857,
      "tokens_rate.above_band": 0.947565543071161,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.052434456928838954
    },
    {
      "epoch": 0.13297872340425532,
      "grad_norm": 424.0257319612182,
      "learning_rate": 1.9977936888790032e-07,
      "loss": 1.2945,
      "step": 800,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.33152173913043476,
      "success_rate.epoch.env.math": 0.8222222222222222,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.5876288659793815,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.501369113729042,
      "success_rate.epoch.global": 0.5526838966202783,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958091341077085,
      "tokens_p.mean_below_band": 6.007030606269836e-08,
      "tokens_p.mean_in_band": 0.5141872829861112,
      "tokens_rate.above_band": 0.9623983739837398,
      "tokens_rate.below_band": 0.0010162601626016261,
      "tokens_rate.in_band": 0.036585365853658534
    },
    {
      "epoch": 0.13380984042553193,
      "grad_norm": 158.49781613193912,
      "learning_rate": 1.9977540466053465e-07,
      "loss": 1.133,
      "step": 805,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.33152173913043476,
      "success_rate.epoch.env.math": 0.8241758241758241,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.5870901639344263,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5014977409934643,
      "success_rate.epoch.global": 0.5530652603823335,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.6666666666666666,
      "tokens_p.mean_above_band": 0.9823069852941176,
      "tokens_p.mean_in_band": 0.5409458705357143,
      "tokens_rate.above_band": 0.8662420382165605,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1337579617834395
    },
    {
      "epoch": 0.1346409574468085,
      "grad_norm": 228.55388713767965,
      "learning_rate": 1.9977140533667043e-07,
      "loss": 1.1052,
      "step": 810,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.33152173913043476,
      "success_rate.epoch.env.math": 0.827027027027027,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.5845213849287169,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5015234158885092,
      "success_rate.epoch.global": 0.5524246395806028,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.2857142857142857,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9925742574257426,
      "tokens_p.mean_in_band": 0.5675048828125,
      "tokens_rate.above_band": 0.7593984962406015,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.24060150375939848
    },
    {
      "epoch": 0.1354720744680851,
      "grad_norm": 187.5224832466495,
      "learning_rate": 1.9976737092340552e-07,
      "loss": 0.8616,
      "step": 815,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.3333333333333333,
      "success_rate.epoch.env.math": 0.8297872340425532,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.5866261398176292,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5021303755346308,
      "success_rate.epoch.global": 0.5546875,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9916845493562232,
      "tokens_p.mean_in_band": 0.755859375,
      "tokens_rate.above_band": 0.9173228346456693,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08267716535433071
    },
    {
      "epoch": 0.1363031914893617,
      "grad_norm": 238.9270160310689,
      "learning_rate": 1.9976330142790002e-07,
      "loss": 1.0656,
      "step": 820,
      "success_rate.epoch.env.abd": 0.35714285714285715,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.33689839572192515,
      "success_rate.epoch.env.math": 0.8272251308900523,
      "success_rate.epoch.env.sat": 0.078125,
      "success_rate.epoch.env.science": 0.5866935483870968,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5021149472110381,
      "success_rate.epoch.global": 0.5549805950840879,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9918193717277487,
      "tokens_p.mean_in_band": 0.60546875,
      "tokens_rate.above_band": 0.8603603603603603,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13963963963963963
    },
    {
      "epoch": 0.1371343085106383,
      "grad_norm": 152.62611687821536,
      "learning_rate": 1.9975919685737626e-07,
      "loss": 0.9879,
      "step": 825,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.3404255319148936,
      "success_rate.epoch.env.math": 0.828125,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.5867602808425276,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5055372704999491,
      "success_rate.epoch.global": 0.5552699228791774,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9945750452079566,
      "tokens_p.mean_in_band": 0.6637290396341463,
      "tokens_rate.above_band": 0.930976430976431,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06902356902356903
    },
    {
      "epoch": 0.1379654255319149,
      "grad_norm": 197.37937153873247,
      "learning_rate": 1.9975505721911885e-07,
      "loss": 1.2908,
      "step": 830,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.3386243386243386,
      "success_rate.epoch.env.math": 0.8238341968911918,
      "success_rate.epoch.env.sat": 0.07575757575757576,
      "success_rate.epoch.env.science": 0.5872382851445663,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5038137268233752,
      "success_rate.epoch.global": 0.5542784163473818,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.13333333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9920258620689655,
      "tokens_p.mean_in_band": 0.6602233420801527,
      "tokens_rate.above_band": 0.8856893542757417,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1143106457242583
    },
    {
      "epoch": 0.1387965425531915,
      "grad_norm": 168.67250919631232,
      "learning_rate": 1.9975088252047466e-07,
      "loss": 0.8651,
      "step": 835,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.3386243386243386,
      "success_rate.epoch.env.math": 0.826530612244898,
      "success_rate.epoch.env.sat": 0.07575757575757576,
      "success_rate.epoch.env.science": 0.5881188118811881,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5041389033770414,
      "success_rate.epoch.global": 0.5558375634517766,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.8571428571428572,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9878826530612245,
      "tokens_p.mean_in_band": 0.6030441810344828,
      "tokens_rate.above_band": 0.7716535433070866,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2283464566929134
    },
    {
      "epoch": 0.13962765957446807,
      "grad_norm": 236.92745478527485,
      "learning_rate": 1.9974667276885278e-07,
      "loss": 1.2177,
      "step": 840,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.3386243386243386,
      "success_rate.epoch.env.math": 0.8282828282828283,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.5895669291338582,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5043270509411021,
      "success_rate.epoch.global": 0.5570977917981073,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9927591463414634,
      "tokens_p.mean_in_band": 0.6500509510869565,
      "tokens_rate.above_band": 0.780952380952381,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21904761904761905
    },
    {
      "epoch": 0.14045877659574468,
      "grad_norm": 254.94563378569697,
      "learning_rate": 1.997424279717244e-07,
      "loss": 1.0805,
      "step": 845,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.3386243386243386,
      "success_rate.epoch.env.math": 0.8291457286432161,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.5888671875,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5043418835526047,
      "success_rate.epoch.global": 0.5570890840652447,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9879966887417219,
      "tokens_p.mean_in_band": 0.6565104166666667,
      "tokens_rate.above_band": 0.8342541436464088,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16574585635359115
    },
    {
      "epoch": 0.14128989361702127,
      "grad_norm": 214.58383700275985,
      "learning_rate": 1.9973814813662307e-07,
      "loss": 0.8665,
      "step": 850,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.3403141361256545,
      "success_rate.epoch.env.math": 0.8258706467661692,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.5904669260700389,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5055072773928855,
      "success_rate.epoch.global": 0.5583281347473488,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9921818510484454,
      "tokens_p.mean_in_band": 0.7228064903846154,
      "tokens_rate.above_band": 0.946611909650924,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053388090349075976
    },
    {
      "epoch": 0.14212101063829788,
      "grad_norm": 165.4617685728654,
      "learning_rate": 1.9973383327114441e-07,
      "loss": 0.8949,
      "step": 855,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.33678756476683935,
      "success_rate.epoch.env.math": 0.8267326732673267,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.5914811229428848,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5052574772209085,
      "success_rate.epoch.global": 0.5583126550868487,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.997221634208298,
      "tokens_p.mean_in_band": 0.5999710648148148,
      "tokens_rate.above_band": 0.9358161648177497,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06418383518225039
    },
    {
      "epoch": 0.14295212765957446,
      "grad_norm": 165.4439759297413,
      "learning_rate": 1.9972948338294628e-07,
      "loss": 1.1022,
      "step": 860,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.3384615384615385,
      "success_rate.epoch.env.math": 0.8275862068965517,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.5905587668593449,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5054034000609433,
      "success_rate.epoch.global": 0.5580246913580247,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.6428571428571429,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9907718120805369,
      "tokens_p.mean_in_band": 0.6482354525862069,
      "tokens_rate.above_band": 0.8370786516853933,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16292134831460675
    },
    {
      "epoch": 0.14378324468085107,
      "grad_norm": 376.50478028307185,
      "learning_rate": 1.9972509847974864e-07,
      "loss": 0.9464,
      "step": 865,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.3384615384615385,
      "success_rate.epoch.env.math": 0.8235294117647058,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.5904306220095694,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.505022950971705,
      "success_rate.epoch.global": 0.5577395577395577,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.986328125,
      "tokens_p.mean_below_band": 9.255018085241318e-09,
      "tokens_p.mean_in_band": 0.6807291666666667,
      "tokens_rate.above_band": 0.8228571428571428,
      "tokens_rate.below_band": 0.005714285714285714,
      "tokens_rate.in_band": 0.17142857142857143
    },
    {
      "epoch": 0.14461436170212766,
      "grad_norm": 590.7139396862939,
      "learning_rate": 1.9972067856933363e-07,
      "loss": 0.9558,
      "step": 870,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.3384615384615385,
      "success_rate.epoch.env.math": 0.8260869565217391,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.5904761904761905,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5042037429140096,
      "success_rate.epoch.global": 0.5583384239462431,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9877976190476191,
      "tokens_p.mean_in_band": 0.7350383254716981,
      "tokens_rate.above_band": 0.9224011713030746,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07759882869692533
    },
    {
      "epoch": 0.14544547872340424,
      "grad_norm": 356.7976976301709,
      "learning_rate": 1.9971622365954551e-07,
      "loss": 1.0622,
      "step": 875,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.34517766497461927,
      "success_rate.epoch.env.math": 0.8269230769230769,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.5909090909090909,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5049296654001295,
      "success_rate.epoch.global": 0.5595382746051033,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.8571428571428571,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9899655963302753,
      "tokens_p.mean_in_band": 0.5986578525641025,
      "tokens_rate.above_band": 0.8482490272373541,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1517509727626459
    },
    {
      "epoch": 0.14627659574468085,
      "grad_norm": 135.93263081715523,
      "learning_rate": 1.9971173375829065e-07,
      "loss": 1.1486,
      "step": 880,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.3434343434343434,
      "success_rate.epoch.env.math": 0.8229665071770335,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.5916824196597353,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5042908105936014,
      "success_rate.epoch.global": 0.5587167070217918,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.15,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.997431506849315,
      "tokens_p.mean_below_band": 4.6566128730773926e-09,
      "tokens_p.mean_in_band": 0.60859375,
      "tokens_rate.above_band": 0.9073446327683616,
      "tokens_rate.below_band": 0.0022598870056497176,
      "tokens_rate.in_band": 0.0903954802259887
    },
    {
      "epoch": 0.14710771276595744,
      "grad_norm": 198.0059643602478,
      "learning_rate": 1.9970720887353752e-07,
      "loss": 1.0517,
      "step": 885,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40816326530612246,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.3415841584158416,
      "success_rate.epoch.env.math": 0.8254716981132075,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.5915094339622642,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5043346306136196,
      "success_rate.epoch.global": 0.5586995785671283,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6388888888888888,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9962780355761794,
      "tokens_p.mean_in_band": 0.6142743644067796,
      "tokens_rate.above_band": 0.9563609467455622,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04363905325443787
    },
    {
      "epoch": 0.14793882978723405,
      "grad_norm": 151.92573701627512,
      "learning_rate": 1.9970264901331668e-07,
      "loss": 0.9846,
      "step": 890,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.3399014778325123,
      "success_rate.epoch.env.math": 0.822429906542056,
      "success_rate.epoch.env.sat": 0.07042253521126761,
      "success_rate.epoch.env.science": 0.5915492957746479,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5030751840803903,
      "success_rate.epoch.global": 0.5577498503889886,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.22000000000000003,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9970122739018088,
      "tokens_p.mean_in_band": 0.5871834590517241,
      "tokens_rate.above_band": 0.8696629213483146,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1303370786516854
    },
    {
      "epoch": 0.14876994680851063,
      "grad_norm": 265.5710421924225,
      "learning_rate": 1.996980541857208e-07,
      "loss": 0.8005,
      "step": 895,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.3431372549019608,
      "success_rate.epoch.env.math": 0.8232558139534883,
      "success_rate.epoch.env.sat": 0.06944444444444445,
      "success_rate.epoch.env.science": 0.5919701213818861,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5023870224622619,
      "success_rate.epoch.global": 0.5580011897679953,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9950149638084632,
      "tokens_p.mean_below_band": 7.188646122813225e-09,
      "tokens_p.mean_in_band": 0.5166774120145631,
      "tokens_rate.above_band": 0.8968789013732834,
      "tokens_rate.below_band": 0.00024968789013732833,
      "tokens_rate.in_band": 0.10287141073657928
    },
    {
      "epoch": 0.14960106382978725,
      "grad_norm": 1009.3990332159907,
      "learning_rate": 1.9969342439890452e-07,
      "loss": 1.2037,
      "step": 900,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.3431372549019608,
      "success_rate.epoch.env.math": 0.8202764976958525,
      "success_rate.epoch.env.sat": 0.06944444444444445,
      "success_rate.epoch.env.science": 0.5936920222634509,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5022727119735281,
      "success_rate.epoch.global": 0.5591715976331361,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7777777777777778,
      "tokens_p.mean_above_band": 0.990946261682243,
      "tokens_p.mean_below_band": 2.648448571562767e-09,
      "tokens_p.mean_in_band": 0.6962425595238095,
      "tokens_rate.above_band": 0.8294573643410853,
      "tokens_rate.below_band": 0.007751937984496124,
      "tokens_rate.in_band": 0.16279069767441862
    },
    {
      "epoch": 0.15043218085106383,
      "grad_norm": 315.54852445723196,
      "learning_rate": 1.996887596610846e-07,
      "loss": 1.0878,
      "step": 905,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.34299516908212563,
      "success_rate.epoch.env.math": 0.817351598173516,
      "success_rate.epoch.env.sat": 0.0684931506849315,
      "success_rate.epoch.env.science": 0.5933456561922366,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5018759260487191,
      "success_rate.epoch.global": 0.558235294117647,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9994387755102041,
      "tokens_p.mean_in_band": 0.5933657786885246,
      "tokens_rate.above_band": 0.9525660964230172,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04743390357698289
    },
    {
      "epoch": 0.1512632978723404,
      "grad_norm": 114.86361275976537,
      "learning_rate": 1.9968405998053982e-07,
      "loss": 1.239,
      "step": 910,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.34299516908212563,
      "success_rate.epoch.env.math": 0.8198198198198198,
      "success_rate.epoch.env.sat": 0.06756756756756757,
      "success_rate.epoch.env.science": 0.594296228150874,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5021025815475897,
      "success_rate.epoch.global": 0.5593914569923932,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9897836538461539,
      "tokens_p.mean_in_band": 0.5973668981481481,
      "tokens_rate.above_band": 0.8524590163934426,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14754098360655737
    },
    {
      "epoch": 0.15209441489361702,
      "grad_norm": 300.2475570926112,
      "learning_rate": 1.9967932536561096e-07,
      "loss": 0.8637,
      "step": 915,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.3492822966507177,
      "success_rate.epoch.env.math": 0.8198198198198198,
      "success_rate.epoch.env.sat": 0.06756756756756757,
      "success_rate.epoch.env.science": 0.5954337899543379,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5027775533086858,
      "success_rate.epoch.global": 0.5607911576497964,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950592885375494,
      "tokens_p.mean_in_band": 0.6321022727272727,
      "tokens_rate.above_band": 0.8846153846153846,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11538461538461539
    },
    {
      "epoch": 0.1529255319148936,
      "grad_norm": 395.5290813945582,
      "learning_rate": 1.9967455582470078e-07,
      "loss": 0.8142,
      "step": 920,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.3443396226415094,
      "success_rate.epoch.env.math": 0.8198198198198198,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.5969062784349408,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5023801818150943,
      "success_rate.epoch.global": 0.5605095541401274,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4166666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9983179886685553,
      "tokens_p.mean_in_band": 0.576514175257732,
      "tokens_rate.above_band": 0.9479054779806659,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05209452201933405
    },
    {
      "epoch": 0.15375664893617022,
      "grad_norm": 325.8851761769983,
      "learning_rate": 1.9966975136627408e-07,
      "loss": 0.9141,
      "step": 925,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.3474178403755869,
      "success_rate.epoch.env.math": 0.820627802690583,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.5987318840579711,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5028994369267189,
      "success_rate.epoch.global": 0.5622837370242214,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9959124472573839,
      "tokens_p.mean_in_band": 0.6730057565789473,
      "tokens_rate.above_band": 0.8618181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13818181818181818
    },
    {
      "epoch": 0.1545877659574468,
      "grad_norm": 218.2941752833363,
      "learning_rate": 1.9966491199885754e-07,
      "loss": 0.9742,
      "step": 930,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40384615384615385,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.35046728971962615,
      "success_rate.epoch.env.math": 0.820627802690583,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.5987376014427412,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.503447084889674,
      "success_rate.epoch.global": 0.5622489959839357,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.997030998389694,
      "tokens_p.mean_in_band": 0.6196428571428572,
      "tokens_rate.above_band": 0.9466463414634146,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053353658536585365
    },
    {
      "epoch": 0.15541888297872342,
      "grad_norm": 231.46974310582704,
      "learning_rate": 1.9966003773103992e-07,
      "loss": 0.9837,
      "step": 935,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40384615384615385,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.35046728971962615,
      "success_rate.epoch.env.math": 0.8214285714285714,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.600358422939068,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5027062454087653,
      "success_rate.epoch.global": 0.5633561643835616,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9895220588235294,
      "tokens_p.mean_in_band": 0.5516921612394958,
      "tokens_rate.above_band": 0.8108108108108109,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1891891891891892
    },
    {
      "epoch": 0.15625,
      "grad_norm": 228.22652972071526,
      "learning_rate": 1.996551285714718e-07,
      "loss": 1.0574,
      "step": 940,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40384615384615385,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.35046728971962615,
      "success_rate.epoch.env.math": 0.8230088495575221,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.6014234875444839,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5029467311118895,
      "success_rate.epoch.global": 0.5646992054483542,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9824766355140186,
      "tokens_p.mean_below_band": 9.918585419654846e-08,
      "tokens_p.mean_in_band": 0.75390625,
      "tokens_rate.above_band": 0.8699186991869918,
      "tokens_rate.below_band": 0.008130081300813009,
      "tokens_rate.in_band": 0.12195121951219512
    },
    {
      "epoch": 0.15708111702127658,
      "grad_norm": 616.08098770576,
      "learning_rate": 1.9965018452886574e-07,
      "loss": 0.8494,
      "step": 945,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40384615384615385,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4444444444444444,
      "success_rate.epoch.env.logic": 0.3488372093023256,
      "success_rate.epoch.env.math": 0.8253275109170306,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.6019503546099291,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.502138952739766,
      "success_rate.epoch.global": 0.5652173913043478,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9980137711864406,
      "tokens_p.mean_below_band": 2.143982176979383e-09,
      "tokens_p.mean_in_band": 0.7151898734177216,
      "tokens_rate.above_band": 0.97736057426836,
      "tokens_rate.below_band": 0.0008282716731087797,
      "tokens_rate.in_band": 0.021811154058531197
    },
    {
      "epoch": 0.1579122340425532,
      "grad_norm": 274.1340082487527,
      "learning_rate": 1.9964520561199625e-07,
      "loss": 1.0499,
      "step": 950,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4444444444444444,
      "success_rate.epoch.env.logic": 0.3456221198156682,
      "success_rate.epoch.env.math": 0.8253275109170306,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.6019417475728155,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5011531858965311,
      "success_rate.epoch.global": 0.5643620011242271,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.16666666666666666,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9974349937343359,
      "tokens_p.mean_in_band": 0.3192830550541516,
      "tokens_rate.above_band": 0.8521089161772557,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14789108382274427
    },
    {
      "epoch": 0.15874335106382978,
      "grad_norm": 276.59972713042356,
      "learning_rate": 1.9964019182969965e-07,
      "loss": 1.042,
      "step": 955,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4444444444444444,
      "success_rate.epoch.env.logic": 0.3486238532110092,
      "success_rate.epoch.env.math": 0.8260869565217391,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.6012269938650306,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5014301336503734,
      "success_rate.epoch.global": 0.5645612073784237,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9913793103448276,
      "tokens_p.mean_in_band": 0.5730794270833334,
      "tokens_rate.above_band": 0.8787878787878788,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12121212121212122
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 292.3355189996635,
      "learning_rate": 1.9963514319087415e-07,
      "loss": 1.0451,
      "step": 960,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4444444444444444,
      "success_rate.epoch.env.logic": 0.3470319634703196,
      "success_rate.epoch.env.math": 0.8283261802575107,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.6010498687664042,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5014728799136875,
      "success_rate.epoch.global": 0.5649025069637883,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9996360989810772,
      "tokens_p.mean_in_band": 0.6727678571428571,
      "tokens_rate.above_band": 0.9515235457063712,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04847645429362881
    },
    {
      "epoch": 0.16040558510638298,
      "grad_norm": 226.28395497949296,
      "learning_rate": 1.996300597044799e-07,
      "loss": 1.0401,
      "step": 965,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.3470319634703196,
      "success_rate.epoch.env.math": 0.8247863247863247,
      "success_rate.epoch.env.sat": 0.06493506493506493,
      "success_rate.epoch.env.science": 0.6022628372497825,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5022816070908727,
      "success_rate.epoch.global": 0.565410199556541,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9897378177966102,
      "tokens_p.mean_in_band": 0.686141304347826,
      "tokens_rate.above_band": 0.9111969111969112,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0888030888030888
    },
    {
      "epoch": 0.1612367021276596,
      "grad_norm": 232.84025810415997,
      "learning_rate": 1.9962494137953883e-07,
      "loss": 1.0182,
      "step": 970,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.3470319634703196,
      "success_rate.epoch.env.math": 0.8235294117647058,
      "success_rate.epoch.env.sat": 0.06493506493506493,
      "success_rate.epoch.env.science": 0.6013864818024264,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5020876735936931,
      "success_rate.epoch.global": 0.5653612796469939,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.3833333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9948261589403974,
      "tokens_p.mean_below_band": 2.1047890186309814e-07,
      "tokens_p.mean_in_band": 0.5435697115384616,
      "tokens_rate.above_band": 0.937888198757764,
      "tokens_rate.below_band": 0.0015527950310559005,
      "tokens_rate.in_band": 0.06055900621118013
    },
    {
      "epoch": 0.16206781914893617,
      "grad_norm": 406.02213582225613,
      "learning_rate": 1.996197882251347e-07,
      "loss": 0.8577,
      "step": 975,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.35,
      "success_rate.epoch.env.math": 0.825,
      "success_rate.epoch.env.sat": 0.06493506493506493,
      "success_rate.epoch.env.science": 0.6008620689655172,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.502443511041699,
      "success_rate.epoch.global": 0.5658616904500549,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.993195564516129,
      "tokens_p.mean_in_band": 0.6822467672413793,
      "tokens_rate.above_band": 0.8953068592057761,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10469314079422383
    },
    {
      "epoch": 0.16289893617021275,
      "grad_norm": 242.50168808098468,
      "learning_rate": 1.996146002504131e-07,
      "loss": 0.9381,
      "step": 980,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.35135135135135137,
      "success_rate.epoch.env.math": 0.825,
      "success_rate.epoch.env.sat": 0.0641025641025641,
      "success_rate.epoch.env.science": 0.6018916595012898,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5025842784103012,
      "success_rate.epoch.global": 0.5661925601750547,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.275,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9987796373779637,
      "tokens_p.mean_below_band": 4.3655745685100555e-09,
      "tokens_p.mean_in_band": 0.5609580592105263,
      "tokens_rate.above_band": 0.9251612903225807,
      "tokens_rate.below_band": 0.0012903225806451613,
      "tokens_rate.in_band": 0.07354838709677419
    },
    {
      "epoch": 0.16373005319148937,
      "grad_norm": 121.89361802490136,
      "learning_rate": 1.9960937746458141e-07,
      "loss": 1.3233,
      "step": 985,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.34977578475336324,
      "success_rate.epoch.env.math": 0.8264462809917356,
      "success_rate.epoch.env.sat": 0.06329113924050633,
      "success_rate.epoch.env.science": 0.602224123182207,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5025289832478109,
      "success_rate.epoch.global": 0.5663764961915125,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9955420197740112,
      "tokens_p.mean_in_band": 0.637217420212766,
      "tokens_rate.above_band": 0.937748344370861,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06225165562913907
    },
    {
      "epoch": 0.16456117021276595,
      "grad_norm": 237.6764822308073,
      "learning_rate": 1.996041198769088e-07,
      "loss": 0.9872,
      "step": 990,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.34977578475336324,
      "success_rate.epoch.env.math": 0.8271604938271605,
      "success_rate.epoch.env.sat": 0.06329113924050633,
      "success_rate.epoch.env.science": 0.6015293118096856,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5025307470171657,
      "success_rate.epoch.global": 0.5663237682728749,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9861918604651163,
      "tokens_p.mean_in_band": 0.6541078629032258,
      "tokens_rate.above_band": 0.80625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19375
    },
    {
      "epoch": 0.16539228723404256,
      "grad_norm": 139.83144603807995,
      "learning_rate": 1.9959882749672624e-07,
      "loss": 0.8594,
      "step": 995,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.35267857142857145,
      "success_rate.epoch.env.math": 0.8237704918032787,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6028789161727349,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5025372242693357,
      "success_rate.epoch.global": 0.5668824163969794,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9883373205741627,
      "tokens_p.mean_in_band": 0.5617357336956522,
      "tokens_rate.above_band": 0.8196078431372549,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1803921568627451
    },
    {
      "epoch": 0.16622340425531915,
      "grad_norm": 110.73587835971473,
      "learning_rate": 1.9959350033342633e-07,
      "loss": 1.0128,
      "step": 1000,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44680851063829785,
      "success_rate.epoch.env.logic": 0.35398230088495575,
      "success_rate.epoch.env.math": 0.8237704918032787,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.603201347935973,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5018020363354707,
      "success_rate.epoch.global": 0.5668276972624798,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.38888888888888884,
      "success_rate.window.global": 0.5555555555555556,
      "tokens_p.mean_above_band": 0.9904321598101266,
      "tokens_p.mean_in_band": 0.5934111015981736,
      "tokens_rate.above_band": 0.8523263654753878,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14767363452461227
    },
    {
      "epoch": 0.16705452127659576,
      "grad_norm": 193.38872491235324,
      "learning_rate": 1.9958813839646348e-07,
      "loss": 0.9668,
      "step": 1005,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39622641509433965,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4375,
      "success_rate.epoch.env.logic": 0.3508771929824561,
      "success_rate.epoch.env.math": 0.8244897959183674,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6031879194630873,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5007376960719622,
      "success_rate.epoch.global": 0.5662393162393162,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9968643707482994,
      "tokens_p.mean_below_band": 3.3155083656311035e-07,
      "tokens_p.mean_in_band": 0.5047869694960212,
      "tokens_rate.above_band": 0.9156840934371524,
      "tokens_rate.below_band": 0.0004449388209121246,
      "tokens_rate.in_band": 0.08387096774193549
    },
    {
      "epoch": 0.16788563829787234,
      "grad_norm": 146.3020329942035,
      "learning_rate": 1.9958274169535392e-07,
      "loss": 0.8669,
      "step": 1010,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42857142857142855,
      "success_rate.epoch.env.logic": 0.34934497816593885,
      "success_rate.epoch.env.math": 0.8218623481781376,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6036789297658863,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5006089477656483,
      "success_rate.epoch.global": 0.5661881977671451,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.42000000000000004,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9983982491753363,
      "tokens_p.mean_below_band": 3.688037395477295e-07,
      "tokens_p.mean_in_band": 0.568425422705314,
      "tokens_rate.above_band": 0.9498674379368522,
      "tokens_rate.below_band": 0.00024102193299590263,
      "tokens_rate.in_band": 0.049891540130151846
    },
    {
      "epoch": 0.16871675531914893,
      "grad_norm": 399.96006466207245,
      "learning_rate": 1.9957731023967538e-07,
      "loss": 1.0633,
      "step": 1015,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42857142857142855,
      "success_rate.epoch.env.logic": 0.35064935064935066,
      "success_rate.epoch.env.math": 0.8192771084337349,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6025,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.500385329854114,
      "success_rate.epoch.global": 0.5653785071466384,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.16666666666666666,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9959720254957507,
      "tokens_p.mean_in_band": 0.5634548611111111,
      "tokens_rate.above_band": 0.9400798934753661,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05992010652463382
    },
    {
      "epoch": 0.16954787234042554,
      "grad_norm": 123.52066398196166,
      "learning_rate": 1.9957184403906738e-07,
      "loss": 0.8311,
      "step": 1020,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42,
      "success_rate.epoch.env.logic": 0.35064935064935066,
      "success_rate.epoch.env.math": 0.8207171314741036,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6044776119402985,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4999168031640448,
      "success_rate.epoch.global": 0.5669125395152792,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9859549409061064,
      "tokens_p.mean_in_band": 0.5458587398373984,
      "tokens_rate.above_band": 0.7796263117481443,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.22037368825185563
    },
    {
      "epoch": 0.17037898936170212,
      "grad_norm": 134.20513569651126,
      "learning_rate": 1.995663431032311e-07,
      "loss": 1.0981,
      "step": 1025,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42,
      "success_rate.epoch.env.logic": 0.35344827586206895,
      "success_rate.epoch.env.math": 0.8207171314741036,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6044591246903386,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4994961695781676,
      "success_rate.epoch.global": 0.5669291338582677,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.994140625,
      "tokens_p.mean_in_band": 0.5643643465909091,
      "tokens_rate.above_band": 0.9385474860335196,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061452513966480445
    },
    {
      "epoch": 0.17121010638297873,
      "grad_norm": 165.92382388904176,
      "learning_rate": 1.9956080744192937e-07,
      "loss": 0.8825,
      "step": 1030,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42,
      "success_rate.epoch.env.logic": 0.358974358974359,
      "success_rate.epoch.env.math": 0.8207171314741036,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.6049382716049383,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.499971953677133,
      "success_rate.epoch.global": 0.5674686192468619,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.5238095238095238,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9903935185185185,
      "tokens_p.mean_in_band": 0.6736971227134146,
      "tokens_rate.above_band": 0.8681672025723473,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13183279742765272
    },
    {
      "epoch": 0.17204122340425532,
      "grad_norm": 155.7053428936629,
      "learning_rate": 1.995552370649866e-07,
      "loss": 1.1059,
      "step": 1035,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42,
      "success_rate.epoch.env.logic": 0.3559322033898305,
      "success_rate.epoch.env.math": 0.8207171314741036,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.6072013093289689,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49990112478072407,
      "success_rate.epoch.global": 0.5684539302446643,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9987157534246576,
      "tokens_p.mean_in_band": 0.6636202830188679,
      "tokens_rate.above_band": 0.9323116219667944,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06768837803320563
    },
    {
      "epoch": 0.17287234042553193,
      "grad_norm": 155.65767786776823,
      "learning_rate": 1.9954963198228883e-07,
      "loss": 0.8423,
      "step": 1040,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42,
      "success_rate.epoch.env.logic": 0.3559322033898305,
      "success_rate.epoch.env.math": 0.8181818181818182,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.6083061889250815,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4997710853537993,
      "success_rate.epoch.global": 0.5692068429237948,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4523809523809524,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9857519157088123,
      "tokens_p.mean_in_band": 0.46028343023255813,
      "tokens_rate.above_band": 0.5483193277310925,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.45168067226890757
    },
    {
      "epoch": 0.1737034574468085,
      "grad_norm": 126.90697398168803,
      "learning_rate": 1.9954399220378377e-07,
      "loss": 0.9028,
      "step": 1045,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43137254901960786,
      "success_rate.epoch.env.logic": 0.35443037974683544,
      "success_rate.epoch.env.math": 0.8188976377952756,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.6097165991902834,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5008617176497331,
      "success_rate.epoch.global": 0.5703971119133574,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9917441291585127,
      "tokens_p.mean_in_band": 0.6861979166666666,
      "tokens_rate.above_band": 0.9659735349716446,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034026465028355386
    },
    {
      "epoch": 0.1745345744680851,
      "grad_norm": 248.92500058424363,
      "learning_rate": 1.9953831773948058e-07,
      "loss": 1.0204,
      "step": 1050,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43137254901960786,
      "success_rate.epoch.env.logic": 0.35714285714285715,
      "success_rate.epoch.env.math": 0.8196078431372549,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.6095008051529791,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.50115325298616,
      "success_rate.epoch.global": 0.5708418891170431,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9915865384615384,
      "tokens_p.mean_in_band": 0.615234375,
      "tokens_rate.above_band": 0.8904109589041096,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1095890410958904
    },
    {
      "epoch": 0.1753656914893617,
      "grad_norm": 162.11820232870596,
      "learning_rate": 1.9953260859945009e-07,
      "loss": 1.0052,
      "step": 1055,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4230769230769231,
      "success_rate.epoch.env.logic": 0.35564853556485354,
      "success_rate.epoch.env.math": 0.8178294573643411,
      "success_rate.epoch.env.sat": 0.06097560975609756,
      "success_rate.epoch.env.science": 0.610128617363344,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5000902251326266,
      "success_rate.epoch.global": 0.5705521472392638,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.2222222222222222,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.993865948533812,
      "tokens_p.mean_in_band": 0.5909261067708333,
      "tokens_rate.above_band": 0.8744113029827315,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12558869701726844
    },
    {
      "epoch": 0.1761968085106383,
      "grad_norm": 140.1974730223309,
      "learning_rate": 1.995268647938246e-07,
      "loss": 0.8321,
      "step": 1060,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4230769230769231,
      "success_rate.epoch.env.logic": 0.36099585062240663,
      "success_rate.epoch.env.math": 0.8185328185328186,
      "success_rate.epoch.env.sat": 0.06097560975609756,
      "success_rate.epoch.env.science": 0.6108887109687751,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5007093860263958,
      "success_rate.epoch.global": 0.5717922606924644,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.991822429906542,
      "tokens_p.mean_in_band": 0.6958451704545454,
      "tokens_rate.above_band": 0.9067796610169492,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09322033898305085
    },
    {
      "epoch": 0.1770279255319149,
      "grad_norm": 642.0174638685222,
      "learning_rate": 1.9952108633279797e-07,
      "loss": 0.8895,
      "step": 1065,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4230769230769231,
      "success_rate.epoch.env.logic": 0.36363636363636365,
      "success_rate.epoch.env.math": 0.8192307692307692,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.6090764331210191,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5007813442048936,
      "success_rate.epoch.global": 0.5709219858156028,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.2857142857142857,
      "success_rate.window.env_macro_mean": 0.5714285714285714,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.994092039800995,
      "tokens_p.mean_below_band": 3.510081114654895e-12,
      "tokens_p.mean_in_band": 0.5476310483870968,
      "tokens_rate.above_band": 0.8626609442060086,
      "tokens_rate.below_band": 0.004291845493562232,
      "tokens_rate.in_band": 0.13304721030042918
    },
    {
      "epoch": 0.1778590425531915,
      "grad_norm": 265.81020007173316,
      "learning_rate": 1.9951527322662555e-07,
      "loss": 0.9334,
      "step": 1070,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4230769230769231,
      "success_rate.epoch.env.logic": 0.35918367346938773,
      "success_rate.epoch.env.math": 0.8192307692307692,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.6098334655035687,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5004453753154002,
      "success_rate.epoch.global": 0.570635721493441,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.2222222222222222,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9998149792776792,
      "tokens_p.mean_in_band": 0.562548225308642,
      "tokens_rate.above_band": 0.9542372881355933,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04576271186440678
    },
    {
      "epoch": 0.17869015957446807,
      "grad_norm": 226.09530519572337,
      "learning_rate": 1.9950942548562418e-07,
      "loss": 1.1182,
      "step": 1075,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4230769230769231,
      "success_rate.epoch.env.logic": 0.3603238866396761,
      "success_rate.epoch.env.math": 0.8212927756653993,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.6097946287519748,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5007329555747935,
      "success_rate.epoch.global": 0.571285140562249,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.7000000000000001,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977156432748538,
      "tokens_p.mean_in_band": 0.5841238839285714,
      "tokens_rate.above_band": 0.9513212795549374,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.048678720445062586
    },
    {
      "epoch": 0.17952127659574468,
      "grad_norm": 264.55522665586335,
      "learning_rate": 1.9950354312017216e-07,
      "loss": 0.9752,
      "step": 1080,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39285714285714285,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.3603238866396761,
      "success_rate.epoch.env.math": 0.8212927756653993,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.6092767295597484,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49931083377576024,
      "success_rate.epoch.global": 0.5705,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.125,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9958608989223844,
      "tokens_p.mean_below_band": 2.169981598854065e-07,
      "tokens_p.mean_in_band": 0.5555615011415526,
      "tokens_rate.above_band": 0.9172922922922923,
      "tokens_rate.below_band": 0.0005005005005005005,
      "tokens_rate.in_band": 0.08220720720720721
    },
    {
      "epoch": 0.18035239361702127,
      "grad_norm": 460.79970668050754,
      "learning_rate": 1.9949762614070927e-07,
      "loss": 0.9209,
      "step": 1085,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39285714285714285,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.3629032258064516,
      "success_rate.epoch.env.math": 0.821969696969697,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.6095461658841941,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49963135166626194,
      "success_rate.epoch.global": 0.5712151394422311,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.7380952380952381,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9987753991291727,
      "tokens_p.mean_in_band": 0.6100983796296297,
      "tokens_rate.above_band": 0.9622905027932961,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03770949720670391
    },
    {
      "epoch": 0.18118351063829788,
      "grad_norm": 178.41552085802275,
      "learning_rate": 1.9949167455773669e-07,
      "loss": 0.9215,
      "step": 1090,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39285714285714285,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.364,
      "success_rate.epoch.env.math": 0.8226415094339623,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6107644305772231,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4998376877589193,
      "success_rate.epoch.global": 0.5719246031746031,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9952598314606742,
      "tokens_p.mean_below_band": 9.255018085241318e-09,
      "tokens_p.mean_in_band": 0.6237847222222223,
      "tokens_rate.above_band": 0.9393139841688655,
      "tokens_rate.below_band": 0.0013192612137203166,
      "tokens_rate.in_band": 0.059366754617414245
    },
    {
      "epoch": 0.18201462765957446,
      "grad_norm": 219.7736325707439,
      "learning_rate": 1.9948568838181696e-07,
      "loss": 1.0282,
      "step": 1095,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39285714285714285,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.36363636363636365,
      "success_rate.epoch.env.math": 0.8226415094339623,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.609472049689441,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49968714073606313,
      "success_rate.epoch.global": 0.5708641975308641,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.3333333333333333,
      "tokens_p.mean_above_band": 0.9967320261437909,
      "tokens_p.mean_in_band": 0.5900735294117647,
      "tokens_rate.above_band": 0.9375,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0625
    },
    {
      "epoch": 0.18284574468085107,
      "grad_norm": 224.39910614315582,
      "learning_rate": 1.994796676235742e-07,
      "loss": 1.0531,
      "step": 1100,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39655172413793105,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.36220472440944884,
      "success_rate.epoch.env.math": 0.8226415094339623,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6102088167053364,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49995984156058754,
      "success_rate.epoch.global": 0.5710772257747172,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.29166666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9987969201154957,
      "tokens_p.mean_in_band": 0.5738044507575758,
      "tokens_rate.above_band": 0.9402714932126697,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05972850678733032
    },
    {
      "epoch": 0.18367686170212766,
      "grad_norm": 266.2200682538834,
      "learning_rate": 1.9947361229369366e-07,
      "loss": 0.8472,
      "step": 1105,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39655172413793105,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.3607843137254902,
      "success_rate.epoch.env.math": 0.8233082706766918,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.611837048424289,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5000393490403806,
      "success_rate.epoch.global": 0.5721977484092021,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.999702380952381,
      "tokens_p.mean_below_band": 1.5688783605583012e-11,
      "tokens_p.mean_in_band": 0.6096643518518519,
      "tokens_rate.above_band": 0.9574468085106383,
      "tokens_rate.below_band": 0.001519756838905775,
      "tokens_rate.in_band": 0.041033434650455926
    },
    {
      "epoch": 0.18450797872340424,
      "grad_norm": 169.38340095825396,
      "learning_rate": 1.9946752240292212e-07,
      "loss": 0.9755,
      "step": 1110,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.3607843137254902,
      "success_rate.epoch.env.math": 0.8252788104089219,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6125574272588055,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4996729583952343,
      "success_rate.epoch.global": 0.5730994152046783,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977379356568364,
      "tokens_p.mean_in_band": 0.51043701171875,
      "tokens_rate.above_band": 0.9209876543209876,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07901234567901234
    },
    {
      "epoch": 0.18533909574468085,
      "grad_norm": 152.13962411654154,
      "learning_rate": 1.9946139796206767e-07,
      "loss": 0.8007,
      "step": 1115,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.41509433962264153,
      "success_rate.epoch.env.logic": 0.35797665369649806,
      "success_rate.epoch.env.math": 0.8252788104089219,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6137404580152672,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4995252648250043,
      "success_rate.epoch.global": 0.5733722060252673,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9983397016011645,
      "tokens_p.mean_in_band": 0.6006634424603174,
      "tokens_rate.above_band": 0.9561586638830898,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04384133611691023
    },
    {
      "epoch": 0.18617021276595744,
      "grad_norm": 439.98687769966773,
      "learning_rate": 1.9945523898199963e-07,
      "loss": 1.0224,
      "step": 1120,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42592592592592593,
      "success_rate.epoch.env.logic": 0.35658914728682173,
      "success_rate.epoch.env.math": 0.8252788104089219,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6135155656795748,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5003633727848148,
      "success_rate.epoch.global": 0.5732946298984035,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9929454851104706,
      "tokens_p.mean_in_band": 0.5964936755952381,
      "tokens_rate.above_band": 0.961218836565097,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038781163434903045
    },
    {
      "epoch": 0.18700132978723405,
      "grad_norm": 442.11912082659296,
      "learning_rate": 1.9944904547364873e-07,
      "loss": 0.9086,
      "step": 1125,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42592592592592593,
      "success_rate.epoch.env.logic": 0.35658914728682173,
      "success_rate.epoch.env.math": 0.8252788104089219,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6131221719457014,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5003276097180991,
      "success_rate.epoch.global": 0.5732177263969171,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.986204954954955,
      "tokens_p.mean_in_band": 0.4508272058823529,
      "tokens_rate.above_band": 0.7655172413793103,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.23448275862068965
    },
    {
      "epoch": 0.18783244680851063,
      "grad_norm": 120.69277736939155,
      "learning_rate": 1.9944281744800692e-07,
      "loss": 0.8571,
      "step": 1130,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42592592592592593,
      "success_rate.epoch.env.logic": 0.3576923076923077,
      "success_rate.epoch.env.math": 0.8252788104089219,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6133633633633634,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5004498235202034,
      "success_rate.epoch.global": 0.5734165067178503,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0001788268955651,
      "tokens_p.mean_below_band": 1.2278178473934531e-11,
      "tokens_p.mean_in_band": 0.5243626644736842,
      "tokens_rate.above_band": 0.9728601252609603,
      "tokens_rate.below_band": 0.0006958942240779402,
      "tokens_rate.in_band": 0.026443980514961725
    },
    {
      "epoch": 0.18866356382978725,
      "grad_norm": 542.5901995373054,
      "learning_rate": 1.9943655491612742e-07,
      "loss": 1.1015,
      "step": 1135,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.42592592592592593,
      "success_rate.epoch.env.logic": 0.3574144486692015,
      "success_rate.epoch.env.math": 0.8252788104089219,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6123973114264376,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.500336740705655,
      "success_rate.epoch.global": 0.5725883476599809,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.38095238095238093,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9929191842900302,
      "tokens_p.mean_in_band": 0.6369047619047619,
      "tokens_rate.above_band": 0.8873994638069705,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1126005361930295
    },
    {
      "epoch": 0.18949468085106383,
      "grad_norm": 269.63365533118093,
      "learning_rate": 1.9943025788912467e-07,
      "loss": 1.1228,
      "step": 1140,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.3574144486692015,
      "success_rate.epoch.env.math": 0.825925925925926,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.6136701337295691,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5014601632745501,
      "success_rate.epoch.global": 0.5739419876367094,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965156794425087,
      "tokens_p.mean_in_band": 0.6739211309523809,
      "tokens_rate.above_band": 0.9318181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06818181818181818
    },
    {
      "epoch": 0.1903257978723404,
      "grad_norm": 143.92137110226676,
      "learning_rate": 1.9942392637817437e-07,
      "loss": 0.9558,
      "step": 1145,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36466165413533835,
      "success_rate.epoch.env.math": 0.825925925925926,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.613905325443787,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5021403812000369,
      "success_rate.epoch.global": 0.5748106060606061,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7083333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9985868863049095,
      "tokens_p.mean_in_band": 0.5771205357142857,
      "tokens_rate.above_band": 0.9567367119901112,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04326328800988875
    },
    {
      "epoch": 0.19115691489361702,
      "grad_norm": 187.30544503821565,
      "learning_rate": 1.9941756039451342e-07,
      "loss": 0.9217,
      "step": 1150,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36704119850187267,
      "success_rate.epoch.env.math": 0.8278388278388278,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.6143067846607669,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5025034380531616,
      "success_rate.epoch.global": 0.5756718528995757,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9932544052863436,
      "tokens_p.mean_in_band": 0.7085433467741935,
      "tokens_rate.above_band": 0.8798449612403101,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12015503875968993
    },
    {
      "epoch": 0.1919880319148936,
      "grad_norm": 1507.552530199978,
      "learning_rate": 1.9941115994943982e-07,
      "loss": 0.9314,
      "step": 1155,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.3898305084745763,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36704119850187267,
      "success_rate.epoch.env.math": 0.8284671532846716,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.6158357771260997,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5026995578632686,
      "success_rate.epoch.global": 0.5769953051643193,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9916857798165137,
      "tokens_p.mean_in_band": 0.6243489583333334,
      "tokens_rate.above_band": 0.8582677165354331,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14173228346456693
    },
    {
      "epoch": 0.19281914893617022,
      "grad_norm": 340.14798639891603,
      "learning_rate": 1.9940472505431285e-07,
      "loss": 0.9579,
      "step": 1160,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39344262295081966,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36704119850187267,
      "success_rate.epoch.env.math": 0.8290909090909091,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.6167883211678832,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5031712318927472,
      "success_rate.epoch.global": 0.5778401122019635,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.7380952380952381,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.998371138996139,
      "tokens_p.mean_in_band": 0.6483623798076923,
      "tokens_rate.above_band": 0.975517890772128,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02448210922787194
    },
    {
      "epoch": 0.1936502659574468,
      "grad_norm": 251.58210047327617,
      "learning_rate": 1.9939825572055284e-07,
      "loss": 1.0158,
      "step": 1165,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.39344262295081966,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.3643122676579926,
      "success_rate.epoch.env.math": 0.8297101449275363,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.6167272727272727,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5029738915793049,
      "success_rate.epoch.global": 0.5775500698649279,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.611111111111111,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9965024330900243,
      "tokens_p.mean_in_band": 0.5450114678899083,
      "tokens_rate.above_band": 0.9187779433681073,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08122205663189269
    },
    {
      "epoch": 0.19448138297872342,
      "grad_norm": 166.83858758307767,
      "learning_rate": 1.9939175195964128e-07,
      "loss": 0.7169,
      "step": 1170,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4032258064516129,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.3643122676579926,
      "success_rate.epoch.env.math": 0.8315412186379928,
      "success_rate.epoch.env.sat": 0.05747126436781609,
      "success_rate.epoch.env.science": 0.6171138506163887,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5039419434026157,
      "success_rate.epoch.global": 0.5781177561427909,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9959446564885496,
      "tokens_p.mean_in_band": 0.6717862215909091,
      "tokens_rate.above_band": 0.8993135011441648,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10068649885583524
    },
    {
      "epoch": 0.1953125,
      "grad_norm": 668.3259426053454,
      "learning_rate": 1.9938521378312078e-07,
      "loss": 0.7603,
      "step": 1175,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4032258064516129,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36666666666666664,
      "success_rate.epoch.env.math": 0.8291814946619217,
      "success_rate.epoch.env.sat": 0.05747126436781609,
      "success_rate.epoch.env.science": 0.6177745664739884,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5040015243926341,
      "success_rate.epoch.global": 0.5787528868360278,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9927884615384616,
      "tokens_p.mean_in_band": 0.6216216216216216,
      "tokens_rate.above_band": 0.7944444444444444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.20555555555555555
    },
    {
      "epoch": 0.19614361702127658,
      "grad_norm": 224.9222325548951,
      "learning_rate": 1.9937864120259492e-07,
      "loss": 0.9413,
      "step": 1180,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4032258064516129,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36531365313653136,
      "success_rate.epoch.env.math": 0.8309859154929577,
      "success_rate.epoch.env.sat": 0.05747126436781609,
      "success_rate.epoch.env.science": 0.619150467962563,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5041676433734955,
      "success_rate.epoch.global": 0.5800367985280589,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9911404639175257,
      "tokens_p.mean_in_band": 0.6908735795454546,
      "tokens_rate.above_band": 0.9463414634146341,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05365853658536585
    },
    {
      "epoch": 0.1969747340425532,
      "grad_norm": 182.2938333894031,
      "learning_rate": 1.9937203422972855e-07,
      "loss": 0.8178,
      "step": 1185,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4032258064516129,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.3639705882352941,
      "success_rate.epoch.env.math": 0.8315789473684211,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6205164992826399,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5041642720775562,
      "success_rate.epoch.global": 0.580659945004583,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9918488777089783,
      "tokens_p.mean_in_band": 0.5329213876705653,
      "tokens_rate.above_band": 0.8831168831168831,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11688311688311688
    },
    {
      "epoch": 0.19780585106382978,
      "grad_norm": 270.4151080623194,
      "learning_rate": 1.9936539287624733e-07,
      "loss": 0.9748,
      "step": 1190,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.3639705882352941,
      "success_rate.epoch.env.math": 0.8327526132404182,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.622412562455389,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5053044843767878,
      "success_rate.epoch.global": 0.5825729927007299,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9959124472573839,
      "tokens_p.mean_in_band": 0.6805098684210527,
      "tokens_rate.above_band": 0.92578125,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07421875
    },
    {
      "epoch": 0.1986369680851064,
      "grad_norm": 187.44005324716238,
      "learning_rate": 1.9935871715393803e-07,
      "loss": 0.7685,
      "step": 1195,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36496350364963503,
      "success_rate.epoch.env.math": 0.8327526132404182,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6228693181818182,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5054362726623123,
      "success_rate.epoch.global": 0.582916855974557,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977438556067588,
      "tokens_p.mean_in_band": 0.527294921875,
      "tokens_rate.above_band": 0.9421128798842258,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05788712011577424
    },
    {
      "epoch": 0.19946808510638298,
      "grad_norm": 173.36894907611784,
      "learning_rate": 1.9935200707464848e-07,
      "loss": 0.9895,
      "step": 1200,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36363636363636365,
      "success_rate.epoch.env.math": 0.8339100346020761,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6242038216560509,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5055421621916414,
      "success_rate.epoch.global": 0.583974649162517,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9961963660245184,
      "tokens_p.mean_in_band": 0.5931165540540541,
      "tokens_rate.above_band": 0.9391447368421053,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06085526315789474
    },
    {
      "epoch": 0.2002992021276596,
      "grad_norm": 162.61905989296628,
      "learning_rate": 1.993452626502874e-07,
      "loss": 0.7882,
      "step": 1205,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43636363636363634,
      "success_rate.epoch.env.logic": 0.36363636363636365,
      "success_rate.epoch.env.math": 0.8350515463917526,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6250880902043693,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49663541494964086,
      "success_rate.epoch.global": 0.584761045987376,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9899193548387096,
      "tokens_p.mean_in_band": 0.60546875,
      "tokens_rate.above_band": 0.84765625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15234375
    },
    {
      "epoch": 0.20113031914893617,
      "grad_norm": 214.75697790751957,
      "learning_rate": 1.993384838928245e-07,
      "loss": 1.2434,
      "step": 1210,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.36363636363636365,
      "success_rate.epoch.env.math": 0.8350515463917526,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6248246844319776,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4975264630671448,
      "success_rate.epoch.global": 0.5849056603773585,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9907029750479847,
      "tokens_p.mean_in_band": 0.6961300872093024,
      "tokens_rate.above_band": 0.9237588652482269,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07624113475177305
    },
    {
      "epoch": 0.20196143617021275,
      "grad_norm": 174.26995888180224,
      "learning_rate": 1.9933167081429038e-07,
      "loss": 0.7754,
      "step": 1215,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.36594202898550726,
      "success_rate.epoch.env.math": 0.8333333333333334,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6261355695317959,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4976990391935577,
      "success_rate.epoch.global": 0.5861297539149888,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9889787946428571,
      "tokens_p.mean_in_band": 0.7231026785714286,
      "tokens_rate.above_band": 0.8648648648648649,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13513513513513514
    },
    {
      "epoch": 0.20279255319148937,
      "grad_norm": 492.1817572691923,
      "learning_rate": 1.993248234267766e-07,
      "loss": 1.1205,
      "step": 1220,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4126984126984127,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.36594202898550726,
      "success_rate.epoch.env.math": 0.8338983050847457,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.6256089074460682,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4977025218904382,
      "success_rate.epoch.global": 0.5860838537020517,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9901960784313726,
      "tokens_p.mean_in_band": 0.6036458333333333,
      "tokens_rate.above_band": 0.7727272727272727,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.22727272727272727
    },
    {
      "epoch": 0.20362367021276595,
      "grad_norm": 271.5292273195168,
      "learning_rate": 1.9931794174243564e-07,
      "loss": 1.0452,
      "step": 1225,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.40625,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.36594202898550726,
      "success_rate.epoch.env.math": 0.831081081081081,
      "success_rate.epoch.env.sat": 0.056179775280898875,
      "success_rate.epoch.env.science": 0.6257796257796258,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49681767417172884,
      "success_rate.epoch.global": 0.5855175477565526,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.17857142857142858,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9943181818181818,
      "tokens_p.mean_in_band": 0.6185360863095238,
      "tokens_rate.above_band": 0.8719512195121951,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12804878048780488
    },
    {
      "epoch": 0.20445478723404256,
      "grad_norm": 136.54441249915374,
      "learning_rate": 1.9931102577348075e-07,
      "loss": 0.9196,
      "step": 1230,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.36462093862815886,
      "success_rate.epoch.env.math": 0.831081081081081,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.6258644536652835,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4969068038893539,
      "success_rate.epoch.global": 0.5850310008857396,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9966831841432225,
      "tokens_p.mean_in_band": 0.6754705255681818,
      "tokens_rate.above_band": 0.9467312348668281,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053268765133171914
    },
    {
      "epoch": 0.20528590425531915,
      "grad_norm": 347.9254341197953,
      "learning_rate": 1.9930407553218612e-07,
      "loss": 1.0113,
      "step": 1235,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.36200716845878134,
      "success_rate.epoch.env.math": 0.8294314381270903,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.6259489302967564,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4964714005164088,
      "success_rate.epoch.global": 0.5844728716365241,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.29166666666666663,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9984069668649108,
      "tokens_p.mean_below_band": 3.1650415621697903e-10,
      "tokens_p.mean_in_band": 0.5015914351851852,
      "tokens_rate.above_band": 0.9348689436060366,
      "tokens_rate.below_band": 0.0007942811755361397,
      "tokens_rate.in_band": 0.06433677521842732
    },
    {
      "epoch": 0.20611702127659576,
      "grad_norm": 166.51054372529995,
      "learning_rate": 1.9929709103088669e-07,
      "loss": 0.9434,
      "step": 1240,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45614035087719296,
      "success_rate.epoch.env.logic": 0.36200716845878134,
      "success_rate.epoch.env.math": 0.83,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.6247422680412371,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4972962804315007,
      "success_rate.epoch.global": 0.5841758241758241,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9945047669491526,
      "tokens_p.mean_in_band": 0.5641276041666666,
      "tokens_rate.above_band": 0.9291338582677166,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07086614173228346
    },
    {
      "epoch": 0.20694813829787234,
      "grad_norm": 225.06886360968747,
      "learning_rate": 1.9929007228197822e-07,
      "loss": 0.8741,
      "step": 1245,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45614035087719296,
      "success_rate.epoch.env.logic": 0.36200716845878134,
      "success_rate.epoch.env.math": 0.8305647840531561,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.6247436773752563,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4973477525576076,
      "success_rate.epoch.global": 0.5845008756567426,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9834947183098591,
      "tokens_p.mean_below_band": 4.1443854570388794e-08,
      "tokens_p.mean_in_band": 0.6045572916666667,
      "tokens_rate.above_band": 0.8208092485549133,
      "tokens_rate.below_band": 0.005780346820809248,
      "tokens_rate.in_band": 0.17341040462427745
    },
    {
      "epoch": 0.20777925531914893,
      "grad_norm": 155.03719314404663,
      "learning_rate": 1.9928301929791736e-07,
      "loss": 1.0002,
      "step": 1250,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45614035087719296,
      "success_rate.epoch.env.logic": 0.36200716845878134,
      "success_rate.epoch.env.math": 0.8327868852459016,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.6232970027247956,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4974182458796335,
      "success_rate.epoch.global": 0.5843872655909289,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.2,
      "success_rate.window.env_macro_mean": 0.7333333333333334,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9945463988919667,
      "tokens_p.mean_below_band": 2.342858351767063e-09,
      "tokens_p.mean_in_band": 0.576171875,
      "tokens_rate.above_band": 0.9304123711340206,
      "tokens_rate.below_band": 0.002577319587628866,
      "tokens_rate.in_band": 0.06701030927835051
    },
    {
      "epoch": 0.20861037234042554,
      "grad_norm": 167.2013906845457,
      "learning_rate": 1.9927593209122133e-07,
      "loss": 0.8269,
      "step": 1255,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45614035087719296,
      "success_rate.epoch.env.logic": 0.36298932384341637,
      "success_rate.epoch.env.math": 0.8349514563106796,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.6240652617267165,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4985759298906898,
      "success_rate.epoch.global": 0.5857577073382545,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9975234619395204,
      "tokens_p.mean_in_band": 0.622750946969697,
      "tokens_rate.above_band": 0.9667338709677419,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03326612903225806
    },
    {
      "epoch": 0.20944148936170212,
      "grad_norm": 151.13123156120764,
      "learning_rate": 1.9926881067446826e-07,
      "loss": 0.8284,
      "step": 1260,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45614035087719296,
      "success_rate.epoch.env.logic": 0.3674911660777385,
      "success_rate.epoch.env.math": 0.8360128617363344,
      "success_rate.epoch.env.sat": 0.05434782608695652,
      "success_rate.epoch.env.science": 0.6239837398373984,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49901997506455886,
      "success_rate.epoch.global": 0.5862516212710766,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.65,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9899038461538462,
      "tokens_p.mean_in_band": 0.6902629573170732,
      "tokens_rate.above_band": 0.8879781420765027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11202185792349727
    },
    {
      "epoch": 0.21027260638297873,
      "grad_norm": 220.56530840404304,
      "learning_rate": 1.9926165506029685e-07,
      "loss": 1.1713,
      "step": 1265,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45614035087719296,
      "success_rate.epoch.env.logic": 0.3674911660777385,
      "success_rate.epoch.env.math": 0.8338658146964856,
      "success_rate.epoch.env.sat": 0.053763440860215055,
      "success_rate.epoch.env.science": 0.6239027683997299,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4987643020005354,
      "success_rate.epoch.global": 0.5859543300301594,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9901315789473685,
      "tokens_p.mean_in_band": 0.6073069852941176,
      "tokens_rate.above_band": 0.8172043010752689,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1827956989247312
    },
    {
      "epoch": 0.21110372340425532,
      "grad_norm": 313.2592446435684,
      "learning_rate": 1.9925446526140663e-07,
      "loss": 1.0604,
      "step": 1270,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46551724137931033,
      "success_rate.epoch.env.logic": 0.3674911660777385,
      "success_rate.epoch.env.math": 0.8322784810126582,
      "success_rate.epoch.env.sat": 0.053763440860215055,
      "success_rate.epoch.env.science": 0.6238223418573351,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49946513202561676,
      "success_rate.epoch.global": 0.5862660944206008,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9954490291262136,
      "tokens_p.mean_in_band": 0.5971258254278273,
      "tokens_rate.above_band": 0.9363636363636364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06363636363636363
    },
    {
      "epoch": 0.21193484042553193,
      "grad_norm": 280.80643101910096,
      "learning_rate": 1.992472412905577e-07,
      "loss": 0.8185,
      "step": 1275,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46551724137931033,
      "success_rate.epoch.env.logic": 0.3674911660777385,
      "success_rate.epoch.env.math": 0.8322784810126582,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.6239946380697051,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4994287997268765,
      "success_rate.epoch.global": 0.5862216516902011,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9968988549618321,
      "tokens_p.mean_in_band": 0.6690705128205128,
      "tokens_rate.above_band": 0.9307282415630551,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06927175843694494
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 220.10210274905896,
      "learning_rate": 1.992399831605708e-07,
      "loss": 1.0441,
      "step": 1280,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46551724137931033,
      "success_rate.epoch.env.logic": 0.3674911660777385,
      "success_rate.epoch.env.math": 0.8333333333333334,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.6230820547031354,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49944173326815877,
      "success_rate.epoch.global": 0.5861040068201193,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.375,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9864738805970149,
      "tokens_p.mean_in_band": 0.60931396484375,
      "tokens_rate.above_band": 0.7701149425287356,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.22988505747126436
    },
    {
      "epoch": 0.2135970744680851,
      "grad_norm": 138.861396860042,
      "learning_rate": 1.9923269088432745e-07,
      "loss": 0.7988,
      "step": 1285,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46551724137931033,
      "success_rate.epoch.env.logic": 0.36713286713286714,
      "success_rate.epoch.env.math": 0.83125,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.6240851630073186,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4993109583614295,
      "success_rate.epoch.global": 0.586411889596603,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.611111111111111,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977506426735219,
      "tokens_p.mean_in_band": 0.6450095663265306,
      "tokens_rate.above_band": 0.9407496977025392,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0592503022974607
    },
    {
      "epoch": 0.2144281914893617,
      "grad_norm": 277.11644678655375,
      "learning_rate": 1.9922536447476952e-07,
      "loss": 0.875,
      "step": 1290,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4576271186440678,
      "success_rate.epoch.env.logic": 0.36713286713286714,
      "success_rate.epoch.env.math": 0.8312883435582822,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.6241699867197875,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4986048715010212,
      "success_rate.epoch.global": 0.586892177589852,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.8333333333333334,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9893594457013575,
      "tokens_p.mean_in_band": 0.6767982219827586,
      "tokens_rate.above_band": 0.859086491739553,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14091350826044705
    },
    {
      "epoch": 0.2152593085106383,
      "grad_norm": 221.7188818829395,
      "learning_rate": 1.9921800394489965e-07,
      "loss": 0.907,
      "step": 1295,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.36713286713286714,
      "success_rate.epoch.env.math": 0.8318042813455657,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.6242544731610338,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4994303316680026,
      "success_rate.epoch.global": 0.5870940531421341,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6166666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9959917971662938,
      "tokens_p.mean_in_band": 0.6155225409836066,
      "tokens_rate.above_band": 0.956490727532097,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043509272467902996
    },
    {
      "epoch": 0.2160904255319149,
      "grad_norm": 229.3978572403193,
      "learning_rate": 1.99210609307781e-07,
      "loss": 1.085,
      "step": 1300,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.36713286713286714,
      "success_rate.epoch.env.math": 0.8323170731707317,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.6249176005273567,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4995372334126834,
      "success_rate.epoch.global": 0.5878151260504202,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9894911504424779,
      "tokens_p.mean_below_band": 1.126900315284729e-07,
      "tokens_p.mean_in_band": 0.72314453125,
      "tokens_rate.above_band": 0.8692307692307693,
      "tokens_rate.below_band": 0.007692307692307693,
      "tokens_rate.in_band": 0.12307692307692308
    },
    {
      "epoch": 0.2169215425531915,
      "grad_norm": 163.0903824275352,
      "learning_rate": 1.992031805765372e-07,
      "loss": 1.0955,
      "step": 1305,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.36585365853658536,
      "success_rate.epoch.env.math": 0.8308157099697885,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.6259040105193951,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49932428728366324,
      "success_rate.epoch.global": 0.5881121808287987,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.3666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.994140625,
      "tokens_p.mean_below_band": 8.149072527885437e-09,
      "tokens_p.mean_in_band": 0.6324637276785714,
      "tokens_rate.above_band": 0.8585365853658536,
      "tokens_rate.below_band": 0.004878048780487805,
      "tokens_rate.in_band": 0.13658536585365855
    },
    {
      "epoch": 0.21775265957446807,
      "grad_norm": 384.7668506257618,
      "learning_rate": 1.9919571776435243e-07,
      "loss": 0.9975,
      "step": 1310,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.36585365853658536,
      "success_rate.epoch.env.math": 0.8308157099697885,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.6254901960784314,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49928666778903014,
      "success_rate.epoch.global": 0.5879899916597164,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9840856481481481,
      "tokens_p.mean_in_band": 0.6072916666666667,
      "tokens_rate.above_band": 0.782608695652174,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21739130434782608
    },
    {
      "epoch": 0.21858377659574468,
      "grad_norm": 158.06117561136978,
      "learning_rate": 1.9918822088447138e-07,
      "loss": 0.8129,
      "step": 1315,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.3689655172413793,
      "success_rate.epoch.env.math": 0.8308157099697885,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.6267100977198697,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4996804641841422,
      "success_rate.epoch.global": 0.5889443059019119,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7619047619047619,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9909511784511784,
      "tokens_p.mean_in_band": 0.7170138888888888,
      "tokens_rate.above_band": 0.9428571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05714285714285714
    },
    {
      "epoch": 0.21941489361702127,
      "grad_norm": 279.1660130433892,
      "learning_rate": 1.9918068995019918e-07,
      "loss": 0.9803,
      "step": 1320,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.3689655172413793,
      "success_rate.epoch.env.math": 0.8313253012048193,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.626701231367466,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49972598462801743,
      "success_rate.epoch.global": 0.5892339544513457,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.986572265625,
      "tokens_p.mean_in_band": 0.5660714285714286,
      "tokens_rate.above_band": 0.7852760736196319,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2147239263803681
    },
    {
      "epoch": 0.22024601063829788,
      "grad_norm": 280.84577768197113,
      "learning_rate": 1.9917312497490136e-07,
      "loss": 0.8061,
      "step": 1325,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.3689655172413793,
      "success_rate.epoch.env.math": 0.8293413173652695,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.6268560361523564,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4995108827520706,
      "success_rate.epoch.global": 0.5891089108910891,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9893790849673203,
      "tokens_p.mean_below_band": 2.514570951461792e-08,
      "tokens_p.mean_in_band": 0.6851806640625,
      "tokens_rate.above_band": 0.8225806451612904,
      "tokens_rate.below_band": 0.005376344086021506,
      "tokens_rate.in_band": 0.17204301075268819
    },
    {
      "epoch": 0.22107712765957446,
      "grad_norm": 137.6809814754868,
      "learning_rate": 1.991655259720039e-07,
      "loss": 0.7748,
      "step": 1330,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.36860068259385664,
      "success_rate.epoch.env.math": 0.8293413173652695,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.6265292981326465,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49944801250959486,
      "success_rate.epoch.global": 0.5886466474701769,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.48333333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 1.0004780595813205,
      "tokens_p.mean_in_band": 0.6159420289855072,
      "tokens_rate.above_band": 0.9473684210526315,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05263157894736842
    },
    {
      "epoch": 0.22190824468085107,
      "grad_norm": 322.99453023291244,
      "learning_rate": 1.9915789295499317e-07,
      "loss": 0.9512,
      "step": 1335,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.36860068259385664,
      "success_rate.epoch.env.math": 0.8293413173652695,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.6277278562259306,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5003518059179759,
      "success_rate.epoch.global": 0.5896594173163726,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963149566955363,
      "tokens_p.mean_in_band": 0.6804596656976745,
      "tokens_rate.above_band": 0.9721502590673575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027849740932642485
    },
    {
      "epoch": 0.22273936170212766,
      "grad_norm": 227.33008092202485,
      "learning_rate": 1.9915022593741594e-07,
      "loss": 0.958,
      "step": 1340,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.3728813559322034,
      "success_rate.epoch.env.math": 0.8293413173652695,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.6282789507357646,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5007910575405378,
      "success_rate.epoch.global": 0.5904255319148937,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9895334928229665,
      "tokens_p.mean_in_band": 0.6583180147058824,
      "tokens_rate.above_band": 0.9247787610619469,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0752212389380531
    },
    {
      "epoch": 0.22357047872340424,
      "grad_norm": 336.850707124167,
      "learning_rate": 1.9914252493287925e-07,
      "loss": 0.8684,
      "step": 1345,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.3728813559322034,
      "success_rate.epoch.env.math": 0.827893175074184,
      "success_rate.epoch.env.sat": 0.05102040816326531,
      "success_rate.epoch.env.science": 0.6279514996809189,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5005818232736975,
      "success_rate.epoch.global": 0.5901305057096248,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9941275167785235,
      "tokens_p.mean_in_band": 0.63125,
      "tokens_rate.above_band": 0.8097826086956522,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19021739130434784
    },
    {
      "epoch": 0.22440159574468085,
      "grad_norm": 122.73715385934305,
      "learning_rate": 1.9913478995505052e-07,
      "loss": 0.8879,
      "step": 1350,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.417910447761194,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.3728813559322034,
      "success_rate.epoch.env.math": 0.8259587020648967,
      "success_rate.epoch.env.sat": 0.050505050505050504,
      "success_rate.epoch.env.science": 0.6296060991105463,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5005095295247998,
      "success_rate.epoch.global": 0.590982940698619,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9884259259259259,
      "tokens_p.mean_in_band": 0.6495414402173914,
      "tokens_rate.above_band": 0.8756756756756757,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12432432432432433
    },
    {
      "epoch": 0.22523271276595744,
      "grad_norm": 169.04876506860631,
      "learning_rate": 1.9912702101765744e-07,
      "loss": 0.8978,
      "step": 1355,
      "success_rate.epoch.env.abd": 0.4,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.3716216216216216,
      "success_rate.epoch.env.math": 0.8264705882352941,
      "success_rate.epoch.env.sat": 0.050505050505050504,
      "success_rate.epoch.env.science": 0.629512349588347,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4998743168392339,
      "success_rate.epoch.global": 0.5906882591093118,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.39285714285714285,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9970903869407497,
      "tokens_p.mean_in_band": 0.5697021484375,
      "tokens_rate.above_band": 0.9451428571428572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054857142857142854
    },
    {
      "epoch": 0.22606382978723405,
      "grad_norm": 196.81713865618812,
      "learning_rate": 1.9911921813448794e-07,
      "loss": 0.8737,
      "step": 1360,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.3745819397993311,
      "success_rate.epoch.env.math": 0.8264705882352941,
      "success_rate.epoch.env.sat": 0.050505050505050504,
      "success_rate.epoch.env.science": 0.6306818181818182,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49797702472752303,
      "success_rate.epoch.global": 0.591367486889875,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975503177966102,
      "tokens_p.mean_in_band": 0.36855394486692017,
      "tokens_rate.above_band": 0.7821043910521955,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21789560894780446
    },
    {
      "epoch": 0.22689494680851063,
      "grad_norm": 326.3222385000378,
      "learning_rate": 1.9911138131939026e-07,
      "loss": 0.9285,
      "step": 1365,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.37333333333333335,
      "success_rate.epoch.env.math": 0.8264705882352941,
      "success_rate.epoch.env.sat": 0.05,
      "success_rate.epoch.env.science": 0.6316781898177247,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49790818060614656,
      "success_rate.epoch.global": 0.5916398713826366,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9929315476190477,
      "tokens_p.mean_in_band": 0.63037109375,
      "tokens_rate.above_band": 0.84,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16
    },
    {
      "epoch": 0.22772606382978725,
      "grad_norm": 203.63806184446858,
      "learning_rate": 1.9910351058627283e-07,
      "loss": 0.8259,
      "step": 1370,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47540983606557374,
      "success_rate.epoch.env.logic": 0.37333333333333335,
      "success_rate.epoch.env.math": 0.8269794721407625,
      "success_rate.epoch.env.sat": 0.05,
      "success_rate.epoch.env.science": 0.6314142678347935,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4979304498718317,
      "success_rate.epoch.global": 0.5917467948717948,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9813262195121951,
      "tokens_p.mean_in_band": 0.62109375,
      "tokens_rate.above_band": 0.845360824742268,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15463917525773196
    },
    {
      "epoch": 0.22855718085106383,
      "grad_norm": 253.73287973499293,
      "learning_rate": 1.9909560594910425e-07,
      "loss": 1.028,
      "step": 1375,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.37209302325581395,
      "success_rate.epoch.env.math": 0.827485380116959,
      "success_rate.epoch.env.sat": 0.04950495049504951,
      "success_rate.epoch.env.science": 0.6317103620474407,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4979165664837659,
      "success_rate.epoch.global": 0.5916167664670658,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.42000000000000004,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9930368922550696,
      "tokens_p.mean_in_band": 0.5398732311320755,
      "tokens_rate.above_band": 0.8853558295479126,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11464417045208738
    },
    {
      "epoch": 0.2293882978723404,
      "grad_norm": 153.18270203047197,
      "learning_rate": 1.990876674219133e-07,
      "loss": 0.6954,
      "step": 1380,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.37209302325581395,
      "success_rate.epoch.env.math": 0.827485380116959,
      "success_rate.epoch.env.sat": 0.04950495049504951,
      "success_rate.epoch.env.science": 0.633147113594041,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4980471802607296,
      "success_rate.epoch.global": 0.5926809864757359,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.98681640625,
      "tokens_p.mean_in_band": 0.5858028017241379,
      "tokens_rate.above_band": 0.8152866242038217,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18471337579617833
    },
    {
      "epoch": 0.23021941489361702,
      "grad_norm": 796.8927197865362,
      "learning_rate": 1.9907969501878895e-07,
      "loss": 0.7867,
      "step": 1385,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.37209302325581395,
      "success_rate.epoch.env.math": 0.8260869565217391,
      "success_rate.epoch.env.sat": 0.04950495049504951,
      "success_rate.epoch.env.science": 0.6336019838809671,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49146789619374187,
      "success_rate.epoch.global": 0.5928571428571429,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9894105450236966,
      "tokens_p.mean_in_band": 0.6906550480769231,
      "tokens_rate.above_band": 0.9154013015184381,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08459869848156182
    },
    {
      "epoch": 0.2310505319148936,
      "grad_norm": 242.0445497876273,
      "learning_rate": 1.9907168875388026e-07,
      "loss": 0.918,
      "step": 1390,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.37209302325581395,
      "success_rate.epoch.env.math": 0.8260869565217391,
      "success_rate.epoch.env.sat": 0.04807692307692308,
      "success_rate.epoch.env.science": 0.634342186534898,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49140536666972406,
      "success_rate.epoch.global": 0.5927243969948597,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.995125,
      "tokens_p.mean_in_band": 0.6332535282258065,
      "tokens_rate.above_band": 0.8012820512820513,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1987179487179487
    },
    {
      "epoch": 0.23188164893617022,
      "grad_norm": 246.44527655047452,
      "learning_rate": 1.9906364864139638e-07,
      "loss": 0.8848,
      "step": 1395,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.3741721854304636,
      "success_rate.epoch.env.math": 0.8270893371757925,
      "success_rate.epoch.env.sat": 0.05714285714285714,
      "success_rate.epoch.env.science": 0.6352433764633395,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4925916091081858,
      "success_rate.epoch.global": 0.5940086716594403,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9904069767441861,
      "tokens_p.mean_in_band": 0.7499302455357143,
      "tokens_rate.above_band": 0.9388646288209607,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0611353711790393
    },
    {
      "epoch": 0.2327127659574468,
      "grad_norm": 302.4349140001914,
      "learning_rate": 1.9905557469560656e-07,
      "loss": 0.8901,
      "step": 1400,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484375,
      "success_rate.epoch.env.logic": 0.3741721854304636,
      "success_rate.epoch.env.math": 0.8270893371757925,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.6365868631062002,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49336069271406463,
      "success_rate.epoch.global": 0.5946582875098193,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995364010989011,
      "tokens_p.mean_in_band": 0.6936773255813954,
      "tokens_rate.above_band": 0.8943488943488943,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10565110565110565
    },
    {
      "epoch": 0.23354388297872342,
      "grad_norm": 118.50638264997775,
      "learning_rate": 1.9904746693084005e-07,
      "loss": 0.9304,
      "step": 1405,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484375,
      "success_rate.epoch.env.logic": 0.375,
      "success_rate.epoch.env.math": 0.8275862068965517,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.6364749082007344,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49347094083995824,
      "success_rate.epoch.global": 0.5947533281127643,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.62,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.995365969581749,
      "tokens_p.mean_in_band": 0.5574776785714286,
      "tokens_rate.above_band": 0.9037800687285223,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09621993127147767
    },
    {
      "epoch": 0.234375,
      "grad_norm": 195.24173270759556,
      "learning_rate": 1.9903932536148616e-07,
      "loss": 0.9224,
      "step": 1410,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.3770491803278688,
      "success_rate.epoch.env.math": 0.828080229226361,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.6378048780487805,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49314559987894013,
      "success_rate.epoch.global": 0.5957861880608661,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9932491289198606,
      "tokens_p.mean_below_band": 5.502442945726216e-11,
      "tokens_p.mean_in_band": 0.7924107142857143,
      "tokens_rate.above_band": 0.9288025889967637,
      "tokens_rate.below_band": 0.003236245954692557,
      "tokens_rate.in_band": 0.06796116504854369
    },
    {
      "epoch": 0.23520611702127658,
      "grad_norm": 461.6477018176616,
      "learning_rate": 1.9903115000199417e-07,
      "loss": 0.9814,
      "step": 1415,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.3770491803278688,
      "success_rate.epoch.env.math": 0.8262108262108262,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.6381299332119005,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49300520461962977,
      "success_rate.epoch.global": 0.5960342146189735,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6904761904761905,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9893543956043956,
      "tokens_p.mean_in_band": 0.6155133928571429,
      "tokens_rate.above_band": 0.8125,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1875
    },
    {
      "epoch": 0.2360372340425532,
      "grad_norm": 198.63044446040092,
      "learning_rate": 1.9902294086687336e-07,
      "loss": 0.8357,
      "step": 1420,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.3758169934640523,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.6386198547215496,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4929826095186799,
      "success_rate.epoch.global": 0.5963551764249709,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.5238095238095238,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9985207100591716,
      "tokens_p.mean_below_band": 2.3401028670377855e-08,
      "tokens_p.mean_in_band": 0.5246448863636364,
      "tokens_rate.above_band": 0.9540322580645161,
      "tokens_rate.below_band": 0.0016129032258064516,
      "tokens_rate.in_band": 0.04435483870967742
    },
    {
      "epoch": 0.23686835106382978,
      "grad_norm": 187.49450361836384,
      "learning_rate": 1.990146979706929e-07,
      "loss": 0.9269,
      "step": 1425,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4117647058823529,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.3758169934640523,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.6395418927064497,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49306643115367077,
      "success_rate.epoch.global": 0.597061098221191,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9911317567567568,
      "tokens_p.mean_in_band": 0.5437729779411765,
      "tokens_rate.above_band": 0.8131868131868132,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18681318681318682
    },
    {
      "epoch": 0.2376994680851064,
      "grad_norm": 122.10865540389376,
      "learning_rate": 1.9900642132808195e-07,
      "loss": 0.8888,
      "step": 1430,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4057971014492754,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.37662337662337664,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.6400240384615384,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4925938596701936,
      "success_rate.epoch.global": 0.5969171483622351,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45999999999999996,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.999460586881473,
      "tokens_p.mean_in_band": 0.6142113095238095,
      "tokens_rate.above_band": 0.9324034334763949,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06759656652360516
    },
    {
      "epoch": 0.23853058510638298,
      "grad_norm": 134.6919880680028,
      "learning_rate": 1.989981109537295e-07,
      "loss": 0.8967,
      "step": 1435,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4057971014492754,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.37540453074433655,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.6395209580838324,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4924373209195803,
      "success_rate.epoch.global": 0.5964642582628747,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6904761904761904,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9968787605294825,
      "tokens_p.mean_in_band": 0.5983473557692308,
      "tokens_rate.above_band": 0.9274553571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07254464285714286
    },
    {
      "epoch": 0.2393617021276596,
      "grad_norm": 185.91445601308547,
      "learning_rate": 1.9898976686238442e-07,
      "loss": 0.9484,
      "step": 1440,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4057971014492754,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.3741935483870968,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.6388557806912991,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.492220426033608,
      "success_rate.epoch.global": 0.5957120980091883,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.16666666666666666,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9978805916305916,
      "tokens_p.mean_in_band": 0.5777064732142857,
      "tokens_rate.above_band": 0.9252336448598131,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07476635514018691
    },
    {
      "epoch": 0.24019281914893617,
      "grad_norm": 103.61172586118464,
      "learning_rate": 1.9898138906885548e-07,
      "loss": 1.0292,
      "step": 1445,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4057971014492754,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47692307692307695,
      "success_rate.epoch.env.logic": 0.3729903536977492,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.638525564803805,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49208102507207696,
      "success_rate.epoch.global": 0.5953381734810852,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9945739549839229,
      "tokens_p.mean_below_band": 4.172325134277344e-07,
      "tokens_p.mean_in_band": 0.5631696428571429,
      "tokens_rate.above_band": 0.9452887537993921,
      "tokens_rate.below_band": 0.001519756838905775,
      "tokens_rate.in_band": 0.05319148936170213
    },
    {
      "epoch": 0.24102393617021275,
      "grad_norm": 97.57096021798458,
      "learning_rate": 1.9897297758801113e-07,
      "loss": 0.8264,
      "step": 1450,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4142857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48484848484848486,
      "success_rate.epoch.env.logic": 0.3769968051118211,
      "success_rate.epoch.env.math": 0.8267045454545454,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.6384113811499703,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4939270513013572,
      "success_rate.epoch.global": 0.595963442498096,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.72,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9896324685534591,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_p.mean_in_band": 0.6689749053030303,
      "tokens_rate.above_band": 0.9492537313432836,
      "tokens_rate.below_band": 0.0014925373134328358,
      "tokens_rate.in_band": 0.049253731343283584
    },
    {
      "epoch": 0.24185505319148937,
      "grad_norm": 399.4931537788219,
      "learning_rate": 1.9896453243477974e-07,
      "loss": 0.7924,
      "step": 1455,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4142857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48484848484848486,
      "success_rate.epoch.env.logic": 0.37579617834394907,
      "success_rate.epoch.env.math": 0.8271954674220963,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.6385115180153573,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4938716360345451,
      "success_rate.epoch.global": 0.5960516324981018,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0001646903820818,
      "tokens_p.mean_in_band": 0.6193892045454545,
      "tokens_rate.above_band": 0.9324324324324325,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06756756756756757
    },
    {
      "epoch": 0.24268617021276595,
      "grad_norm": 219.41326363457327,
      "learning_rate": 1.989560536241494e-07,
      "loss": 0.8301,
      "step": 1460,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4142857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48484848484848486,
      "success_rate.epoch.env.logic": 0.37777777777777777,
      "success_rate.epoch.env.math": 0.8271954674220963,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.6397881106533255,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49416783531379943,
      "success_rate.epoch.global": 0.5971223021582733,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9897959183673469,
      "tokens_p.mean_below_band": 3.342393029015511e-11,
      "tokens_p.mean_in_band": 0.6927083333333334,
      "tokens_rate.above_band": 0.875,
      "tokens_rate.below_band": 0.004464285714285714,
      "tokens_rate.in_band": 0.12053571428571429
    },
    {
      "epoch": 0.24351728723404256,
      "grad_norm": 138.15334489710972,
      "learning_rate": 1.9894754117116785e-07,
      "loss": 0.9311,
      "step": 1465,
      "success_rate.epoch.env.abd": 0.375,
      "success_rate.epoch.env.agentgym:alfworld": 0.4084507042253521,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48484848484848486,
      "success_rate.epoch.env.logic": 0.37658227848101267,
      "success_rate.epoch.env.math": 0.8248587570621468,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.6392961876832844,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4932715496149705,
      "success_rate.epoch.global": 0.5962264150943396,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.1,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9945874183006536,
      "tokens_p.mean_in_band": 0.6085111177884616,
      "tokens_rate.above_band": 0.8547486033519553,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1452513966480447
    },
    {
      "epoch": 0.24434840425531915,
      "grad_norm": 142.00132860885753,
      "learning_rate": 1.989389950909427e-07,
      "loss": 0.8617,
      "step": 1470,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4084507042253521,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.3785488958990536,
      "success_rate.epoch.env.math": 0.8253521126760563,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.6391812865497076,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49082152268942364,
      "success_rate.epoch.global": 0.5960887551711169,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9830729166666666,
      "tokens_p.mean_below_band": 2.0211564333294518e-07,
      "tokens_p.mean_in_band": 0.06323905323134561,
      "tokens_rate.above_band": 0.15209928703459202,
      "tokens_rate.below_band": 0.002112490097702667,
      "tokens_rate.in_band": 0.8457882228677053
    },
    {
      "epoch": 0.24517952127659576,
      "grad_norm": 200.88504001102518,
      "learning_rate": 1.989304153986411e-07,
      "loss": 1.0422,
      "step": 1475,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4084507042253521,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.3805031446540881,
      "success_rate.epoch.env.math": 0.8263305322128851,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.6394399066511085,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49106614736024956,
      "success_rate.epoch.global": 0.5965504311961005,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9916516245487365,
      "tokens_p.mean_in_band": 0.6830929487179487,
      "tokens_rate.above_band": 0.8765822784810127,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12341772151898735
    },
    {
      "epoch": 0.24601063829787234,
      "grad_norm": 227.04335971840112,
      "learning_rate": 1.9892180210948992e-07,
      "loss": 0.9042,
      "step": 1480,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4084507042253521,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38317757009345793,
      "success_rate.epoch.env.math": 0.8263305322128851,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.6401162790697674,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4913707653473431,
      "success_rate.epoch.global": 0.5971599402092675,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6904761904761905,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.999033938172043,
      "tokens_p.mean_in_band": 0.5027426861702128,
      "tokens_rate.above_band": 0.9405815423514539,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05941845764854614
    },
    {
      "epoch": 0.24684175531914893,
      "grad_norm": 192.13632320292336,
      "learning_rate": 1.989131552387756e-07,
      "loss": 0.7372,
      "step": 1485,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4084507042253521,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38317757009345793,
      "success_rate.epoch.env.math": 0.8272980501392758,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.6402085747392816,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4914671120378799,
      "success_rate.epoch.global": 0.5976154992548435,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9955553519061584,
      "tokens_p.mean_in_band": 0.5665283203125,
      "tokens_rate.above_band": 0.9551820728291317,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04481792717086835
    },
    {
      "epoch": 0.24767287234042554,
      "grad_norm": 145.0123704187015,
      "learning_rate": 1.9890447480184426e-07,
      "loss": 0.8365,
      "step": 1490,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4027777777777778,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38317757009345793,
      "success_rate.epoch.env.math": 0.8282548476454293,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.640877598152425,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49109919335349106,
      "success_rate.epoch.global": 0.5982176011882658,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9985641891891892,
      "tokens_p.mean_in_band": 0.5862068965517241,
      "tokens_rate.above_band": 0.9622886866059818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0377113133940182
    },
    {
      "epoch": 0.24850398936170212,
      "grad_norm": 350.40903485092116,
      "learning_rate": 1.9889576081410156e-07,
      "loss": 0.8084,
      "step": 1495,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4027777777777778,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38317757009345793,
      "success_rate.epoch.env.math": 0.8282548476454293,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.6408045977011494,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4910925569488296,
      "success_rate.epoch.global": 0.5982969270640504,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9998094512195121,
      "tokens_p.mean_in_band": 0.5777698863636364,
      "tokens_rate.above_band": 0.9371428571428572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06285714285714286
    },
    {
      "epoch": 0.24933510638297873,
      "grad_norm": 131.929210476678,
      "learning_rate": 1.9888701329101264e-07,
      "loss": 0.8795,
      "step": 1500,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4027777777777778,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38317757009345793,
      "success_rate.epoch.env.math": 0.8264462809917356,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.6407322654462243,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4909215661389552,
      "success_rate.epoch.global": 0.5983032091479159,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9814583333333333,
      "tokens_p.mean_in_band": 0.4888630319148936,
      "tokens_rate.above_band": 0.7614213197969543,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.23857868020304568
    },
    {
      "epoch": 0.2501662234042553,
      "grad_norm": 158.09697914328336,
      "learning_rate": 1.9887823224810223e-07,
      "loss": 0.7213,
      "step": 1505,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4027777777777778,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38317757009345793,
      "success_rate.epoch.env.math": 0.8273972602739726,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.6408209806157354,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49097141104444136,
      "success_rate.epoch.global": 0.5985294117647059,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9884708737864077,
      "tokens_p.mean_in_band": 0.6474609375,
      "tokens_rate.above_band": 0.8110236220472441,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1889763779527559
    },
    {
      "epoch": 0.2509973404255319,
      "grad_norm": 138.87652901713895,
      "learning_rate": 1.9886941770095453e-07,
      "loss": 0.9555,
      "step": 1510,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.4027777777777778,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38390092879256965,
      "success_rate.epoch.env.math": 0.8278688524590164,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.640704945992041,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4910694943408469,
      "success_rate.epoch.global": 0.5986070381231672,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9948940417690417,
      "tokens_p.mean_below_band": 2.2851054382044822e-11,
      "tokens_p.mean_in_band": 0.6820790816326531,
      "tokens_rate.above_band": 0.9421296296296297,
      "tokens_rate.below_band": 0.0011574074074074073,
      "tokens_rate.in_band": 0.056712962962962965
    },
    {
      "epoch": 0.2518284574468085,
      "grad_norm": 205.53311133833452,
      "learning_rate": 1.9886056966521324e-07,
      "loss": 0.7624,
      "step": 1515,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3972602739726027,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38390092879256965,
      "success_rate.epoch.env.math": 0.8278688524590164,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.6409966024915063,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49059441731305503,
      "success_rate.epoch.global": 0.5986842105263158,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9957157258064516,
      "tokens_p.mean_in_band": 0.657421875,
      "tokens_rate.above_band": 0.9253731343283582,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07462686567164178
    },
    {
      "epoch": 0.2526595744680851,
      "grad_norm": 169.47070855145245,
      "learning_rate": 1.9885168815658142e-07,
      "loss": 0.887,
      "step": 1520,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3972602739726027,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38390092879256965,
      "success_rate.epoch.env.math": 0.8278688524590164,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.6410835214446953,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49060231903607227,
      "success_rate.epoch.global": 0.5988329686360321,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9918241279069767,
      "tokens_p.mean_in_band": 0.6893279246794872,
      "tokens_rate.above_band": 0.8151658767772512,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1848341232227488
    },
    {
      "epoch": 0.2534906914893617,
      "grad_norm": 158.18996698575802,
      "learning_rate": 1.9884277319082154e-07,
      "loss": 0.8415,
      "step": 1525,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3972602739726027,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38390092879256965,
      "success_rate.epoch.env.math": 0.8288043478260869,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.6408094435075885,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4906624478933417,
      "success_rate.epoch.global": 0.599054889131225,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9900568181818182,
      "tokens_p.mean_in_band": 0.575927734375,
      "tokens_rate.above_band": 0.8048780487804879,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1951219512195122
    },
    {
      "epoch": 0.2543218085106383,
      "grad_norm": 150.50251436930847,
      "learning_rate": 1.9883382478375555e-07,
      "loss": 0.9778,
      "step": 1530,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3972602739726027,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38390092879256965,
      "success_rate.epoch.env.math": 0.8288043478260869,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.6403361344537815,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4906194197975411,
      "success_rate.epoch.global": 0.5988393180993834,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.4444444444444444,
      "success_rate.window.env_macro_mean": 0.2222222222222222,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9850780116110305,
      "tokens_p.mean_below_band": 4.1443854570388794e-08,
      "tokens_p.mean_in_band": 0.58267578125,
      "tokens_rate.above_band": 0.7741573033707865,
      "tokens_rate.below_band": 0.0011235955056179776,
      "tokens_rate.in_band": 0.2247191011235955
    },
    {
      "epoch": 0.2551529255319149,
      "grad_norm": 386.06829289088074,
      "learning_rate": 1.9882484295126466e-07,
      "loss": 1.1215,
      "step": 1535,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3972602739726027,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38271604938271603,
      "success_rate.epoch.env.math": 0.8297297297297297,
      "success_rate.epoch.env.sat": 0.05357142857142857,
      "success_rate.epoch.env.science": 0.640581330352152,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4905742446074987,
      "success_rate.epoch.global": 0.5989150090415913,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9937065972222222,
      "tokens_p.mean_in_band": 0.6541819852941176,
      "tokens_rate.above_band": 0.8495575221238938,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1504424778761062
    },
    {
      "epoch": 0.2559840425531915,
      "grad_norm": 514.3055939231841,
      "learning_rate": 1.9881582770928938e-07,
      "loss": 1.0413,
      "step": 1540,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3972602739726027,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38153846153846155,
      "success_rate.epoch.env.math": 0.8279569892473119,
      "success_rate.epoch.env.sat": 0.05357142857142857,
      "success_rate.epoch.env.science": 0.64086859688196,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.490332148080511,
      "success_rate.epoch.global": 0.5989189189189189,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0002003205128205,
      "tokens_p.mean_in_band": 0.560791015625,
      "tokens_rate.above_band": 0.9285714285714286,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07142857142857142
    },
    {
      "epoch": 0.2568151595744681,
      "grad_norm": 360.7866453047551,
      "learning_rate": 1.988067790738296e-07,
      "loss": 0.9376,
      "step": 1545,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3918918918918919,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.3803680981595092,
      "success_rate.epoch.env.math": 0.8284182305630027,
      "success_rate.epoch.env.sat": 0.05357142857142857,
      "success_rate.epoch.env.science": 0.64,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4897006843508809,
      "success_rate.epoch.global": 0.5981308411214953,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.25,
      "success_rate.window.env_macro_mean": 0.18333333333333332,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9968513001083423,
      "tokens_p.mean_below_band": 8.754432201385498e-08,
      "tokens_p.mean_in_band": 0.5670166015625,
      "tokens_rate.above_band": 0.9495884773662552,
      "tokens_rate.below_band": 0.00102880658436214,
      "tokens_rate.in_band": 0.04938271604938271
    },
    {
      "epoch": 0.2576462765957447,
      "grad_norm": 252.78054867468754,
      "learning_rate": 1.987976970609444e-07,
      "loss": 0.7714,
      "step": 1550,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38666666666666666,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38109756097560976,
      "success_rate.epoch.env.math": 0.8293333333333334,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.6402439024390244,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4893542442928396,
      "success_rate.epoch.global": 0.5981375358166189,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9974118098159509,
      "tokens_p.mean_in_band": 0.597320556640625,
      "tokens_rate.above_band": 0.9532163742690059,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04678362573099415
    },
    {
      "epoch": 0.25847739361702127,
      "grad_norm": 211.21949877739684,
      "learning_rate": 1.9878858168675214e-07,
      "loss": 0.8431,
      "step": 1555,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38666666666666666,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47761194029850745,
      "success_rate.epoch.env.logic": 0.38109756097560976,
      "success_rate.epoch.env.math": 0.8293333333333334,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.6408839779005525,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4894124329711603,
      "success_rate.epoch.global": 0.5986418870621872,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951847484276729,
      "tokens_p.mean_in_band": 0.6688368055555556,
      "tokens_rate.above_band": 0.9464285714285714,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05357142857142857
    },
    {
      "epoch": 0.25930851063829785,
      "grad_norm": 224.0802653100846,
      "learning_rate": 1.987794329674304e-07,
      "loss": 0.8477,
      "step": 1560,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38666666666666666,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.38109756097560976,
      "success_rate.epoch.env.math": 0.8297872340425532,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.6407713498622589,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48880493912266354,
      "success_rate.epoch.global": 0.5985739750445633,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9922518298261666,
      "tokens_p.mean_below_band": 7.851497230149107e-13,
      "tokens_p.mean_in_band": 0.7527426861702128,
      "tokens_rate.above_band": 0.92003367003367,
      "tokens_rate.below_band": 0.0008417508417508417,
      "tokens_rate.in_band": 0.07912457912457913
    },
    {
      "epoch": 0.2601396276595745,
      "grad_norm": 132.72067798628524,
      "learning_rate": 1.9877025091921588e-07,
      "loss": 0.6671,
      "step": 1565,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38666666666666666,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3829787234042553,
      "success_rate.epoch.env.math": 0.8311345646437994,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.6417582417582418,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48918815593410675,
      "success_rate.epoch.global": 0.5998578535891969,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9937015503875969,
      "tokens_p.mean_in_band": 0.7973090277777778,
      "tokens_rate.above_band": 0.9052631578947369,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09473684210526316
    },
    {
      "epoch": 0.2609707446808511,
      "grad_norm": 181.16148600362826,
      "learning_rate": 1.987610355584045e-07,
      "loss": 0.8627,
      "step": 1570,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38666666666666666,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3829787234042553,
      "success_rate.epoch.env.math": 0.8315789473684211,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.6420361247947455,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48921147407735677,
      "success_rate.epoch.global": 0.600070846617074,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9932133838383839,
      "tokens_p.mean_below_band": 1.6916601452976465e-10,
      "tokens_p.mean_in_band": 0.6852678571428571,
      "tokens_rate.above_band": 0.8722466960352423,
      "tokens_rate.below_band": 0.004405286343612335,
      "tokens_rate.in_band": 0.12334801762114538
    },
    {
      "epoch": 0.26180186170212766,
      "grad_norm": 490.13935433943726,
      "learning_rate": 1.9875178690135123e-07,
      "loss": 0.8757,
      "step": 1575,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.39473684210526316,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3806646525679758,
      "success_rate.epoch.env.math": 0.8324607329842932,
      "success_rate.epoch.env.sat": 0.06086956521739131,
      "success_rate.epoch.env.science": 0.642818132168214,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49063491806478227,
      "success_rate.epoch.global": 0.6007765619484645,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9977602389078498,
      "tokens_p.mean_in_band": 0.5754123263888888,
      "tokens_rate.above_band": 0.9606557377049181,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03934426229508197
    },
    {
      "epoch": 0.26263297872340424,
      "grad_norm": 209.38634985288667,
      "learning_rate": 1.987425049644702e-07,
      "loss": 0.9739,
      "step": 1580,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.39473684210526316,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3806646525679758,
      "success_rate.epoch.env.math": 0.8328981723237598,
      "success_rate.epoch.env.sat": 0.06086956521739131,
      "success_rate.epoch.env.science": 0.6410675381263616,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4905155403645654,
      "success_rate.epoch.global": 0.5998591053187742,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9938360091743119,
      "tokens_p.mean_below_band": 5.289912223815918e-07,
      "tokens_p.mean_in_band": 0.5101316689466484,
      "tokens_rate.above_band": 0.8168873344991257,
      "tokens_rate.below_band": 0.0004996252810392206,
      "tokens_rate.in_band": 0.18261304021983513
    },
    {
      "epoch": 0.2634640957446808,
      "grad_norm": 192.27175642442387,
      "learning_rate": 1.9873318976423458e-07,
      "loss": 0.7256,
      "step": 1585,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.39473684210526316,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3806646525679758,
      "success_rate.epoch.env.math": 0.8333333333333334,
      "success_rate.epoch.env.sat": 0.06779661016949153,
      "success_rate.epoch.env.science": 0.6414991852254209,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49122407246099564,
      "success_rate.epoch.global": 0.6000702247191011,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.3333333333333333,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7222222222222223,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9947467672413793,
      "tokens_p.mean_below_band": 4.1443854570388794e-08,
      "tokens_p.mean_in_band": 0.67578125,
      "tokens_rate.above_band": 0.8405797101449275,
      "tokens_rate.below_band": 0.0036231884057971015,
      "tokens_rate.in_band": 0.15579710144927536
    },
    {
      "epoch": 0.26429521276595747,
      "grad_norm": 240.16106637909726,
      "learning_rate": 1.9872384131717652e-07,
      "loss": 0.7972,
      "step": 1590,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.39473684210526316,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3825301204819277,
      "success_rate.epoch.env.math": 0.8337662337662337,
      "success_rate.epoch.env.sat": 0.06779661016949153,
      "success_rate.epoch.env.science": 0.6413867822318526,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4914227965840215,
      "success_rate.epoch.global": 0.6003502626970227,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9920742753623188,
      "tokens_p.mean_in_band": 0.5440340909090909,
      "tokens_rate.above_band": 0.8625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1375
    },
    {
      "epoch": 0.26512632978723405,
      "grad_norm": 354.5628839874318,
      "learning_rate": 1.987144596398873e-07,
      "loss": 0.9163,
      "step": 1595,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.39473684210526316,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3825301204819277,
      "success_rate.epoch.env.math": 0.8350515463917526,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.6414686825053996,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49149529599182845,
      "success_rate.epoch.global": 0.6006980802792321,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9906684027777778,
      "tokens_p.mean_in_band": 0.5745634191176471,
      "tokens_rate.above_band": 0.8089887640449438,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19101123595505617
    },
    {
      "epoch": 0.26595744680851063,
      "grad_norm": 219.75021955239902,
      "learning_rate": 1.9870504474901703e-07,
      "loss": 0.9037,
      "step": 1600,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.37910447761194027,
      "success_rate.epoch.env.math": 0.8333333333333334,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.6413160733549083,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49054775803057643,
      "success_rate.epoch.global": 0.5997215454229029,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.3125,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9984931506849315,
      "tokens_p.mean_in_band": 0.5259588068181819,
      "tokens_rate.above_band": 0.9707446808510638,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02925531914893617
    },
    {
      "epoch": 0.2667885638297872,
      "grad_norm": 157.0005335801091,
      "learning_rate": 1.9869559666127485e-07,
      "loss": 1.0439,
      "step": 1605,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.38095238095238093,
      "success_rate.epoch.env.math": 0.8337595907928389,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.6413978494623656,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49076193411306773,
      "success_rate.epoch.global": 0.6001388406803193,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9944401840490797,
      "tokens_p.mean_in_band": 0.5199776785714286,
      "tokens_rate.above_band": 0.8232323232323232,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17676767676767677
    },
    {
      "epoch": 0.26761968085106386,
      "grad_norm": 170.02996866554872,
      "learning_rate": 1.986861153934288e-07,
      "loss": 0.8706,
      "step": 1610,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.3827893175074184,
      "success_rate.epoch.env.math": 0.8350253807106599,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6414385399892646,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4909967698321697,
      "success_rate.epoch.global": 0.6005538248528903,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.8,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6166666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9886363636363636,
      "tokens_p.mean_in_band": 0.539794921875,
      "tokens_rate.above_band": 0.8608695652173913,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1391304347826087
    },
    {
      "epoch": 0.26845079787234044,
      "grad_norm": 134.0523531361425,
      "learning_rate": 1.9867660096230582e-07,
      "loss": 0.8275,
      "step": 1615,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.3816568047337278,
      "success_rate.epoch.env.math": 0.8358585858585859,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6420150053590568,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4849295290159278,
      "success_rate.epoch.global": 0.6004140786749482,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.35,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9913850706376479,
      "tokens_p.mean_below_band": 2.868473529815674e-07,
      "tokens_p.mean_in_band": 0.5772412025043178,
      "tokens_rate.above_band": 0.8186933416692717,
      "tokens_rate.below_band": 0.00031259768677711783,
      "tokens_rate.in_band": 0.18099406064395124
    },
    {
      "epoch": 0.269281914893617,
      "grad_norm": 203.83527746812365,
      "learning_rate": 1.986670533847917e-07,
      "loss": 0.7779,
      "step": 1620,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.3816568047337278,
      "success_rate.epoch.env.math": 0.8358585858585859,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6422851041110518,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4849540834479273,
      "success_rate.epoch.global": 0.6006884681583476,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9837372448979592,
      "tokens_p.mean_in_band": 0.524387668918919,
      "tokens_rate.above_band": 0.725925925925926,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2740740740740741
    },
    {
      "epoch": 0.2701130319148936,
      "grad_norm": 239.60967974463873,
      "learning_rate": 1.9865747267783107e-07,
      "loss": 0.7279,
      "step": 1625,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.3805309734513274,
      "success_rate.epoch.env.math": 0.8358585858585859,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6427432216905901,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48489338220221256,
      "success_rate.epoch.global": 0.6008922443376802,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976105697151424,
      "tokens_p.mean_in_band": 0.5700520833333333,
      "tokens_rate.above_band": 0.9569583931133429,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043041606886657105
    },
    {
      "epoch": 0.2709441489361702,
      "grad_norm": 174.79111366182423,
      "learning_rate": 1.9864785885842727e-07,
      "loss": 1.0569,
      "step": 1630,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.3805309734513274,
      "success_rate.epoch.env.math": 0.8341708542713567,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6424403183023872,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48471241538626414,
      "success_rate.epoch.global": 0.6006849315068493,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9910714285714286,
      "tokens_p.mean_in_band": 0.5723805147058824,
      "tokens_rate.above_band": 0.8475336322869955,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15246636771300448
    },
    {
      "epoch": 0.27177526595744683,
      "grad_norm": 243.72217720344182,
      "learning_rate": 1.9863821194364254e-07,
      "loss": 0.8252,
      "step": 1635,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.37941176470588234,
      "success_rate.epoch.env.math": 0.835,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6426680783483325,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4847067514798227,
      "success_rate.epoch.global": 0.6009566108643662,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9909188034188035,
      "tokens_p.mean_below_band": 2.066371962428093e-09,
      "tokens_p.mean_in_band": 0.599609375,
      "tokens_rate.above_band": 0.924901185770751,
      "tokens_rate.below_band": 0.003952569169960474,
      "tokens_rate.in_band": 0.07114624505928854
    },
    {
      "epoch": 0.2726063829787234,
      "grad_norm": 134.0703756130931,
      "learning_rate": 1.9862853195059778e-07,
      "loss": 0.8195,
      "step": 1640,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4507042253521127,
      "success_rate.epoch.env.logic": 0.37941176470588234,
      "success_rate.epoch.env.math": 0.835,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6422163588390501,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.484080355907093,
      "success_rate.epoch.global": 0.6005453306066802,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9951331967213115,
      "tokens_p.mean_in_band": 0.5467655925829875,
      "tokens_rate.above_band": 0.8836310960888459,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11636890391115404
    },
    {
      "epoch": 0.2734375,
      "grad_norm": 150.62552403983057,
      "learning_rate": 1.9861881889647253e-07,
      "loss": 0.8853,
      "step": 1645,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.37719298245614036,
      "success_rate.epoch.env.math": 0.8329177057356608,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6421052631578947,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4843728046149097,
      "success_rate.epoch.global": 0.600067957866123,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.99298828125,
      "tokens_p.mean_below_band": 2.7008354663848877e-07,
      "tokens_p.mean_in_band": 0.6689165900735294,
      "tokens_rate.above_band": 0.9586578789694428,
      "tokens_rate.below_band": 0.0005991611743559018,
      "tokens_rate.in_band": 0.04074295985620132
    },
    {
      "epoch": 0.2742686170212766,
      "grad_norm": 145.90566336549276,
      "learning_rate": 1.986090727985052e-07,
      "loss": 0.7381,
      "step": 1650,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.37790697674418605,
      "success_rate.epoch.env.math": 0.8341584158415841,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6423319327731093,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48457111134301734,
      "success_rate.epoch.global": 0.600609756097561,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943625710227273,
      "tokens_p.mean_in_band": 0.5457899305555556,
      "tokens_rate.above_band": 0.9513513513513514,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04864864864864865
    },
    {
      "epoch": 0.27509973404255317,
      "grad_norm": 130.26235127790272,
      "learning_rate": 1.9859929367399266e-07,
      "loss": 0.7372,
      "step": 1655,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.37790697674418605,
      "success_rate.epoch.env.math": 0.8349753694581281,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6420335429769392,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4846182535085059,
      "success_rate.epoch.global": 0.6007437457741718,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9983320251177394,
      "tokens_p.mean_in_band": 0.6366257440476191,
      "tokens_rate.above_band": 0.9381443298969072,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061855670103092786
    },
    {
      "epoch": 0.2759308510638298,
      "grad_norm": 178.74040015921125,
      "learning_rate": 1.9858948154029048e-07,
      "loss": 0.8405,
      "step": 1660,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38961038961038963,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.3786127167630058,
      "success_rate.epoch.env.math": 0.8357843137254902,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6419236800836383,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4847459645442223,
      "success_rate.epoch.global": 0.6009437141894169,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.525,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9947916666666666,
      "tokens_p.mean_in_band": 0.7235863095238095,
      "tokens_rate.above_band": 0.8813559322033898,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11864406779661017
    },
    {
      "epoch": 0.2767619680851064,
      "grad_norm": 279.2343264473249,
      "learning_rate": 1.9857963641481276e-07,
      "loss": 0.8266,
      "step": 1665,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38461538461538464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.37752161383285304,
      "success_rate.epoch.env.math": 0.8357843137254902,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6416666666666667,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48416931714948325,
      "success_rate.epoch.global": 0.6004704301075269,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.20833333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9955357142857143,
      "tokens_p.mean_below_band": 6.927791673660977e-13,
      "tokens_p.mean_in_band": 0.6085464015151515,
      "tokens_rate.above_band": 0.9577114427860697,
      "tokens_rate.below_band": 0.0012437810945273632,
      "tokens_rate.in_band": 0.041044776119402986
    },
    {
      "epoch": 0.277593085106383,
      "grad_norm": 247.05071237680056,
      "learning_rate": 1.985697583150322e-07,
      "loss": 0.9812,
      "step": 1670,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38461538461538464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.37752161383285304,
      "success_rate.epoch.env.math": 0.8365853658536585,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.6427829698857737,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4843436221810537,
      "success_rate.epoch.global": 0.6015415549597856,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.999671052631579,
      "tokens_p.mean_in_band": 0.5691964285714286,
      "tokens_rate.above_band": 0.9421487603305785,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05785123966942149
    },
    {
      "epoch": 0.27842420212765956,
      "grad_norm": 119.81137439713153,
      "learning_rate": 1.9855984725848002e-07,
      "loss": 0.7041,
      "step": 1675,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38461538461538464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.3793103448275862,
      "success_rate.epoch.env.math": 0.8365853658536585,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.643190056965303,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48449315435259327,
      "success_rate.epoch.global": 0.6018054162487463,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9954144021739131,
      "tokens_p.mean_below_band": 6.07222318649292e-07,
      "tokens_p.mean_in_band": 0.5784143518518519,
      "tokens_rate.above_band": 0.8679245283018868,
      "tokens_rate.below_band": 0.0047169811320754715,
      "tokens_rate.in_band": 0.12735849056603774
    },
    {
      "epoch": 0.27925531914893614,
      "grad_norm": 84.33912835295705,
      "learning_rate": 1.9854990326274592e-07,
      "loss": 0.7299,
      "step": 1680,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38461538461538464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4657534246575342,
      "success_rate.epoch.env.logic": 0.3793103448275862,
      "success_rate.epoch.env.math": 0.8345498783454988,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.6437790397521941,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4850362076801325,
      "success_rate.epoch.global": 0.6022007335778593,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9915987780040734,
      "tokens_p.mean_in_band": 0.70654296875,
      "tokens_rate.above_band": 0.9388145315487572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06118546845124283
    },
    {
      "epoch": 0.2800864361702128,
      "grad_norm": 147.27081177833776,
      "learning_rate": 1.9853992634547806e-07,
      "loss": 0.7638,
      "step": 1685,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.38461538461538464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4657534246575342,
      "success_rate.epoch.env.logic": 0.3793103448275862,
      "success_rate.epoch.env.math": 0.8353510895883777,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.6445473251028807,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48517888918863855,
      "success_rate.epoch.global": 0.6030585106382979,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9892086330935251,
      "tokens_p.mean_in_band": 0.6942349137931034,
      "tokens_rate.above_band": 0.8273809523809523,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17261904761904762
    },
    {
      "epoch": 0.28091755319148937,
      "grad_norm": 156.10964463792166,
      "learning_rate": 1.98529916524383e-07,
      "loss": 0.8599,
      "step": 1690,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4657534246575342,
      "success_rate.epoch.env.logic": 0.37822349570200575,
      "success_rate.epoch.env.math": 0.8357487922705314,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.6437371663244353,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4857507413208097,
      "success_rate.epoch.global": 0.6026533996683251,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.48,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.996755079006772,
      "tokens_p.mean_in_band": 0.5961334745762712,
      "tokens_rate.above_band": 0.9375661375661376,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06243386243386243
    },
    {
      "epoch": 0.28174867021276595,
      "grad_norm": 254.2391005933246,
      "learning_rate": 1.9851987381722575e-07,
      "loss": 0.9832,
      "step": 1695,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4657534246575342,
      "success_rate.epoch.env.logic": 0.37822349570200575,
      "success_rate.epoch.env.math": 0.8365384615384616,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.6434426229508197,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4857957527657474,
      "success_rate.epoch.global": 0.602780536246276,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.8125,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9909274193548387,
      "tokens_p.mean_in_band": 0.6128472222222222,
      "tokens_rate.above_band": 0.8378378378378378,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16216216216216217
    },
    {
      "epoch": 0.28257978723404253,
      "grad_norm": 114.4961207204423,
      "learning_rate": 1.985097982418296e-07,
      "loss": 0.7428,
      "step": 1700,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38,
      "success_rate.epoch.env.math": 0.8369304556354916,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.6443536024527338,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48673202787596337,
      "success_rate.epoch.global": 0.6038296467481017,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9897798742138365,
      "tokens_p.mean_in_band": 0.7215401785714286,
      "tokens_rate.above_band": 0.9578313253012049,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04216867469879518
    },
    {
      "epoch": 0.2834109042553192,
      "grad_norm": 869.5856733452797,
      "learning_rate": 1.984996898160763e-07,
      "loss": 0.7348,
      "step": 1705,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38,
      "success_rate.epoch.env.math": 0.8357142857142857,
      "success_rate.epoch.env.sat": 0.06504065040650407,
      "success_rate.epoch.env.science": 0.6442405708460754,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.486513459366809,
      "success_rate.epoch.global": 0.6034879894702204,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.4222222222222222,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9924679487179487,
      "tokens_p.mean_in_band": 0.6404157366071429,
      "tokens_rate.above_band": 0.7768924302788844,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.22310756972111553
    },
    {
      "epoch": 0.28424202127659576,
      "grad_norm": 149.36512886203056,
      "learning_rate": 1.984895485579058e-07,
      "loss": 0.8248,
      "step": 1710,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3806818181818182,
      "success_rate.epoch.env.math": 0.833729216152019,
      "success_rate.epoch.env.sat": 0.06451612903225806,
      "success_rate.epoch.env.science": 0.6435845213849287,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48628765734718704,
      "success_rate.epoch.global": 0.6026272577996716,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.0,
      "success_rate.window.env_macro_mean": 0.08333333333333333,
      "success_rate.window.global": 0.125,
      "tokens_p.mean_above_band": 0.997469473007712,
      "tokens_p.mean_below_band": 1.4435499906539917e-07,
      "tokens_p.mean_in_band": 0.567311356707317,
      "tokens_rate.above_band": 0.9036004645760743,
      "tokens_rate.below_band": 0.0011614401858304297,
      "tokens_rate.in_band": 0.09523809523809523
    },
    {
      "epoch": 0.28507313829787234,
      "grad_norm": 149.31829693678955,
      "learning_rate": 1.984793744853163e-07,
      "loss": 0.9204,
      "step": 1715,
      "success_rate.epoch.env.abd": 0.35294117647058826,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3806818181818182,
      "success_rate.epoch.env.math": 0.8349056603773585,
      "success_rate.epoch.env.sat": 0.06451612903225806,
      "success_rate.epoch.env.science": 0.6434738445911631,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48638454529551195,
      "success_rate.epoch.global": 0.6030134294136914,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.8571428571428572,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9912280701754386,
      "tokens_p.mean_in_band": 0.689453125,
      "tokens_rate.above_band": 0.8028169014084507,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19718309859154928
    },
    {
      "epoch": 0.2859042553191489,
      "grad_norm": 124.19771709447896,
      "learning_rate": 1.9846916761636438e-07,
      "loss": 0.9969,
      "step": 1720,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38243626062322944,
      "success_rate.epoch.env.math": 0.8349056603773585,
      "success_rate.epoch.env.sat": 0.06451612903225806,
      "success_rate.epoch.env.science": 0.6433637284701115,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48475149831215786,
      "success_rate.epoch.global": 0.6029411764705882,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9910919540229886,
      "tokens_p.mean_in_band": 0.5250592912946429,
      "tokens_rate.above_band": 0.8534990189666448,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14650098103335513
    },
    {
      "epoch": 0.2867353723404255,
      "grad_norm": 137.96552426288633,
      "learning_rate": 1.9845892796916466e-07,
      "loss": 0.929,
      "step": 1725,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38243626062322944,
      "success_rate.epoch.env.math": 0.8356807511737089,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.6439049064238745,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4847780622403323,
      "success_rate.epoch.global": 0.6031953048581676,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9943612258953168,
      "tokens_p.mean_in_band": 0.6978889627659575,
      "tokens_rate.above_band": 0.9391979301423027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06080206985769728
    },
    {
      "epoch": 0.28756648936170215,
      "grad_norm": 164.31520923456802,
      "learning_rate": 1.9844865556189002e-07,
      "loss": 0.8119,
      "step": 1730,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38309859154929576,
      "success_rate.epoch.env.math": 0.8356807511737089,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.6439393939393939,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4848414093713856,
      "success_rate.epoch.global": 0.6031901041666666,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.6444444444444445,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9974747474747475,
      "tokens_p.mean_in_band": 0.6173295454545454,
      "tokens_rate.above_band": 0.9557522123893806,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04424778761061947
    },
    {
      "epoch": 0.28839760638297873,
      "grad_norm": 150.14807994498668,
      "learning_rate": 1.9843835041277148e-07,
      "loss": 0.7307,
      "step": 1735,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38309859154929576,
      "success_rate.epoch.env.math": 0.8360655737704918,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.6445115810674723,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4849284102554638,
      "success_rate.epoch.global": 0.6037674569665475,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9951400501672241,
      "tokens_p.mean_in_band": 0.6222098214285714,
      "tokens_rate.above_band": 0.9660743134087237,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033925686591276254
    },
    {
      "epoch": 0.2892287234042553,
      "grad_norm": 243.48793304606505,
      "learning_rate": 1.9842801254009814e-07,
      "loss": 0.8648,
      "step": 1740,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38375350140056025,
      "success_rate.epoch.env.math": 0.8364485981308412,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.6445783132530121,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4850288344733869,
      "success_rate.epoch.global": 0.6039507772020726,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9951238127544098,
      "tokens_p.mean_in_band": 0.5689453125,
      "tokens_rate.above_band": 0.9485199485199485,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05148005148005148
    },
    {
      "epoch": 0.2900598404255319,
      "grad_norm": 196.45183014909537,
      "learning_rate": 1.9841764196221722e-07,
      "loss": 0.6999,
      "step": 1745,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38375350140056025,
      "success_rate.epoch.env.math": 0.8368298368298368,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.6446115288220552,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48506651213411767,
      "success_rate.epoch.global": 0.6041397153945667,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9866803278688525,
      "tokens_p.mean_in_band": 0.5878276209677419,
      "tokens_rate.above_band": 0.7973856209150327,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.20261437908496732
    },
    {
      "epoch": 0.2908909574468085,
      "grad_norm": 311.443971821392,
      "learning_rate": 1.9840723869753396e-07,
      "loss": 0.9836,
      "step": 1750,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38375350140056025,
      "success_rate.epoch.env.math": 0.8375870069605569,
      "success_rate.epoch.env.sat": 0.06299212598425197,
      "success_rate.epoch.env.science": 0.645,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48512521247964985,
      "success_rate.epoch.global": 0.604516129032258,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9888535031847133,
      "tokens_p.mean_in_band": 0.6088541666666667,
      "tokens_rate.above_band": 0.839572192513369,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16042780748663102
    },
    {
      "epoch": 0.2917220744680851,
      "grad_norm": 134.917482294454,
      "learning_rate": 1.9839680276451155e-07,
      "loss": 0.7225,
      "step": 1755,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38440111420612816,
      "success_rate.epoch.env.math": 0.8379629629629629,
      "success_rate.epoch.env.sat": 0.06299212598425197,
      "success_rate.epoch.env.science": 0.6443890274314215,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4851627212286857,
      "success_rate.epoch.global": 0.6042471042471043,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6904761904761904,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9990768094534712,
      "tokens_p.mean_in_band": 0.459375,
      "tokens_rate.above_band": 0.9312242090784044,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0687757909215956
    },
    {
      "epoch": 0.2925531914893617,
      "grad_norm": 133.6640868994498,
      "learning_rate": 1.983863341816712e-07,
      "loss": 0.7707,
      "step": 1760,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3861111111111111,
      "success_rate.epoch.env.math": 0.8379629629629629,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.6437810945273632,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48521817013929236,
      "success_rate.epoch.global": 0.603852327447833,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9927685950413223,
      "tokens_p.mean_in_band": 0.6369850852272727,
      "tokens_rate.above_band": 0.8461538461538461,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15384615384615385
    },
    {
      "epoch": 0.2933843085106383,
      "grad_norm": 169.19694821539974,
      "learning_rate": 1.9837583296759218e-07,
      "loss": 0.8373,
      "step": 1765,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3878116343490305,
      "success_rate.epoch.env.math": 0.836405529953917,
      "success_rate.epoch.env.sat": 0.06201550387596899,
      "success_rate.epoch.env.science": 0.6439920556107249,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4776305539442806,
      "success_rate.epoch.global": 0.6037131882202305,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45999999999999996,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9961905991735537,
      "tokens_p.mean_in_band": 0.6551192434210527,
      "tokens_rate.above_band": 0.9272030651340997,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07279693486590039
    },
    {
      "epoch": 0.2942154255319149,
      "grad_norm": 175.58074786393445,
      "learning_rate": 1.9836529914091152e-07,
      "loss": 1.0126,
      "step": 1770,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.3924050632911392,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3878116343490305,
      "success_rate.epoch.env.math": 0.8375286041189931,
      "success_rate.epoch.env.sat": 0.06201550387596899,
      "success_rate.epoch.env.science": 0.6450495049504951,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4778287833538121,
      "success_rate.epoch.global": 0.6048515799553144,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9898298816568047,
      "tokens_p.mean_in_band": 0.75375,
      "tokens_rate.above_band": 0.8711340206185567,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12886597938144329
    },
    {
      "epoch": 0.2950465425531915,
      "grad_norm": 225.79861534910873,
      "learning_rate": 1.9835473272032416e-07,
      "loss": 0.8841,
      "step": 1775,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.38950276243093923,
      "success_rate.epoch.env.math": 0.8390022675736961,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.6454005934718101,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.47879549012011036,
      "success_rate.epoch.global": 0.6056651814131127,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954427083333334,
      "tokens_p.mean_in_band": 0.69140625,
      "tokens_rate.above_band": 0.9411764705882353,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.058823529411764705
    },
    {
      "epoch": 0.2958776595744681,
      "grad_norm": 396.33425728135785,
      "learning_rate": 1.9834413372458295e-07,
      "loss": 1.061,
      "step": 1780,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3917808219178082,
      "success_rate.epoch.env.math": 0.8390022675736961,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.6451135241855873,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.47897648922926,
      "success_rate.epoch.global": 0.6055890758971102,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.38888888888888884,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9973275370581528,
      "tokens_p.mean_in_band": 0.5534939236111112,
      "tokens_rate.above_band": 0.9605695509309967,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03943044906900329
    },
    {
      "epoch": 0.2967087765957447,
      "grad_norm": 181.6838301079621,
      "learning_rate": 1.9833350217249847e-07,
      "loss": 0.8669,
      "step": 1785,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.39402173913043476,
      "success_rate.epoch.env.math": 0.8390022675736961,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.645320197044335,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4791989974175667,
      "success_rate.epoch.global": 0.605830164765526,
      "success_rate.window.env.logic": 0.4,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9985522598870057,
      "tokens_p.mean_in_band": 0.5005008012820513,
      "tokens_rate.above_band": 0.9577922077922078,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04220779220779221
    },
    {
      "epoch": 0.29753989361702127,
      "grad_norm": 144.47263518111075,
      "learning_rate": 1.9832283808293913e-07,
      "loss": 0.8329,
      "step": 1790,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.39402173913043476,
      "success_rate.epoch.env.math": 0.8393665158371041,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.6463654223968566,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4793271313826512,
      "success_rate.epoch.global": 0.6067024976288334,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9906352908891328,
      "tokens_p.mean_in_band": 0.6921027131782945,
      "tokens_rate.above_band": 0.8759615384615385,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12403846153846154
    },
    {
      "epoch": 0.29837101063829785,
      "grad_norm": 258.9570646023226,
      "learning_rate": 1.983121414748311e-07,
      "loss": 0.7325,
      "step": 1795,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.39402173913043476,
      "success_rate.epoch.env.math": 0.8400900900900901,
      "success_rate.epoch.env.sat": 0.061068702290076333,
      "success_rate.epoch.env.science": 0.6474045053868757,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.47944466756398024,
      "success_rate.epoch.global": 0.6075031525851198,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963565022421524,
      "tokens_p.mean_below_band": 4.843059286940843e-11,
      "tokens_p.mean_in_band": 0.6871995192307693,
      "tokens_rate.above_band": 0.892,
      "tokens_rate.below_band": 0.004,
      "tokens_rate.in_band": 0.104
    },
    {
      "epoch": 0.2992021276595745,
      "grad_norm": 117.93606495434574,
      "learning_rate": 1.983014123671582e-07,
      "loss": 0.737,
      "step": 1800,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.39295392953929537,
      "success_rate.epoch.env.math": 0.8400900900900901,
      "success_rate.epoch.env.sat": 0.06818181818181818,
      "success_rate.epoch.env.science": 0.6484375,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4800881494652282,
      "success_rate.epoch.global": 0.6081761006289308,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9971509971509972,
      "tokens_p.mean_in_band": 0.5111083984375,
      "tokens_rate.above_band": 0.9564032697547684,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043596730245231606
    },
    {
      "epoch": 0.3000332446808511,
      "grad_norm": 165.55263056487317,
      "learning_rate": 1.9829065077896203e-07,
      "loss": 0.8661,
      "step": 1805,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.39622641509433965,
      "success_rate.epoch.env.math": 0.8400900900900901,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.6481481481481481,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4809452568464115,
      "success_rate.epoch.global": 0.6082183186951067,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.725,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9952512254901961,
      "tokens_p.mean_in_band": 0.6074683779761905,
      "tokens_rate.above_band": 0.9066666666666666,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09333333333333334
    },
    {
      "epoch": 0.30086436170212766,
      "grad_norm": 168.1160135624176,
      "learning_rate": 1.9827985672934172e-07,
      "loss": 0.9137,
      "step": 1810,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.3951612903225806,
      "success_rate.epoch.env.math": 0.8400900900900901,
      "success_rate.epoch.env.sat": 0.07407407407407407,
      "success_rate.epoch.env.science": 0.6488326848249028,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4815338048204874,
      "success_rate.epoch.global": 0.6084507042253521,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.999292071197411,
      "tokens_p.mean_in_band": 0.598876953125,
      "tokens_rate.above_band": 0.9507692307692308,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04923076923076923
    },
    {
      "epoch": 0.30169547872340424,
      "grad_norm": 267.5530777460492,
      "learning_rate": 1.9826903023745408e-07,
      "loss": 0.9431,
      "step": 1815,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.3983957219251337,
      "success_rate.epoch.env.math": 0.8400900900900901,
      "success_rate.epoch.env.sat": 0.07407407407407407,
      "success_rate.epoch.env.science": 0.6482290150412421,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48119966441254064,
      "success_rate.epoch.global": 0.608179831408055,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.998049303655807,
      "tokens_p.mean_below_band": 2.477318048477173e-07,
      "tokens_p.mean_in_band": 0.468992761299435,
      "tokens_rate.above_band": 0.9569252736792003,
      "tokens_rate.below_band": 0.0009519276534983341,
      "tokens_rate.in_band": 0.04212279866730129
    },
    {
      "epoch": 0.3025265957446808,
      "grad_norm": 138.39670036359678,
      "learning_rate": 1.9825817132251345e-07,
      "loss": 0.8651,
      "step": 1820,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4,
      "success_rate.epoch.env.math": 0.8404494382022472,
      "success_rate.epoch.env.sat": 0.07407407407407407,
      "success_rate.epoch.env.science": 0.6484526112185687,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48139850280929974,
      "success_rate.epoch.global": 0.6086550435865504,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.7380952380952381,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9938599706744868,
      "tokens_p.mean_in_band": 0.55126953125,
      "tokens_rate.above_band": 0.9393939393939394,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06060606060606061
    },
    {
      "epoch": 0.30335771276595747,
      "grad_norm": 168.03979056395144,
      "learning_rate": 1.982472800037918e-07,
      "loss": 0.9215,
      "step": 1825,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.39893617021276595,
      "success_rate.epoch.env.math": 0.8404494382022472,
      "success_rate.epoch.env.sat": 0.08029197080291971,
      "success_rate.epoch.env.science": 0.6493005306319344,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48194413793247953,
      "success_rate.epoch.global": 0.6090062111801242,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9979910714285715,
      "tokens_p.mean_in_band": 0.52734375,
      "tokens_rate.above_band": 0.9186351706036745,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08136482939632546
    },
    {
      "epoch": 0.30418882978723405,
      "grad_norm": 211.80256465400694,
      "learning_rate": 1.982363563006185e-07,
      "loss": 0.8253,
      "step": 1830,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.40105540897097625,
      "success_rate.epoch.env.math": 0.8404494382022472,
      "success_rate.epoch.env.sat": 0.07971014492753623,
      "success_rate.epoch.env.science": 0.6490129995185363,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48205776354788216,
      "success_rate.epoch.global": 0.6087360594795539,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.38888888888888884,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9948738170347003,
      "tokens_p.mean_in_band": 0.6034740691489362,
      "tokens_rate.above_band": 0.8708791208791209,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12912087912087913
    },
    {
      "epoch": 0.30501994680851063,
      "grad_norm": 136.09499319463293,
      "learning_rate": 1.982254002323805e-07,
      "loss": 0.6994,
      "step": 1835,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.40105540897097625,
      "success_rate.epoch.env.math": 0.8408071748878924,
      "success_rate.epoch.env.sat": 0.07971014492753623,
      "success_rate.epoch.env.science": 0.6487265737626141,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48206424635967515,
      "success_rate.epoch.global": 0.6087225487163626,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9996576682316118,
      "tokens_p.mean_in_band": 0.5874763257575758,
      "tokens_rate.above_band": 0.9508928571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049107142857142856
    },
    {
      "epoch": 0.3058510638297872,
      "grad_norm": 173.3700097091341,
      "learning_rate": 1.982144118185221e-07,
      "loss": 0.7882,
      "step": 1840,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4026315789473684,
      "success_rate.epoch.env.math": 0.8408071748878924,
      "success_rate.epoch.env.sat": 0.07857142857142857,
      "success_rate.epoch.env.science": 0.6489208633093525,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4821216775566772,
      "success_rate.epoch.global": 0.608641975308642,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.4444444444444445,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9930227987421384,
      "tokens_p.mean_in_band": 0.6687360491071429,
      "tokens_rate.above_band": 0.8502673796791443,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1497326203208556
    },
    {
      "epoch": 0.30668218085106386,
      "grad_norm": 261.1019482562245,
      "learning_rate": 1.9820339107854505e-07,
      "loss": 0.8301,
      "step": 1845,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.40575916230366493,
      "success_rate.epoch.env.math": 0.8408071748878924,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.649593106749641,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48236651273463643,
      "success_rate.epoch.global": 0.6089901477832512,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9955218068535826,
      "tokens_p.mean_in_band": 0.5590277777777778,
      "tokens_rate.above_band": 0.856,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.144
    },
    {
      "epoch": 0.30751329787234044,
      "grad_norm": 383.5429073159267,
      "learning_rate": 1.9819233803200846e-07,
      "loss": 0.9382,
      "step": 1850,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.40575916230366493,
      "success_rate.epoch.env.math": 0.8408071748878924,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6494992846924177,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.482357983456707,
      "success_rate.epoch.global": 0.609029484029484,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9884615384615385,
      "tokens_p.mean_in_band": 0.5446428571428571,
      "tokens_rate.above_band": 0.8227848101265823,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17721518987341772
    },
    {
      "epoch": 0.308344414893617,
      "grad_norm": 171.78647100768598,
      "learning_rate": 1.9818125269852878e-07,
      "loss": 0.7666,
      "step": 1855,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4024390243902439,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4073107049608355,
      "success_rate.epoch.env.math": 0.8411633109619687,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6496906235126131,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48209713205073235,
      "success_rate.epoch.global": 0.6092552865461232,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9934623430962343,
      "tokens_p.mean_in_band": 0.7020596590909091,
      "tokens_rate.above_band": 0.9157088122605364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0842911877394636
    },
    {
      "epoch": 0.3091755319148936,
      "grad_norm": 117.46381511606609,
      "learning_rate": 1.9817013509777976e-07,
      "loss": 0.6933,
      "step": 1860,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.40963855421686746,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.40625,
      "success_rate.epoch.env.math": 0.8411633109619687,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6503795066413662,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48271783277750885,
      "success_rate.epoch.global": 0.6097188264058679,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0006325910931173,
      "tokens_p.mean_in_band": 0.58859375,
      "tokens_rate.above_band": 0.9367888748419722,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0632111251580278
    },
    {
      "epoch": 0.3100066489361702,
      "grad_norm": 237.6914534637881,
      "learning_rate": 1.9815898524949244e-07,
      "loss": 0.874,
      "step": 1865,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.40963855421686746,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.40625,
      "success_rate.epoch.env.math": 0.84,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6502602934216754,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4826012396700852,
      "success_rate.epoch.global": 0.6097560975609756,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9833333333333333,
      "tokens_p.mean_in_band": 0.6727764423076923,
      "tokens_rate.above_band": 0.8015267175572519,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1984732824427481
    },
    {
      "epoch": 0.31083776595744683,
      "grad_norm": 264.4057550452638,
      "learning_rate": 1.9814780317345504e-07,
      "loss": 0.8081,
      "step": 1870,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.40963855421686746,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4051948051948052,
      "success_rate.epoch.env.math": 0.84,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6507786691835772,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4825524379388767,
      "success_rate.epoch.global": 0.609978703985397,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995583717357911,
      "tokens_p.mean_in_band": 0.6124674479166666,
      "tokens_rate.above_band": 0.9313304721030042,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06866952789699571
    },
    {
      "epoch": 0.3116688829787234,
      "grad_norm": 153.1849065261085,
      "learning_rate": 1.9813658888951304e-07,
      "loss": 0.7847,
      "step": 1875,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4235294117647059,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4051948051948052,
      "success_rate.epoch.env.math": 0.8403547671840355,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6516007532956686,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4839222296519645,
      "success_rate.epoch.global": 0.6109256449165402,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9980283911671924,
      "tokens_p.mean_in_band": 0.6779399671052632,
      "tokens_rate.above_band": 0.9804123711340206,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01958762886597938
    },
    {
      "epoch": 0.3125,
      "grad_norm": 130.037019408199,
      "learning_rate": 1.9812534241756898e-07,
      "loss": 0.7954,
      "step": 1880,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4235294117647059,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4051948051948052,
      "success_rate.epoch.env.math": 0.8407079646017699,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.651949271958666,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4839860220229401,
      "success_rate.epoch.global": 0.6113299000302939,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9950208649468892,
      "tokens_p.mean_in_band": 0.553203125,
      "tokens_rate.above_band": 0.9294781382228491,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07052186177715092
    },
    {
      "epoch": 0.3133311170212766,
      "grad_norm": 214.9477828823179,
      "learning_rate": 1.981140637775827e-07,
      "loss": 0.8792,
      "step": 1885,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4235294117647059,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4666666666666667,
      "success_rate.epoch.env.logic": 0.4051948051948052,
      "success_rate.epoch.env.math": 0.8410596026490066,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6515222482435598,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4839791687804065,
      "success_rate.epoch.global": 0.6112454655380894,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9889112903225806,
      "tokens_p.mean_in_band": 0.5125558035714286,
      "tokens_rate.above_band": 0.8157894736842105,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18421052631578946
    },
    {
      "epoch": 0.31416223404255317,
      "grad_norm": 185.33333393201696,
      "learning_rate": 1.9810275298957092e-07,
      "loss": 0.9321,
      "step": 1890,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4235294117647059,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4605263157894737,
      "success_rate.epoch.env.logic": 0.40414507772020725,
      "success_rate.epoch.env.math": 0.8417582417582418,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.6510757717492984,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4833484491679686,
      "success_rate.epoch.global": 0.6108597285067874,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9985274869109948,
      "tokens_p.mean_in_band": 0.5329296875,
      "tokens_rate.above_band": 0.9683143219264893,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.031685678073510776
    },
    {
      "epoch": 0.3149933510638298,
      "grad_norm": 139.5118804210538,
      "learning_rate": 1.9809141007360754e-07,
      "loss": 0.7876,
      "step": 1895,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4235294117647059,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4605263157894737,
      "success_rate.epoch.env.logic": 0.40414507772020725,
      "success_rate.epoch.env.math": 0.8427947598253275,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.65142323845077,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4834742659651102,
      "success_rate.epoch.global": 0.6114956364730665,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9864665354330708,
      "tokens_p.mean_in_band": 0.6157670454545454,
      "tokens_rate.above_band": 0.9202898550724637,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07971014492753623
    },
    {
      "epoch": 0.3158244680851064,
      "grad_norm": 207.0388021716609,
      "learning_rate": 1.9808003504982352e-07,
      "loss": 0.8993,
      "step": 1900,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4186046511627907,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4605263157894737,
      "success_rate.epoch.env.logic": 0.40414507772020725,
      "success_rate.epoch.env.math": 0.8431372549019608,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.6520726595249184,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48306748812325107,
      "success_rate.epoch.global": 0.6117117117117117,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9947183098591549,
      "tokens_p.mean_in_band": 0.5027817234848485,
      "tokens_rate.above_band": 0.9281045751633987,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0718954248366013
    },
    {
      "epoch": 0.316655585106383,
      "grad_norm": 592.2308993935935,
      "learning_rate": 1.9806862793840667e-07,
      "loss": 0.7883,
      "step": 1905,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4186046511627907,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.375,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.40359897172236503,
      "success_rate.epoch.env.math": 0.841648590021692,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.652396463471382,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4823682310163722,
      "success_rate.epoch.global": 0.6114439784301977,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.36666666666666664,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.99769079345851,
      "tokens_p.mean_below_band": 1.9190338207408786e-10,
      "tokens_p.mean_in_band": 0.653076171875,
      "tokens_rate.above_band": 0.9711764705882353,
      "tokens_rate.below_band": 0.000588235294117647,
      "tokens_rate.in_band": 0.02823529411764706
    },
    {
      "epoch": 0.31748670212765956,
      "grad_norm": 131.64471110232353,
      "learning_rate": 1.9805718875960181e-07,
      "loss": 0.6776,
      "step": 1910,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4186046511627907,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.40359897172236503,
      "success_rate.epoch.env.math": 0.8423326133909287,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.6516488620529494,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.47921030031429446,
      "success_rate.epoch.global": 0.6111775254034668,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9975679916317992,
      "tokens_p.mean_below_band": 1.1874362826347351e-08,
      "tokens_p.mean_in_band": 0.534545216480447,
      "tokens_rate.above_band": 0.8690909090909091,
      "tokens_rate.below_band": 0.0007272727272727272,
      "tokens_rate.in_band": 0.13018181818181818
    },
    {
      "epoch": 0.31831781914893614,
      "grad_norm": 112.29823107983792,
      "learning_rate": 1.9804571753371078e-07,
      "loss": 0.9103,
      "step": 1915,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.42528735632183906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.4025641025641026,
      "success_rate.epoch.env.math": 0.843010752688172,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6516697588126159,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4803700392659265,
      "success_rate.epoch.global": 0.6115086463923673,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.72,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982130984042553,
      "tokens_p.mean_below_band": 5.3085386753082275e-08,
      "tokens_p.mean_in_band": 0.5998186383928571,
      "tokens_rate.above_band": 0.9628681177976952,
      "tokens_rate.below_band": 0.0012804097311139564,
      "tokens_rate.in_band": 0.03585147247119078
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 617.4480033444044,
      "learning_rate": 1.9803421428109209e-07,
      "loss": 0.7003,
      "step": 1920,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42528735632183906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.4040920716112532,
      "success_rate.epoch.env.math": 0.8436830835117773,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6524757056918093,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4838331270884897,
      "success_rate.epoch.global": 0.6125483199524234,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9895833333333334,
      "tokens_p.mean_in_band": 0.6716056034482759,
      "tokens_rate.above_band": 0.903010033444816,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09698996655518395
    },
    {
      "epoch": 0.31998005319148937,
      "grad_norm": 175.8314906467214,
      "learning_rate": 1.9802267902216124e-07,
      "loss": 0.7462,
      "step": 1925,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42045454545454547,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.40561224489795916,
      "success_rate.epoch.env.math": 0.8443496801705757,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6520332717190388,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4835523566435296,
      "success_rate.epoch.global": 0.6124629080118694,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.65,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9935810810810811,
      "tokens_p.mean_in_band": 0.7121744791666667,
      "tokens_rate.above_band": 0.925,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.075
    },
    {
      "epoch": 0.32081117021276595,
      "grad_norm": 174.71926594610449,
      "learning_rate": 1.9801111177739047e-07,
      "loss": 0.9158,
      "step": 1930,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42045454545454547,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46835443037974683,
      "success_rate.epoch.env.logic": 0.40458015267175573,
      "success_rate.epoch.env.math": 0.8446808510638298,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.65283540802213,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4841811915354776,
      "success_rate.epoch.global": 0.613084665482534,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.993834279630944,
      "tokens_p.mean_in_band": 0.6550399116847826,
      "tokens_rate.above_band": 0.8844946641556811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1155053358443189
    },
    {
      "epoch": 0.32164228723404253,
      "grad_norm": 223.9156515493342,
      "learning_rate": 1.9799951256730882e-07,
      "loss": 0.8614,
      "step": 1935,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42045454545454547,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.40458015267175573,
      "success_rate.epoch.env.math": 0.8453389830508474,
      "success_rate.epoch.env.sat": 0.08275862068965517,
      "success_rate.epoch.env.science": 0.6531738730450782,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4848236873524358,
      "success_rate.epoch.global": 0.6135222911130794,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.76,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9953931203931204,
      "tokens_p.mean_in_band": 0.6908967391304348,
      "tokens_rate.above_band": 0.9465116279069767,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053488372093023255
    },
    {
      "epoch": 0.3224734042553192,
      "grad_norm": 218.20803178592098,
      "learning_rate": 1.9798788141250203e-07,
      "loss": 0.9407,
      "step": 1940,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42045454545454547,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.4035532994923858,
      "success_rate.epoch.env.math": 0.8456659619450317,
      "success_rate.epoch.env.sat": 0.0821917808219178,
      "success_rate.epoch.env.science": 0.6531924666972898,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4847102218523712,
      "success_rate.epoch.global": 0.6133215443560271,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.2333333333333333,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9949742268041237,
      "tokens_p.mean_in_band": 0.6322544642857143,
      "tokens_rate.above_band": 0.885036496350365,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11496350364963503
    },
    {
      "epoch": 0.32330452127659576,
      "grad_norm": 154.42341866073517,
      "learning_rate": 1.9797621833361263e-07,
      "loss": 0.9645,
      "step": 1945,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42045454545454547,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.4035532994923858,
      "success_rate.epoch.env.math": 0.8456659619450317,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.6535288725939505,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48468997441018646,
      "success_rate.epoch.global": 0.6134157105030892,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.39285714285714285,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9960365853658537,
      "tokens_p.mean_in_band": 0.3281324546755725,
      "tokens_rate.above_band": 0.701254275940707,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.29874572405929306
    },
    {
      "epoch": 0.32413563829787234,
      "grad_norm": 176.34030738672908,
      "learning_rate": 1.979645233513396e-07,
      "loss": 0.7489,
      "step": 1950,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42045454545454547,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.4050632911392405,
      "success_rate.epoch.env.math": 0.8459915611814346,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.654337899543379,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48493039421315787,
      "success_rate.epoch.global": 0.6142563801701378,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9910402097902098,
      "tokens_p.mean_in_band": 0.5890625,
      "tokens_rate.above_band": 0.8773006134969326,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12269938650306748
    },
    {
      "epoch": 0.3249667553191489,
      "grad_norm": 126.23954534188171,
      "learning_rate": 1.9795279648643874e-07,
      "loss": 0.809,
      "step": 1955,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.40404040404040403,
      "success_rate.epoch.env.math": 0.8459915611814346,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.6548269581056466,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48547384131713217,
      "success_rate.epoch.global": 0.6145741878841089,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9994544887780549,
      "tokens_p.mean_in_band": 0.6108141447368421,
      "tokens_rate.above_band": 0.9547619047619048,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04523809523809524
    },
    {
      "epoch": 0.3257978723404255,
      "grad_norm": 180.16353002658522,
      "learning_rate": 1.9794103775972237e-07,
      "loss": 0.7907,
      "step": 1960,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.40554156171284633,
      "success_rate.epoch.env.math": 0.8459915611814346,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.6548592188919165,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4856132429951969,
      "success_rate.epoch.global": 0.6147780373831776,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995677537250492,
      "tokens_p.mean_in_band": 0.5518613565488566,
      "tokens_rate.above_band": 0.8808816245666171,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11911837543338286
    },
    {
      "epoch": 0.32662898936170215,
      "grad_norm": 164.9703329127884,
      "learning_rate": 1.9792924719205932e-07,
      "loss": 0.7462,
      "step": 1965,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.40554156171284633,
      "success_rate.epoch.env.math": 0.8466386554621849,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.655328798185941,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48627886648168667,
      "success_rate.epoch.global": 0.6154518950437318,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9901620370370371,
      "tokens_p.mean_below_band": 2.648448571562767e-09,
      "tokens_p.mean_in_band": 0.7585227272727273,
      "tokens_rate.above_band": 0.9310344827586207,
      "tokens_rate.below_band": 0.005747126436781609,
      "tokens_rate.in_band": 0.06321839080459771
    },
    {
      "epoch": 0.32746010638297873,
      "grad_norm": 461.95040314697394,
      "learning_rate": 1.9791742480437498e-07,
      "loss": 0.5795,
      "step": 1970,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.4045226130653266,
      "success_rate.epoch.env.math": 0.8466386554621849,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.6561085972850679,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48625712561365103,
      "success_rate.epoch.global": 0.6158323632130385,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9953342013888888,
      "tokens_p.mean_in_band": 0.6043113425925926,
      "tokens_rate.above_band": 0.9552238805970149,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04477611940298507
    },
    {
      "epoch": 0.3282912234042553,
      "grad_norm": 98.41478633184958,
      "learning_rate": 1.9790557061765116e-07,
      "loss": 0.8591,
      "step": 1975,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.40601503759398494,
      "success_rate.epoch.env.math": 0.8466386554621849,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.6565884476534296,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4864364233315619,
      "success_rate.epoch.global": 0.6163229741504502,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9995124113475178,
      "tokens_p.mean_in_band": 0.6399305555555556,
      "tokens_rate.above_band": 0.94,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06
    },
    {
      "epoch": 0.3291223404255319,
      "grad_norm": 155.1278879482167,
      "learning_rate": 1.9789368465292617e-07,
      "loss": 0.8568,
      "step": 1980,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.475,
      "success_rate.epoch.env.logic": 0.40601503759398494,
      "success_rate.epoch.env.math": 0.8469601677148847,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.656770130454341,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48648216833643565,
      "success_rate.epoch.global": 0.6166328600405679,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.6666666666666666,
      "tokens_p.mean_above_band": 0.9971676737160121,
      "tokens_p.mean_in_band": 0.6021075581395349,
      "tokens_rate.above_band": 0.9390070921985816,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06099290780141844
    },
    {
      "epoch": 0.3299534574468085,
      "grad_norm": 129.8109960608089,
      "learning_rate": 1.978817669312947e-07,
      "loss": 0.72,
      "step": 1985,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48148148148148145,
      "success_rate.epoch.env.logic": 0.40601503759398494,
      "success_rate.epoch.env.math": 0.8472803347280334,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.6567834681042228,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4871017125313913,
      "success_rate.epoch.global": 0.6168981481481481,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.99528125,
      "tokens_p.mean_in_band": 0.5909288194444444,
      "tokens_rate.above_band": 0.9652509652509652,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03474903474903475
    },
    {
      "epoch": 0.3307845744680851,
      "grad_norm": 104.26200129000952,
      "learning_rate": 1.9786981747390774e-07,
      "loss": 0.6822,
      "step": 1990,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48148148148148145,
      "success_rate.epoch.env.logic": 0.40601503759398494,
      "success_rate.epoch.env.math": 0.8475991649269311,
      "success_rate.epoch.env.sat": 0.087248322147651,
      "success_rate.epoch.env.science": 0.6577060931899642,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48716097976725065,
      "success_rate.epoch.global": 0.6174942263279446,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.990506329113924,
      "tokens_p.mean_in_band": 0.6486979166666667,
      "tokens_rate.above_band": 0.8404255319148937,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1595744680851064
    },
    {
      "epoch": 0.3316156914893617,
      "grad_norm": 159.86115952178918,
      "learning_rate": 1.9785783630197266e-07,
      "loss": 0.7802,
      "step": 1995,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48148148148148145,
      "success_rate.epoch.env.logic": 0.405,
      "success_rate.epoch.env.math": 0.8475991649269311,
      "success_rate.epoch.env.sat": 0.08666666666666667,
      "success_rate.epoch.env.science": 0.6578829834747655,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48703190678632624,
      "success_rate.epoch.global": 0.6173337172473365,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9964025658807212,
      "tokens_p.mean_below_band": 7.566995918750763e-10,
      "tokens_p.mean_in_band": 0.6957720588235294,
      "tokens_rate.above_band": 0.9327296248382924,
      "tokens_rate.below_band": 0.00129366106080207,
      "tokens_rate.in_band": 0.06597671410090557
    },
    {
      "epoch": 0.3324468085106383,
      "grad_norm": 134.60845839540934,
      "learning_rate": 1.9784582343675314e-07,
      "loss": 0.9367,
      "step": 2000,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.40648379052369077,
      "success_rate.epoch.env.math": 0.8479166666666667,
      "success_rate.epoch.env.sat": 0.08666666666666667,
      "success_rate.epoch.env.science": 0.6583518930957684,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4867044955590998,
      "success_rate.epoch.global": 0.6177484204480184,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941907051282052,
      "tokens_p.mean_below_band": 1.545430450278218e-13,
      "tokens_p.mean_in_band": 0.7065972222222222,
      "tokens_rate.above_band": 0.9425981873111783,
      "tokens_rate.below_band": 0.0030211480362537764,
      "tokens_rate.in_band": 0.054380664652567974
    },
    {
      "epoch": 0.3332779255319149,
      "grad_norm": 144.5416703421745,
      "learning_rate": 1.97833778899569e-07,
      "loss": 0.8982,
      "step": 2005,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.40648379052369077,
      "success_rate.epoch.env.math": 0.8482328482328483,
      "success_rate.epoch.env.sat": 0.08666666666666667,
      "success_rate.epoch.env.science": 0.6589698046181173,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48678941311260254,
      "success_rate.epoch.global": 0.6183381088825215,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9868055555555556,
      "tokens_p.mean_in_band": 0.65640625,
      "tokens_rate.above_band": 0.84375,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15625
    },
    {
      "epoch": 0.3341090425531915,
      "grad_norm": 193.94001096760982,
      "learning_rate": 1.9782170271179645e-07,
      "loss": 0.939,
      "step": 2010,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.42696629213483145,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.4034653465346535,
      "success_rate.epoch.env.math": 0.8485477178423236,
      "success_rate.epoch.env.sat": 0.08609271523178808,
      "success_rate.epoch.env.science": 0.6594235033259424,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4865327015574557,
      "success_rate.epoch.global": 0.6180674671240709,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9938650306748467,
      "tokens_p.mean_in_band": 0.6032968101659751,
      "tokens_rate.above_band": 0.8256150506512301,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17438494934876989
    },
    {
      "epoch": 0.3349401595744681,
      "grad_norm": 156.6257582971536,
      "learning_rate": 1.978095948948677e-07,
      "loss": 0.6731,
      "step": 2015,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4222222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.4049382716049383,
      "success_rate.epoch.env.math": 0.8488612836438924,
      "success_rate.epoch.env.sat": 0.08552631578947369,
      "success_rate.epoch.env.science": 0.6597345132743363,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4862406135088487,
      "success_rate.epoch.global": 0.6181921870544625,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958984375,
      "tokens_p.mean_in_band": 0.641633064516129,
      "tokens_rate.above_band": 0.9116809116809117,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08831908831908832
    },
    {
      "epoch": 0.3357712765957447,
      "grad_norm": 141.13826303276414,
      "learning_rate": 1.9779745547027115e-07,
      "loss": 0.8363,
      "step": 2020,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4175824175824176,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.4049382716049383,
      "success_rate.epoch.env.math": 0.8488612836438924,
      "success_rate.epoch.env.sat": 0.08552631578947369,
      "success_rate.epoch.env.science": 0.6601941747572816,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48586060049458873,
      "success_rate.epoch.global": 0.6183836084234491,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9948850896860987,
      "tokens_p.mean_in_band": 0.7233072916666666,
      "tokens_rate.above_band": 0.9674620390455532,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03253796095444685
    },
    {
      "epoch": 0.33660239361702127,
      "grad_norm": 219.97975682352043,
      "learning_rate": 1.977852844595513e-07,
      "loss": 0.7148,
      "step": 2025,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4175824175824176,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.4049382716049383,
      "success_rate.epoch.env.math": 0.8488612836438924,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.6609423161602818,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48587779557413097,
      "success_rate.epoch.global": 0.61875,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9985835694050992,
      "tokens_p.mean_in_band": 0.5753255208333333,
      "tokens_rate.above_band": 0.9216710182767625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0783289817232376
    },
    {
      "epoch": 0.33743351063829785,
      "grad_norm": 335.72442402858115,
      "learning_rate": 1.9777308188430876e-07,
      "loss": 0.9032,
      "step": 2030,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4175824175824176,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.4039408866995074,
      "success_rate.epoch.env.math": 0.8477366255144033,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.6609498680738787,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48568556910855615,
      "success_rate.epoch.global": 0.6186560816557981,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.47916666666666663,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9930803571428571,
      "tokens_p.mean_in_band": 0.703046875,
      "tokens_rate.above_band": 0.8484848484848485,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15151515151515152
    },
    {
      "epoch": 0.3382646276595745,
      "grad_norm": 180.70770770572085,
      "learning_rate": 1.9776084776620008e-07,
      "loss": 0.7969,
      "step": 2035,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4175824175824176,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47560975609756095,
      "success_rate.epoch.env.logic": 0.40294840294840295,
      "success_rate.epoch.env.math": 0.8480492813141683,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.6615452151009658,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48567788902453324,
      "success_rate.epoch.global": 0.6190206623266346,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0005196523053665,
      "tokens_p.mean_in_band": 0.5813210227272727,
      "tokens_rate.above_band": 0.9678127286027798,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03218727139722019
    },
    {
      "epoch": 0.3390957446808511,
      "grad_norm": 170.82886261002986,
      "learning_rate": 1.977485821269378e-07,
      "loss": 0.8812,
      "step": 2040,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4175824175824176,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4819277108433735,
      "success_rate.epoch.env.logic": 0.40294840294840295,
      "success_rate.epoch.env.math": 0.8486707566462167,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.6621384750219106,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48636267902442465,
      "success_rate.epoch.global": 0.619774011299435,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.988747553816047,
      "tokens_p.mean_in_band": 0.80810546875,
      "tokens_rate.above_band": 0.9012345679012346,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09876543209876543
    },
    {
      "epoch": 0.33992686170212766,
      "grad_norm": 133.08859243571013,
      "learning_rate": 1.977362849882905e-07,
      "loss": 0.9156,
      "step": 2045,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4175824175824176,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4819277108433735,
      "success_rate.epoch.env.logic": 0.40294840294840295,
      "success_rate.epoch.env.math": 0.8489795918367347,
      "success_rate.epoch.env.sat": 0.08441558441558442,
      "success_rate.epoch.env.science": 0.661706783369803,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4863013524510208,
      "success_rate.epoch.global": 0.6194640338504936,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.525,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.996549317617866,
      "tokens_p.mean_below_band": 7.729977369308472e-08,
      "tokens_p.mean_in_band": 0.6587171052631579,
      "tokens_rate.above_band": 0.912797281993205,
      "tokens_rate.below_band": 0.0011325028312570782,
      "tokens_rate.in_band": 0.08607021517553794
    },
    {
      "epoch": 0.34075797872340424,
      "grad_norm": 171.3487937304551,
      "learning_rate": 1.977239563720825e-07,
      "loss": 0.7762,
      "step": 2050,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4819277108433735,
      "success_rate.epoch.env.logic": 0.4019607843137255,
      "success_rate.epoch.env.math": 0.8492871690427699,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.6620026235242676,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4858042836083504,
      "success_rate.epoch.global": 0.6192621796676993,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9983705098493627,
      "tokens_p.mean_in_band": 0.5961277173913043,
      "tokens_rate.above_band": 0.9493949394939494,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050605060506050605
    },
    {
      "epoch": 0.3415890957446808,
      "grad_norm": 201.94683922299325,
      "learning_rate": 1.9771159630019412e-07,
      "loss": 0.7822,
      "step": 2055,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4019607843137255,
      "success_rate.epoch.env.math": 0.847870182555781,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.6621562636403318,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4862501182338903,
      "success_rate.epoch.global": 0.6194491287240023,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6555555555555556,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9934612771739131,
      "tokens_p.mean_below_band": 1.2014061212539673e-07,
      "tokens_p.mean_in_band": 0.5257874750996016,
      "tokens_rate.above_band": 0.8797513746115229,
      "tokens_rate.below_band": 0.0002390628735357399,
      "tokens_rate.in_band": 0.12000956251494142
    },
    {
      "epoch": 0.34242021276595747,
      "grad_norm": 124.6837014424957,
      "learning_rate": 1.9769920479456145e-07,
      "loss": 0.7904,
      "step": 2060,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4019607843137255,
      "success_rate.epoch.env.math": 0.8487903225806451,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.6617326948193296,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4862952610706051,
      "success_rate.epoch.global": 0.6195682646481637,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9869025735294118,
      "tokens_p.mean_below_band": 2.8405338525772095e-08,
      "tokens_p.mean_in_band": 0.6170099431818182,
      "tokens_rate.above_band": 0.8553459119496856,
      "tokens_rate.below_band": 0.006289308176100629,
      "tokens_rate.in_band": 0.13836477987421383
    },
    {
      "epoch": 0.34325132978723405,
      "grad_norm": 213.16549747677635,
      "learning_rate": 1.9768678187717638e-07,
      "loss": 0.7796,
      "step": 2065,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.41935483870967744,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.40097799511002447,
      "success_rate.epoch.env.math": 0.8487903225806451,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.661598609904431,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.486767487100624,
      "success_rate.epoch.global": 0.6194739787353106,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9985085756897838,
      "tokens_p.mean_in_band": 0.4836881868131868,
      "tokens_rate.above_band": 0.9364525139664804,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06354748603351955
    },
    {
      "epoch": 0.34408244680851063,
      "grad_norm": 116.84908200473514,
      "learning_rate": 1.9767432757008655e-07,
      "loss": 0.7543,
      "step": 2070,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.41935483870967744,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4024390243902439,
      "success_rate.epoch.env.math": 0.8487903225806451,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.6620390455531453,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48694034754870885,
      "success_rate.epoch.global": 0.6200055881531154,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9962548324742269,
      "tokens_p.mean_below_band": 1.9190338207408786e-10,
      "tokens_p.mean_in_band": 0.6834635416666667,
      "tokens_rate.above_band": 0.9615861214374225,
      "tokens_rate.below_band": 0.0012391573729863693,
      "tokens_rate.in_band": 0.03717472118959108
    },
    {
      "epoch": 0.3449135638297872,
      "grad_norm": 138.59798139190588,
      "learning_rate": 1.976618418953953e-07,
      "loss": 0.7698,
      "step": 2075,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.41935483870967744,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4024390243902439,
      "success_rate.epoch.env.math": 0.8490945674044266,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.6626297577854672,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4870217072810819,
      "success_rate.epoch.global": 0.6205742960691386,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9933035714285714,
      "tokens_p.mean_in_band": 0.6496803977272727,
      "tokens_rate.above_band": 0.8166666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18333333333333332
    },
    {
      "epoch": 0.34574468085106386,
      "grad_norm": 138.28187139862686,
      "learning_rate": 1.9764932487526163e-07,
      "loss": 0.6239,
      "step": 2080,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.4024390243902439,
      "success_rate.epoch.env.math": 0.8490945674044266,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6626349892008639,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4871152331248982,
      "success_rate.epoch.global": 0.6203729473977178,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9909950071326676,
      "tokens_p.mean_in_band": 0.7669270833333334,
      "tokens_rate.above_band": 0.9033505154639175,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09664948453608248
    },
    {
      "epoch": 0.34657579787234044,
      "grad_norm": 207.4961467261952,
      "learning_rate": 1.9763677653190018e-07,
      "loss": 0.676,
      "step": 2085,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.4024390243902439,
      "success_rate.epoch.env.math": 0.845691382765531,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6635071090047393,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4868851363217146,
      "success_rate.epoch.global": 0.6206609275201332,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9891939252336449,
      "tokens_p.mean_below_band": 8.149072527885437e-09,
      "tokens_p.mean_in_band": 0.69921875,
      "tokens_rate.above_band": 0.816793893129771,
      "tokens_rate.below_band": 0.007633587786259542,
      "tokens_rate.in_band": 0.17557251908396945
    },
    {
      "epoch": 0.347406914893617,
      "grad_norm": 162.35393397977262,
      "learning_rate": 1.9762419688758123e-07,
      "loss": 0.6411,
      "step": 2090,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.4053398058252427,
      "success_rate.epoch.env.math": 0.845691382765531,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6638005159071367,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48717551707965967,
      "success_rate.epoch.global": 0.621119733924612,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9891561514195584,
      "tokens_p.mean_in_band": 0.6729835304054054,
      "tokens_rate.above_band": 0.8107416879795396,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18925831202046037
    },
    {
      "epoch": 0.3482380319148936,
      "grad_norm": 159.10187801087,
      "learning_rate": 1.9761158596463051e-07,
      "loss": 0.8077,
      "step": 2095,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.4053398058252427,
      "success_rate.epoch.env.math": 0.845691382765531,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6646655231560892,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48725415410229167,
      "success_rate.epoch.global": 0.62174875484228,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967811158798283,
      "tokens_p.mean_in_band": 0.5761284722222222,
      "tokens_rate.above_band": 0.9628099173553719,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0371900826446281
    },
    {
      "epoch": 0.3490691489361702,
      "grad_norm": 200.00058197347562,
      "learning_rate": 1.9759894378542938e-07,
      "loss": 0.8468,
      "step": 2100,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.40481927710843374,
      "success_rate.epoch.env.math": 0.846307385229541,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.6645271715875053,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4872502561185296,
      "success_rate.epoch.global": 0.6216887417218543,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.6444444444444445,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9995993589743589,
      "tokens_p.mean_in_band": 0.44331498579545453,
      "tokens_rate.above_band": 0.9497716894977168,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0502283105022831
    },
    {
      "epoch": 0.34990026595744683,
      "grad_norm": 86.50107371896644,
      "learning_rate": 1.9758627037241456e-07,
      "loss": 0.6994,
      "step": 2105,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4883720930232558,
      "success_rate.epoch.env.logic": 0.40481927710843374,
      "success_rate.epoch.env.math": 0.8466135458167331,
      "success_rate.epoch.env.sat": 0.08280254777070063,
      "success_rate.epoch.env.science": 0.6652433817250214,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48677262258457576,
      "success_rate.epoch.global": 0.6219713656387665,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9886060767590619,
      "tokens_p.mean_in_band": 0.7242268041237113,
      "tokens_rate.above_band": 0.8286219081272085,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17137809187279152
    },
    {
      "epoch": 0.3507313829787234,
      "grad_norm": 72.33977276892092,
      "learning_rate": 1.9757356574807827e-07,
      "loss": 0.768,
      "step": 2110,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4148936170212766,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4883720930232558,
      "success_rate.epoch.env.logic": 0.40384615384615385,
      "success_rate.epoch.env.math": 0.8472222222222222,
      "success_rate.epoch.env.sat": 0.08227848101265822,
      "success_rate.epoch.env.science": 0.6656716417910448,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4867307813528658,
      "success_rate.epoch.global": 0.6221489420170376,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9960106382978723,
      "tokens_p.mean_in_band": 0.5833610372340425,
      "tokens_rate.above_band": 0.9375,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0625
    },
    {
      "epoch": 0.3515625,
      "grad_norm": 122.91251426632387,
      "learning_rate": 1.975608299349681e-07,
      "loss": 0.656,
      "step": 2115,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4105263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4883720930232558,
      "success_rate.epoch.env.logic": 0.4028776978417266,
      "success_rate.epoch.env.math": 0.8481262327416174,
      "success_rate.epoch.env.sat": 0.08227848101265822,
      "success_rate.epoch.env.science": 0.6659574468085107,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48635387756201404,
      "success_rate.epoch.global": 0.6223622910386407,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9955778301886793,
      "tokens_p.mean_in_band": 0.67890625,
      "tokens_rate.above_band": 0.9695121951219512,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03048780487804878
    },
    {
      "epoch": 0.3523936170212766,
      "grad_norm": 145.75762946279514,
      "learning_rate": 1.9754806295568703e-07,
      "loss": 0.7459,
      "step": 2120,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4105263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4883720930232558,
      "success_rate.epoch.env.logic": 0.4028776978417266,
      "success_rate.epoch.env.math": 0.8481262327416174,
      "success_rate.epoch.env.sat": 0.08176100628930817,
      "success_rate.epoch.env.science": 0.6655333616659583,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48626828121056836,
      "success_rate.epoch.global": 0.6219545578976184,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.29166666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9917355371900827,
      "tokens_p.mean_in_band": 0.6981969762731481,
      "tokens_rate.above_band": 0.8175675675675675,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18243243243243243
    },
    {
      "epoch": 0.35322473404255317,
      "grad_norm": 166.58920362574537,
      "learning_rate": 1.9753526483289325e-07,
      "loss": 0.8161,
      "step": 2125,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4105263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4883720930232558,
      "success_rate.epoch.env.logic": 0.4019138755980861,
      "success_rate.epoch.env.math": 0.8487229862475442,
      "success_rate.epoch.env.sat": 0.08176100628930817,
      "success_rate.epoch.env.science": 0.6658184902459712,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48626083210532284,
      "success_rate.epoch.global": 0.6222343621961213,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994140625,
      "tokens_p.mean_in_band": 0.5240625,
      "tokens_rate.above_band": 0.9768732654949122,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02312673450508788
    },
    {
      "epoch": 0.3540558510638298,
      "grad_norm": 84.31554724364025,
      "learning_rate": 1.9752243558930039e-07,
      "loss": 0.6842,
      "step": 2130,
      "success_rate.epoch.env.abd": 0.3684210526315789,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4883720930232558,
      "success_rate.epoch.env.logic": 0.4019138755980861,
      "success_rate.epoch.env.math": 0.8490196078431372,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.665961049957663,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.486812516277611,
      "success_rate.epoch.global": 0.6224100327153762,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9970238095238095,
      "tokens_p.mean_in_band": 0.5981685450819673,
      "tokens_rate.above_band": 0.8610478359908884,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13895216400911162
    },
    {
      "epoch": 0.3548869680851064,
      "grad_norm": 162.95437907151003,
      "learning_rate": 1.975095752476771e-07,
      "loss": 0.8477,
      "step": 2135,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4827586206896552,
      "success_rate.epoch.env.logic": 0.4033412887828162,
      "success_rate.epoch.env.math": 0.8493150684931506,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.6658206429780034,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48477142008578417,
      "success_rate.epoch.global": 0.6222101252041372,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.42000000000000004,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9880216383307573,
      "tokens_p.mean_below_band": 2.676642907317728e-09,
      "tokens_p.mean_in_band": 0.684285121681416,
      "tokens_rate.above_band": 0.8490813648293963,
      "tokens_rate.below_band": 0.0026246719160104987,
      "tokens_rate.in_band": 0.14829396325459318
    },
    {
      "epoch": 0.355718085106383,
      "grad_norm": 169.48388464635582,
      "learning_rate": 1.9749668383084744e-07,
      "loss": 0.8139,
      "step": 2140,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.4166666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4827586206896552,
      "success_rate.epoch.env.logic": 0.4033412887828162,
      "success_rate.epoch.env.math": 0.8493150684931506,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.6663851351351351,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4848227375546143,
      "success_rate.epoch.global": 0.622620989668298,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9925595238095238,
      "tokens_p.mean_in_band": 0.6245659722222222,
      "tokens_rate.above_band": 0.875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.125
    },
    {
      "epoch": 0.35654920212765956,
      "grad_norm": 95.28194179703517,
      "learning_rate": 1.9748376136169046e-07,
      "loss": 0.734,
      "step": 2145,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.422680412371134,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4033412887828162,
      "success_rate.epoch.env.math": 0.8493150684931506,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.6672283066554339,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4849473760825996,
      "success_rate.epoch.global": 0.6231687466087901,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9930527822151225,
      "tokens_p.mean_below_band": 1.4435499906539917e-07,
      "tokens_p.mean_in_band": 0.5313714378238342,
      "tokens_rate.above_band": 0.9065894279507604,
      "tokens_rate.below_band": 0.0002413709872073377,
      "tokens_rate.in_band": 0.09316920106203234
    },
    {
      "epoch": 0.35738031914893614,
      "grad_norm": 384.2611069554617,
      "learning_rate": 1.974708078631404e-07,
      "loss": 0.7637,
      "step": 2150,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.422680412371134,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4023809523809524,
      "success_rate.epoch.env.math": 0.8499025341130604,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.6675073560319462,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48493884686392313,
      "success_rate.epoch.global": 0.6234434217650243,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9913015463917526,
      "tokens_p.mean_in_band": 0.6534090909090909,
      "tokens_rate.above_band": 0.8546255506607929,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14537444933920704
    },
    {
      "epoch": 0.3582114361702128,
      "grad_norm": 117.31698365846226,
      "learning_rate": 1.9745782335818653e-07,
      "loss": 0.6945,
      "step": 2155,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4023809523809524,
      "success_rate.epoch.env.math": 0.8499025341130604,
      "success_rate.epoch.env.sat": 0.08074534161490683,
      "success_rate.epoch.env.science": 0.6677852348993288,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48545377747143076,
      "success_rate.epoch.global": 0.623615239124561,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.996629213483146,
      "tokens_p.mean_in_band": 0.559188179347826,
      "tokens_rate.above_band": 0.9063136456211812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09368635437881874
    },
    {
      "epoch": 0.35904255319148937,
      "grad_norm": 164.57010704848997,
      "learning_rate": 1.9744480786987316e-07,
      "loss": 0.77,
      "step": 2160,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.40380047505938244,
      "success_rate.epoch.env.math": 0.8504854368932039,
      "success_rate.epoch.env.sat": 0.08074534161490683,
      "success_rate.epoch.env.science": 0.6683417085427136,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48568640466251783,
      "success_rate.epoch.global": 0.6243257820927723,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930245535714286,
      "tokens_p.mean_in_band": 0.6948784722222222,
      "tokens_rate.above_band": 0.9613733905579399,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03862660944206009
    },
    {
      "epoch": 0.35987367021276595,
      "grad_norm": 166.71312425883977,
      "learning_rate": 1.9743176142129963e-07,
      "loss": 0.6699,
      "step": 2165,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4056603773584906,
      "success_rate.epoch.env.math": 0.8504854368932039,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6683396068590548,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48580998398804404,
      "success_rate.epoch.global": 0.6242261103633917,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6166666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.99515625,
      "tokens_p.mean_in_band": 0.5082370923913043,
      "tokens_rate.above_band": 0.9456264775413712,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054373522458628844
    },
    {
      "epoch": 0.36070478723404253,
      "grad_norm": 304.0544051190945,
      "learning_rate": 1.9741868403562014e-07,
      "loss": 0.7596,
      "step": 2170,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4047058823529412,
      "success_rate.epoch.env.math": 0.8507751937984496,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6681969949916527,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48534304268834316,
      "success_rate.epoch.global": 0.62395917271018,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.39285714285714285,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.997300392670157,
      "tokens_p.mean_in_band": 0.4777260638297872,
      "tokens_rate.above_band": 0.9420468557336621,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05795314426633785
    },
    {
      "epoch": 0.3615359042553192,
      "grad_norm": 113.96124949939217,
      "learning_rate": 1.9740557573604387e-07,
      "loss": 0.6863,
      "step": 2175,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.405152224824356,
      "success_rate.epoch.env.math": 0.851063829787234,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6680567139282736,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48539710608805414,
      "success_rate.epoch.global": 0.6239270386266095,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998046875,
      "tokens_p.mean_in_band": 0.5688802083333333,
      "tokens_rate.above_band": 0.9591280653950953,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04087193460490463
    },
    {
      "epoch": 0.36236702127659576,
      "grad_norm": 158.5559387645458,
      "learning_rate": 1.9739243654583485e-07,
      "loss": 0.7521,
      "step": 2180,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.40420560747663553,
      "success_rate.epoch.env.math": 0.8513513513513513,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6676372712146422,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48529905713376015,
      "success_rate.epoch.global": 0.6236616702355461,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9969254032258065,
      "tokens_p.mean_in_band": 0.5421875,
      "tokens_rate.above_band": 0.9393939393939394,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06060606060606061
    },
    {
      "epoch": 0.36319813829787234,
      "grad_norm": 104.46820216220819,
      "learning_rate": 1.9737926648831192e-07,
      "loss": 0.8485,
      "step": 2185,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4046511627906977,
      "success_rate.epoch.env.math": 0.8497109826589595,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6679119966791199,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4852154127779553,
      "success_rate.epoch.global": 0.6236645299145299,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9964595921450151,
      "tokens_p.mean_in_band": 0.512668918918919,
      "tokens_rate.above_band": 0.9470672389127325,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05293276108726753
    },
    {
      "epoch": 0.3640292553191489,
      "grad_norm": 161.6217803672966,
      "learning_rate": 1.9736606558684872e-07,
      "loss": 0.5828,
      "step": 2190,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4046511627906977,
      "success_rate.epoch.env.math": 0.85,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.668185584092792,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4852665586647474,
      "success_rate.epoch.global": 0.624,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9961828175895765,
      "tokens_p.mean_below_band": 1.6916601452976465e-10,
      "tokens_p.mean_in_band": 0.7063210227272727,
      "tokens_rate.above_band": 0.9638932496075353,
      "tokens_rate.below_band": 0.0015698587127158557,
      "tokens_rate.in_band": 0.03453689167974882
    },
    {
      "epoch": 0.3648603723404255,
      "grad_norm": 278.57117942104793,
      "learning_rate": 1.973528338648736e-07,
      "loss": 0.7787,
      "step": 2195,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4772727272727273,
      "success_rate.epoch.env.logic": 0.4060324825986079,
      "success_rate.epoch.env.math": 0.85,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6681818181818182,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4853917908371962,
      "success_rate.epoch.global": 0.6241682193239286,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9908088235294118,
      "tokens_p.mean_in_band": 0.6768798828125,
      "tokens_rate.above_band": 0.8735177865612648,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12648221343873517
    },
    {
      "epoch": 0.36569148936170215,
      "grad_norm": 166.85460207699504,
      "learning_rate": 1.9733957134586957e-07,
      "loss": 0.9068,
      "step": 2200,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47191011235955055,
      "success_rate.epoch.env.logic": 0.4060324825986079,
      "success_rate.epoch.env.math": 0.8505747126436781,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6683168316831684,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48496880094918265,
      "success_rate.epoch.global": 0.6243358129649309,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9934572391767211,
      "tokens_p.mean_below_band": 7.729977369308472e-08,
      "tokens_p.mean_in_band": 0.6528111645299145,
      "tokens_rate.above_band": 0.8570559610705596,
      "tokens_rate.below_band": 0.0006082725060827251,
      "tokens_rate.in_band": 0.14233576642335766
    },
    {
      "epoch": 0.36652260638297873,
      "grad_norm": 450.9470110920482,
      "learning_rate": 1.9732627805337446e-07,
      "loss": 1.0085,
      "step": 2205,
      "success_rate.epoch.env.abd": 0.35,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47191011235955055,
      "success_rate.epoch.env.logic": 0.40415704387990764,
      "success_rate.epoch.env.math": 0.8505747126436781,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6681762041992589,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4847855222034909,
      "success_rate.epoch.global": 0.6239724211084593,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.4583333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9988251879699248,
      "tokens_p.mean_in_band": 0.5187230603448276,
      "tokens_rate.above_band": 0.9520925110132159,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04790748898678414
    },
    {
      "epoch": 0.3673537234042553,
      "grad_norm": 489.9581590847949,
      "learning_rate": 1.9731295401098052e-07,
      "loss": 0.9225,
      "step": 2210,
      "success_rate.epoch.env.abd": 0.38095238095238093,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47191011235955055,
      "success_rate.epoch.env.logic": 0.4055299539170507,
      "success_rate.epoch.env.math": 0.8508604206500956,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6678997122893547,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4877250228476761,
      "success_rate.epoch.global": 0.6241397564849126,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950892857142857,
      "tokens_p.mean_in_band": 0.6326069078947368,
      "tokens_rate.above_band": 0.9364548494983278,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06354515050167224
    },
    {
      "epoch": 0.3681848404255319,
      "grad_norm": 99.90563541538353,
      "learning_rate": 1.972995992423347e-07,
      "loss": 0.6576,
      "step": 2215,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47191011235955055,
      "success_rate.epoch.env.logic": 0.4068965517241379,
      "success_rate.epoch.env.math": 0.851145038167939,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6672131147540984,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4903707633866036,
      "success_rate.epoch.global": 0.6240760295670539,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.8571428571428572,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9904384328358209,
      "tokens_p.mean_in_band": 0.5766741071428572,
      "tokens_rate.above_band": 0.8844884488448845,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11551155115511551
    },
    {
      "epoch": 0.3690159574468085,
      "grad_norm": 175.67127626612353,
      "learning_rate": 1.9728621377113841e-07,
      "loss": 0.8039,
      "step": 2220,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47191011235955055,
      "success_rate.epoch.env.logic": 0.4096109839816934,
      "success_rate.epoch.env.math": 0.8514285714285714,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.6673486088379705,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49065562335042723,
      "success_rate.epoch.global": 0.6245059288537549,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.8095238095238096,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.990909090909091,
      "tokens_p.mean_in_band": 0.6293150436046512,
      "tokens_rate.above_band": 0.8647798742138365,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13522012578616352
    },
    {
      "epoch": 0.3698470744680851,
      "grad_norm": 97.7200196216115,
      "learning_rate": 1.9727279762114763e-07,
      "loss": 0.5809,
      "step": 2225,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42424242424242425,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.410958904109589,
      "success_rate.epoch.env.math": 0.8519924098671727,
      "success_rate.epoch.env.sat": 0.07975460122699386,
      "success_rate.epoch.env.science": 0.6677564364527994,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4913551632819091,
      "success_rate.epoch.global": 0.6250328687877991,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972112860892388,
      "tokens_p.mean_in_band": 0.6765252976190477,
      "tokens_rate.above_band": 0.9477611940298507,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05223880597014925
    },
    {
      "epoch": 0.3706781914893617,
      "grad_norm": 233.0538426510748,
      "learning_rate": 1.9725935081617274e-07,
      "loss": 0.7786,
      "step": 2230,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41002277904328016,
      "success_rate.epoch.env.math": 0.8519924098671727,
      "success_rate.epoch.env.sat": 0.07926829268292683,
      "success_rate.epoch.env.science": 0.667890656874745,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49085237806092236,
      "success_rate.epoch.global": 0.6246719160104987,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.2,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9976927252985885,
      "tokens_p.mean_in_band": 0.6255686313291139,
      "tokens_rate.above_band": 0.921,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.079
    },
    {
      "epoch": 0.3715093085106383,
      "grad_norm": 126.02605568941038,
      "learning_rate": 1.9724587338007846e-07,
      "loss": 0.9944,
      "step": 2235,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4090909090909091,
      "success_rate.epoch.env.math": 0.8519924098671727,
      "success_rate.epoch.env.sat": 0.07878787878787878,
      "success_rate.epoch.env.science": 0.6688364524003255,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4908099700316642,
      "success_rate.epoch.global": 0.625032731081435,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9999074074074074,
      "tokens_p.mean_in_band": 0.5775991586538461,
      "tokens_rate.above_band": 0.9284731774415406,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07152682255845942
    },
    {
      "epoch": 0.3723404255319149,
      "grad_norm": 101.04668029304527,
      "learning_rate": 1.97232365336784e-07,
      "loss": 0.6937,
      "step": 2240,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41043083900226757,
      "success_rate.epoch.env.math": 0.8522727272727273,
      "success_rate.epoch.env.sat": 0.07878787878787878,
      "success_rate.epoch.env.science": 0.6691027202598457,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4879511683810369,
      "success_rate.epoch.global": 0.6252939639404234,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.994359756097561,
      "tokens_p.mean_in_band": 0.5496323529411765,
      "tokens_rate.above_band": 0.9601873536299765,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03981264637002342
    },
    {
      "epoch": 0.3731715425531915,
      "grad_norm": 259.93543710110924,
      "learning_rate": 1.972188267102628e-07,
      "loss": 0.6695,
      "step": 2245,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42574257425742573,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41043083900226757,
      "success_rate.epoch.env.math": 0.8525519848771267,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6696356275303643,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48905155108486015,
      "success_rate.epoch.global": 0.6260099035704978,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9642857142857143,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9955119680851063,
      "tokens_p.mean_in_band": 0.58466796875,
      "tokens_rate.above_band": 0.9494949494949495,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050505050505050504
    },
    {
      "epoch": 0.3740026595744681,
      "grad_norm": 170.37953314414946,
      "learning_rate": 1.972052575245426e-07,
      "loss": 0.6322,
      "step": 2250,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42574257425742573,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4117647058823529,
      "success_rate.epoch.env.math": 0.8531073446327684,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6700363930448847,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48925973218942803,
      "success_rate.epoch.global": 0.6265938069216758,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9971049046321526,
      "tokens_p.mean_in_band": 0.7662760416666666,
      "tokens_rate.above_band": 0.9839142091152815,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0160857908847185
    },
    {
      "epoch": 0.3748337765957447,
      "grad_norm": 191.85400134815322,
      "learning_rate": 1.9719165780370542e-07,
      "loss": 0.7102,
      "step": 2255,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42574257425742573,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4117647058823529,
      "success_rate.epoch.env.math": 0.8533834586466166,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6702986279257466,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4893086729980381,
      "success_rate.epoch.global": 0.6269160820992465,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9976760284810127,
      "tokens_p.mean_in_band": 0.595703125,
      "tokens_rate.above_band": 0.948948948948949,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05105105105105105
    },
    {
      "epoch": 0.37566489361702127,
      "grad_norm": 125.06878636799533,
      "learning_rate": 1.9717802757188738e-07,
      "loss": 0.5586,
      "step": 2260,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.42574257425742573,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4117647058823529,
      "success_rate.epoch.env.math": 0.8533834586466166,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.670555108608206,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48933198942371625,
      "success_rate.epoch.global": 0.6271713767176562,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9858870967741935,
      "tokens_p.mean_in_band": 0.71875,
      "tokens_rate.above_band": 0.8211920529801324,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17880794701986755
    },
    {
      "epoch": 0.37649601063829785,
      "grad_norm": 352.14754221086093,
      "learning_rate": 1.9716436685327884e-07,
      "loss": 0.598,
      "step": 2265,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.4215686274509804,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4117647058823529,
      "success_rate.epoch.env.math": 0.8533834586466166,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6709470304975923,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4889881689767108,
      "success_rate.epoch.global": 0.6273291925465838,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994589552238806,
      "tokens_p.mean_in_band": 0.6861979166666666,
      "tokens_rate.above_band": 0.925414364640884,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07458563535911603
    },
    {
      "epoch": 0.3773271276595745,
      "grad_norm": 201.4983490720875,
      "learning_rate": 1.971506756721242e-07,
      "loss": 0.6947,
      "step": 2270,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.4174757281553398,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41309255079006774,
      "success_rate.epoch.env.math": 0.8536585365853658,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.671205446535843,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48878529984844493,
      "success_rate.epoch.global": 0.6275826446280992,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9956955922865014,
      "tokens_p.mean_in_band": 0.6378173828125,
      "tokens_rate.above_band": 0.9577836411609498,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04221635883905013
    },
    {
      "epoch": 0.3781582446808511,
      "grad_norm": 83.74577021972645,
      "learning_rate": 1.9713695405272197e-07,
      "loss": 0.6504,
      "step": 2275,
      "success_rate.epoch.env.abd": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:alfworld": 0.4174757281553398,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4144144144144144,
      "success_rate.epoch.env.math": 0.8542056074766355,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6709316273490604,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.48893031033288425,
      "success_rate.epoch.global": 0.6277391080175303,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.7999999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9937770562770563,
      "tokens_p.mean_in_band": 0.56536865234375,
      "tokens_rate.above_band": 0.9352226720647774,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06477732793522267
    },
    {
      "epoch": 0.37898936170212766,
      "grad_norm": 242.0518233652568,
      "learning_rate": 1.9712320201942466e-07,
      "loss": 0.6159,
      "step": 2280,
      "success_rate.epoch.env.abd": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:alfworld": 0.4174757281553398,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4157303370786517,
      "success_rate.epoch.env.math": 0.8544776119402985,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6713258785942492,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49144611742177813,
      "success_rate.epoch.global": 0.6283140283140283,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.992468134414832,
      "tokens_p.mean_in_band": 0.6107474662162162,
      "tokens_rate.above_band": 0.9588888888888889,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04111111111111111
    },
    {
      "epoch": 0.37982047872340424,
      "grad_norm": 171.3749426959497,
      "learning_rate": 1.9710941959663876e-07,
      "loss": 0.8784,
      "step": 2285,
      "success_rate.epoch.env.abd": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:alfworld": 0.4174757281553398,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4170403587443946,
      "success_rate.epoch.env.math": 0.8550185873605948,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.671451355661882,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4916257968902938,
      "success_rate.epoch.global": 0.6287255909558068,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9965523785425101,
      "tokens_p.mean_in_band": 0.4839618389423077,
      "tokens_rate.above_band": 0.95,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05
    },
    {
      "epoch": 0.3806515957446808,
      "grad_norm": 216.32496356539426,
      "learning_rate": 1.970956068088247e-07,
      "loss": 0.8025,
      "step": 2290,
      "success_rate.epoch.env.abd": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:alfworld": 0.4174757281553398,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41834451901565994,
      "success_rate.epoch.env.math": 0.8558225508317929,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.671047391477499,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4917807204864829,
      "success_rate.epoch.global": 0.6288791997948192,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9883052147239264,
      "tokens_p.mean_below_band": 1.0800249583553523e-11,
      "tokens_p.mean_in_band": 0.6879111842105263,
      "tokens_rate.above_band": 0.8907103825136612,
      "tokens_rate.below_band": 0.00546448087431694,
      "tokens_rate.in_band": 0.10382513661202186
    },
    {
      "epoch": 0.38148271276595747,
      "grad_norm": 113.91064570835519,
      "learning_rate": 1.9708176368049677e-07,
      "loss": 0.6917,
      "step": 2295,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.41346153846153844,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41834451901565994,
      "success_rate.epoch.env.math": 0.8560885608856088,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6713091922005571,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4936047519156423,
      "success_rate.epoch.global": 0.6290983606557377,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9960133744855967,
      "tokens_p.mean_in_band": 0.6800944010416666,
      "tokens_rate.above_band": 0.9681274900398407,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03187250996015936
    },
    {
      "epoch": 0.38231382978723405,
      "grad_norm": 320.1123134365402,
      "learning_rate": 1.970678902362232e-07,
      "loss": 0.7575,
      "step": 2300,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4095238095238095,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.3,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.41964285714285715,
      "success_rate.epoch.env.math": 0.8550458715596331,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6714342471195868,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4932813859867808,
      "success_rate.epoch.global": 0.6291847687196525,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.995844414893617,
      "tokens_p.mean_in_band": 0.6862571022727273,
      "tokens_rate.above_band": 0.9447236180904522,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05527638190954774
    },
    {
      "epoch": 0.38314494680851063,
      "grad_norm": 74.54539615641788,
      "learning_rate": 1.9705398650062587e-07,
      "loss": 0.5729,
      "step": 2305,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4095238095238095,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4777777777777778,
      "success_rate.epoch.env.logic": 0.4177777777777778,
      "success_rate.epoch.env.math": 0.8555758683729433,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6720856463124505,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49073989411117774,
      "success_rate.epoch.global": 0.6293652816721896,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9957757654966393,
      "tokens_p.mean_in_band": 0.542016006097561,
      "tokens_rate.above_band": 0.9422941590429276,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.057705840957072485
    },
    {
      "epoch": 0.3839760638297872,
      "grad_norm": 148.1718887318526,
      "learning_rate": 1.9704005249838053e-07,
      "loss": 0.7807,
      "step": 2310,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4095238095238095,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4725274725274725,
      "success_rate.epoch.env.logic": 0.4177777777777778,
      "success_rate.epoch.env.math": 0.8558394160583942,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6725978647686833,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49033311782857586,
      "success_rate.epoch.global": 0.62970498474059,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9869897959183673,
      "tokens_p.mean_in_band": 0.22960464015151516,
      "tokens_rate.above_band": 0.4260869565217391,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.5739130434782609
    },
    {
      "epoch": 0.38480718085106386,
      "grad_norm": 145.0841983963652,
      "learning_rate": 1.9702608825421662e-07,
      "loss": 0.8626,
      "step": 2315,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4725274725274725,
      "success_rate.epoch.env.logic": 0.4177777777777778,
      "success_rate.epoch.env.math": 0.8558394160583942,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.6732438831886346,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.490040625669906,
      "success_rate.epoch.global": 0.6300152361604876,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9941611842105263,
      "tokens_p.mean_in_band": 0.6964518229166666,
      "tokens_rate.above_band": 0.9405940594059405,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0594059405940594
    },
    {
      "epoch": 0.38563829787234044,
      "grad_norm": 213.57600364462067,
      "learning_rate": 1.970120937929173e-07,
      "loss": 0.9426,
      "step": 2320,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4673913043478261,
      "success_rate.epoch.env.logic": 0.41685144124168516,
      "success_rate.epoch.env.math": 0.8558394160583942,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.6734935013784955,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4900106368842669,
      "success_rate.epoch.global": 0.6300050684237202,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958898747390397,
      "tokens_p.mean_in_band": 0.5388842680608364,
      "tokens_rate.above_band": 0.9425010931351115,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.057498906864888503
    },
    {
      "epoch": 0.386469414893617,
      "grad_norm": 339.14442542069975,
      "learning_rate": 1.9699806913931925e-07,
      "loss": 0.8085,
      "step": 2325,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4673913043478261,
      "success_rate.epoch.env.logic": 0.4175824175824176,
      "success_rate.epoch.env.math": 0.8561020036429873,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.6740070782540307,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49014764968434493,
      "success_rate.epoch.global": 0.6303413400758533,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9945667220376523,
      "tokens_p.mean_in_band": 0.6427859042553191,
      "tokens_rate.above_band": 0.9505263157894737,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049473684210526316
    },
    {
      "epoch": 0.3873005319148936,
      "grad_norm": 164.1906112757732,
      "learning_rate": 1.9698401431831282e-07,
      "loss": 0.6465,
      "step": 2330,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4673913043478261,
      "success_rate.epoch.env.logic": 0.41885964912280704,
      "success_rate.epoch.env.math": 0.8561020036429873,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.6747744213417026,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49033352010507786,
      "success_rate.epoch.global": 0.6309944472488642,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9895287958115183,
      "tokens_p.mean_in_band": 0.7799479166666666,
      "tokens_rate.above_band": 0.9138755980861244,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0861244019138756
    },
    {
      "epoch": 0.3881316489361702,
      "grad_norm": 136.1435542467951,
      "learning_rate": 1.9696992935484188e-07,
      "loss": 0.7365,
      "step": 2335,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4673913043478261,
      "success_rate.epoch.env.logic": 0.41885964912280704,
      "success_rate.epoch.env.math": 0.8563636363636363,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.675146771037182,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.4903911548701804,
      "success_rate.epoch.global": 0.6313932980599647,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9829931972789115,
      "tokens_p.mean_in_band": 0.6982717803030303,
      "tokens_rate.above_band": 0.8166666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18333333333333332
    },
    {
      "epoch": 0.38896276595744683,
      "grad_norm": 222.28414961351368,
      "learning_rate": 1.9695581427390374e-07,
      "loss": 0.9462,
      "step": 2340,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4673913043478261,
      "success_rate.epoch.env.logic": 0.4201312910284464,
      "success_rate.epoch.env.math": 0.8566243194192378,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.6755173760249903,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.49056414850191227,
      "success_rate.epoch.global": 0.6318833291425697,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9887820512820513,
      "tokens_p.mean_in_band": 0.5688244047619048,
      "tokens_rate.above_band": 0.9176470588235294,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08235294117647059
    },
    {
      "epoch": 0.3897938829787234,
      "grad_norm": 182.55120314801775,
      "learning_rate": 1.969416691005493e-07,
      "loss": 0.7169,
      "step": 2345,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4673913043478261,
      "success_rate.epoch.env.logic": 0.42139737991266374,
      "success_rate.epoch.env.math": 0.8568840579710145,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.6753804135778385,
      "success_rate.epoch.env.webshop": 0.3333333333333333,
      "success_rate.epoch.env_macro_mean": 0.47553889380392816,
      "success_rate.epoch.global": 0.6318432948267202,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9913740920096852,
      "tokens_p.mean_in_band": 0.49870445979899497,
      "tokens_rate.above_band": 0.6748366013071896,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.32516339869281047
    },
    {
      "epoch": 0.390625,
      "grad_norm": 136.82508102092632,
      "learning_rate": 1.969274938598827e-07,
      "loss": 0.8511,
      "step": 2350,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.41956521739130437,
      "success_rate.epoch.env.math": 0.8568840579710145,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.6754966887417219,
      "success_rate.epoch.env.webshop": 0.3333333333333333,
      "success_rate.epoch.env_macro_mean": 0.4764130949448388,
      "success_rate.epoch.global": 0.6318295739348371,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9962775037936267,
      "tokens_p.mean_in_band": 0.6385143649193549,
      "tokens_rate.above_band": 0.9770200148257969,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022979985174203115
    },
    {
      "epoch": 0.3914561170212766,
      "grad_norm": 117.64524890024998,
      "learning_rate": 1.9691328857706155e-07,
      "loss": 0.6044,
      "step": 2355,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.41865509761388287,
      "success_rate.epoch.env.math": 0.8568840579710145,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.675990675990676,
      "success_rate.epoch.env.webshop": 0.3333333333333333,
      "success_rate.epoch.env_macro_mean": 0.47637526471497815,
      "success_rate.epoch.global": 0.6320660330165082,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9945673076923077,
      "tokens_p.mean_in_band": 0.5319393382352942,
      "tokens_rate.above_band": 0.9502923976608187,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049707602339181284
    },
    {
      "epoch": 0.39228723404255317,
      "grad_norm": 180.84536452626043,
      "learning_rate": 1.9689905327729675e-07,
      "loss": 0.7345,
      "step": 2360,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.41865509761388287,
      "success_rate.epoch.env.math": 0.8568840579710145,
      "success_rate.epoch.env.sat": 0.08875739644970414,
      "success_rate.epoch.env.science": 0.6761055081458495,
      "success_rate.epoch.env.webshop": 0.3333333333333333,
      "success_rate.epoch.env_macro_mean": 0.47628907101710904,
      "success_rate.epoch.global": 0.6318681318681318,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9929187192118226,
      "tokens_p.mean_in_band": 0.6389973958333334,
      "tokens_rate.above_band": 0.8087649402390438,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19123505976095617
    },
    {
      "epoch": 0.3931183510638298,
      "grad_norm": 179.73182958390456,
      "learning_rate": 1.9688478798585246e-07,
      "loss": 0.8133,
      "step": 2365,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.4199134199134199,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.08875739644970414,
      "success_rate.epoch.env.science": 0.6767324816105303,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4689082311628115,
      "success_rate.epoch.global": 0.6323529411764706,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.989227207977208,
      "tokens_p.mean_in_band": 0.582958984375,
      "tokens_rate.above_band": 0.814385150812065,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18561484918793503
    },
    {
      "epoch": 0.3939494680851064,
      "grad_norm": 145.6081595339324,
      "learning_rate": 1.9687049272804607e-07,
      "loss": 0.8447,
      "step": 2370,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.4199134199134199,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.08823529411764706,
      "success_rate.epoch.env.science": 0.6768457672980286,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4688710660133062,
      "success_rate.epoch.global": 0.6323126711476226,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9972426470588235,
      "tokens_p.mean_in_band": 0.595,
      "tokens_rate.above_band": 0.9373433583959899,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06265664160401002
    },
    {
      "epoch": 0.394780585106383,
      "grad_norm": 178.85416131259834,
      "learning_rate": 1.9685616752924818e-07,
      "loss": 0.7202,
      "step": 2375,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.4190064794816415,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.08823529411764706,
      "success_rate.epoch.env.science": 0.677207867335133,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4688215350683358,
      "success_rate.epoch.global": 0.632455268389662,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9904442148760331,
      "tokens_p.mean_in_band": 0.6848958333333334,
      "tokens_rate.above_band": 0.88,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12
    },
    {
      "epoch": 0.39561170212765956,
      "grad_norm": 137.48257854830314,
      "learning_rate": 1.9684181241488252e-07,
      "loss": 0.8424,
      "step": 2380,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.4190064794816415,
      "success_rate.epoch.env.math": 0.8571428571428571,
      "success_rate.epoch.env.sat": 0.08823529411764706,
      "success_rate.epoch.env.science": 0.6775682954982686,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4688543012649845,
      "success_rate.epoch.global": 0.6327543424317618,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995958429561201,
      "tokens_p.mean_in_band": 0.6864346590909091,
      "tokens_rate.above_band": 0.9516483516483516,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04835164835164835
    },
    {
      "epoch": 0.39644281914893614,
      "grad_norm": 178.4357826812623,
      "learning_rate": 1.9682742741042585e-07,
      "loss": 0.7598,
      "step": 2385,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.41935483870967744,
      "success_rate.epoch.env.math": 0.8576576576576577,
      "success_rate.epoch.env.sat": 0.0872093023255814,
      "success_rate.epoch.env.science": 0.6779400461183704,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4688732938623366,
      "success_rate.epoch.global": 0.6328299083931667,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9992897727272727,
      "tokens_p.mean_in_band": 0.6840359669811321,
      "tokens_rate.above_band": 0.9372781065088758,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06272189349112427
    },
    {
      "epoch": 0.3972739361702128,
      "grad_norm": 133.1453574293202,
      "learning_rate": 1.9681301254140808e-07,
      "loss": 0.5345,
      "step": 2390,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47368421052631576,
      "success_rate.epoch.env.logic": 0.41755888650963596,
      "success_rate.epoch.env.math": 0.8579136690647482,
      "success_rate.epoch.env.sat": 0.0872093023255814,
      "success_rate.epoch.env.science": 0.6783109404990403,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46830890839494704,
      "success_rate.epoch.global": 0.6327236777063767,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9940575132978723,
      "tokens_p.mean_in_band": 0.6707732371794872,
      "tokens_rate.above_band": 0.9506953223767383,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0493046776232617
    },
    {
      "epoch": 0.39810505319148937,
      "grad_norm": 103.41521914656765,
      "learning_rate": 1.9679856783341205e-07,
      "loss": 0.9273,
      "step": 2395,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.41755888650963596,
      "success_rate.epoch.env.math": 0.8581687612208259,
      "success_rate.epoch.env.sat": 0.0872093023255814,
      "success_rate.epoch.env.science": 0.678544061302682,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46790472679798384,
      "success_rate.epoch.global": 0.6328645447816432,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9840158045977011,
      "tokens_p.mean_in_band": 0.5209029103053435,
      "tokens_rate.above_band": 0.7265135699373695,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.27348643006263046
    },
    {
      "epoch": 0.39893617021276595,
      "grad_norm": 202.55159073370515,
      "learning_rate": 1.9678409331207356e-07,
      "loss": 0.8917,
      "step": 2400,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.417910447761194,
      "success_rate.epoch.env.math": 0.8586762075134168,
      "success_rate.epoch.env.sat": 0.08670520231213873,
      "success_rate.epoch.env.science": 0.6786671773266948,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46794818348477646,
      "success_rate.epoch.global": 0.6329145109632914,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9931579535299374,
      "tokens_p.mean_in_band": 0.7709558823529412,
      "tokens_rate.above_band": 0.9294019933554817,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07059800664451828
    },
    {
      "epoch": 0.39976728723404253,
      "grad_norm": 144.3813228811916,
      "learning_rate": 1.9676958900308137e-07,
      "loss": 0.7197,
      "step": 2405,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.4182590233545648,
      "success_rate.epoch.env.math": 0.8586762075134168,
      "success_rate.epoch.env.sat": 0.08670520231213873,
      "success_rate.epoch.env.science": 0.6794038975926634,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46804684674471647,
      "success_rate.epoch.global": 0.6333907056798623,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9969470827679783,
      "tokens_p.mean_in_band": 0.6713541666666667,
      "tokens_rate.above_band": 0.9608865710560626,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03911342894393742
    },
    {
      "epoch": 0.4005984042553192,
      "grad_norm": 303.8825594122185,
      "learning_rate": 1.9675505493217704e-07,
      "loss": 0.781,
      "step": 2410,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.4194915254237288,
      "success_rate.epoch.env.math": 0.8594306049822064,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.6796338672768879,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4682030797866949,
      "success_rate.epoch.global": 0.6337993622761835,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9914259927797834,
      "tokens_p.mean_in_band": 0.5450994318181818,
      "tokens_rate.above_band": 0.8629283489096573,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13707165109034267
    },
    {
      "epoch": 0.40142952127659576,
      "grad_norm": 161.17103152176114,
      "learning_rate": 1.9674049112515505e-07,
      "loss": 0.8039,
      "step": 2415,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4639175257731959,
      "success_rate.epoch.env.logic": 0.4194915254237288,
      "success_rate.epoch.env.math": 0.8599290780141844,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6796190476190476,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46776294963304904,
      "success_rate.epoch.global": 0.633692458374143,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9890287769784173,
      "tokens_p.mean_below_band": 1.8189894035458565e-09,
      "tokens_p.mean_in_band": 0.6151167168674698,
      "tokens_rate.above_band": 0.8062645011600929,
      "tokens_rate.below_band": 0.001160092807424594,
      "tokens_rate.in_band": 0.1925754060324826
    },
    {
      "epoch": 0.40226063829787234,
      "grad_norm": 494.3951137688073,
      "learning_rate": 1.9672589760786253e-07,
      "loss": 0.7364,
      "step": 2420,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4056603773584906,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4639175257731959,
      "success_rate.epoch.env.logic": 0.42071881606765327,
      "success_rate.epoch.env.math": 0.8601769911504424,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6804711246200608,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46797452061315764,
      "success_rate.epoch.global": 0.6344979232836551,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9900147928994083,
      "tokens_p.mean_in_band": 0.7309027777777778,
      "tokens_rate.above_band": 0.949438202247191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05056179775280899
    },
    {
      "epoch": 0.4030917553191489,
      "grad_norm": 93.89993135424115,
      "learning_rate": 1.9671127440619942e-07,
      "loss": 0.7083,
      "step": 2425,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4639175257731959,
      "success_rate.epoch.env.logic": 0.42105263157894735,
      "success_rate.epoch.env.math": 0.859402460456942,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6808349146110056,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.46847248886054643,
      "success_rate.epoch.global": 0.6349012917377529,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8125,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.996326754385965,
      "tokens_p.mean_in_band": 0.762542724609375,
      "tokens_rate.above_band": 0.946843853820598,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053156146179401995
    },
    {
      "epoch": 0.4039228723404255,
      "grad_norm": 161.3842075736701,
      "learning_rate": 1.966966215461183e-07,
      "loss": 0.8298,
      "step": 2430,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42105263157894735,
      "success_rate.epoch.env.math": 0.8601398601398601,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6808349146110056,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4686057923656543,
      "success_rate.epoch.global": 0.6351022395326192,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9896760633036598,
      "tokens_p.mean_in_band": 0.6954210069444444,
      "tokens_rate.above_band": 0.8753246753246753,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12467532467532468
    },
    {
      "epoch": 0.40475398936170215,
      "grad_norm": 165.3783824669458,
      "learning_rate": 1.9668193905362442e-07,
      "loss": 0.7713,
      "step": 2435,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42016806722689076,
      "success_rate.epoch.env.math": 0.8586387434554974,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6813020439061317,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4684313785709913,
      "success_rate.epoch.global": 0.635171241195045,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9954028925619834,
      "tokens_p.mean_in_band": 0.5255126953125,
      "tokens_rate.above_band": 0.9497645211930926,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05023547880690738
    },
    {
      "epoch": 0.40558510638297873,
      "grad_norm": 120.33365203894601,
      "learning_rate": 1.9666722695477561e-07,
      "loss": 0.7,
      "step": 2440,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.4205020920502092,
      "success_rate.epoch.env.math": 0.8588850174216028,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6810117025292564,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4684577383357684,
      "success_rate.epoch.global": 0.6350860188999273,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6904761904761904,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9931102362204725,
      "tokens_p.mean_in_band": 0.6144649621212122,
      "tokens_rate.above_band": 0.8850174216027874,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11498257839721254
    },
    {
      "epoch": 0.4064162234042553,
      "grad_norm": 167.69555133464618,
      "learning_rate": 1.9665248527568227e-07,
      "loss": 0.6946,
      "step": 2445,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42083333333333334,
      "success_rate.epoch.env.math": 0.8588850174216028,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.6816126601356444,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4685424836893604,
      "success_rate.epoch.global": 0.6354620222544751,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9927474402730375,
      "tokens_p.mean_in_band": 0.466734446347032,
      "tokens_rate.above_band": 0.8005464480874317,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1994535519125683
    },
    {
      "epoch": 0.4072473404255319,
      "grad_norm": 121.39749774839373,
      "learning_rate": 1.9663771404250722e-07,
      "loss": 0.6475,
      "step": 2450,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42203742203742206,
      "success_rate.epoch.env.math": 0.8588850174216028,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.6817155756207675,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4686170283441058,
      "success_rate.epoch.global": 0.6355072463768116,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9974385245901639,
      "tokens_p.mean_in_band": 0.7049725506756757,
      "tokens_rate.above_band": 0.9202586206896551,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07974137931034483
    },
    {
      "epoch": 0.4080784574468085,
      "grad_norm": 226.74189587465628,
      "learning_rate": 1.966229132814658e-07,
      "loss": 0.8378,
      "step": 2455,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42203742203742206,
      "success_rate.epoch.env.math": 0.8596187175043327,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.6816816816816816,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4686806470844372,
      "success_rate.epoch.global": 0.6358158592431912,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9889481707317073,
      "tokens_p.mean_in_band": 0.6402994791666666,
      "tokens_rate.above_band": 0.9318181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06818181818181818
    },
    {
      "epoch": 0.4089095744680851,
      "grad_norm": 155.17495827800832,
      "learning_rate": 1.9660808301882575e-07,
      "loss": 0.8739,
      "step": 2460,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42203742203742206,
      "success_rate.epoch.env.math": 0.8581314878892734,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.6812734082397004,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4685083286247062,
      "success_rate.epoch.global": 0.6354667949951877,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.42857142857142855,
      "success_rate.window.env_macro_mean": 0.10714285714285714,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9965329835082459,
      "tokens_p.mean_in_band": 0.5718587239583334,
      "tokens_rate.above_band": 0.9328671328671329,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06713286713286713
    },
    {
      "epoch": 0.4097406914893617,
      "grad_norm": 112.72425591902896,
      "learning_rate": 1.965932232809071e-07,
      "loss": 0.6732,
      "step": 2465,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.411214953271028,
      "success_rate.epoch.env.agentgym:sciworld": 0.25,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42203742203742206,
      "success_rate.epoch.env.math": 0.8586206896551725,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.6814953271028037,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4685729759546154,
      "success_rate.epoch.global": 0.6358395387941388,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.43333333333333335,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9906914893617021,
      "tokens_p.mean_below_band": 4.760636329592671e-13,
      "tokens_p.mean_in_band": 0.61181640625,
      "tokens_rate.above_band": 0.8703703703703703,
      "tokens_rate.below_band": 0.006172839506172839,
      "tokens_rate.in_band": 0.12345679012345678
    },
    {
      "epoch": 0.4105718085106383,
      "grad_norm": 120.93056771817326,
      "learning_rate": 1.965783340940823e-07,
      "loss": 0.5889,
      "step": 2470,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42203742203742206,
      "success_rate.epoch.env.math": 0.8588640275387264,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.6822081312942931,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48195012106474483,
      "success_rate.epoch.global": 0.636385426653883,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9989961961115807,
      "tokens_p.mean_in_band": 0.57529296875,
      "tokens_rate.above_band": 0.9833748960931006,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01662510390689942
    },
    {
      "epoch": 0.4114029255319149,
      "grad_norm": 123.10377028336032,
      "learning_rate": 1.9656341548477602e-07,
      "loss": 0.6356,
      "step": 2475,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42203742203742206,
      "success_rate.epoch.env.math": 0.8588640275387264,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.683153588694682,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4820360717375074,
      "success_rate.epoch.global": 0.6370813397129187,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9889914772727273,
      "tokens_p.mean_in_band": 0.75453125,
      "tokens_rate.above_band": 0.8756218905472637,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12437810945273632
    },
    {
      "epoch": 0.4122340425531915,
      "grad_norm": 92.46562463980615,
      "learning_rate": 1.9654846747946509e-07,
      "loss": 0.6101,
      "step": 2480,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.4244306418219462,
      "success_rate.epoch.env.math": 0.8591065292096219,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.6831352154531947,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48274384952956634,
      "success_rate.epoch.global": 0.6374492476713638,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.4,
      "success_rate.window.env_macro_mean": 0.85,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9932278067885117,
      "tokens_p.mean_in_band": 0.6555059523809523,
      "tokens_rate.above_band": 0.948019801980198,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05198019801980198
    },
    {
      "epoch": 0.4130651595744681,
      "grad_norm": 196.18699160321822,
      "learning_rate": 1.9653349010467856e-07,
      "loss": 0.5627,
      "step": 2485,
      "success_rate.epoch.env.abd": 0.48,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.4244306418219462,
      "success_rate.epoch.env.math": 0.8591065292096219,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.683839881393625,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4847776070393024,
      "success_rate.epoch.global": 0.6380543633762518,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9776011560693642,
      "tokens_p.mean_in_band": 0.75390625,
      "tokens_rate.above_band": 0.8398058252427184,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16019417475728157
    },
    {
      "epoch": 0.4138962765957447,
      "grad_norm": 144.46116431404732,
      "learning_rate": 1.9651848338699765e-07,
      "loss": 0.7585,
      "step": 2490,
      "success_rate.epoch.env.abd": 0.48,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.4256198347107438,
      "success_rate.epoch.env.math": 0.8598290598290599,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.6843079200592154,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4849939490551048,
      "success_rate.epoch.global": 0.6387434554973822,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9893382352941177,
      "tokens_p.mean_in_band": 0.6808712121212122,
      "tokens_rate.above_band": 0.8854166666666666,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11458333333333333
    },
    {
      "epoch": 0.41472739361702127,
      "grad_norm": 135.361212760332,
      "learning_rate": 1.9650344735305554e-07,
      "loss": 0.7252,
      "step": 2495,
      "success_rate.epoch.env.abd": 0.48,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.4247422680412371,
      "success_rate.epoch.env.math": 0.8600682593856656,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.6845216106390839,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48495534209755636,
      "success_rate.epoch.global": 0.6388690900451414,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9995639534883721,
      "tokens_p.mean_in_band": 0.5611979166666666,
      "tokens_rate.above_band": 0.9388646288209607,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0611353711790393
    },
    {
      "epoch": 0.41555851063829785,
      "grad_norm": 105.40935994278132,
      "learning_rate": 1.9648838202953754e-07,
      "loss": 0.7333,
      "step": 2500,
      "success_rate.epoch.env.abd": 0.48,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.42505133470225875,
      "success_rate.epoch.env.math": 0.8603066439522998,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.6851032448377581,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4850579862272228,
      "success_rate.epoch.global": 0.6393170500355703,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9994989067055393,
      "tokens_p.mean_in_band": 0.6082261029411765,
      "tokens_rate.above_band": 0.9758179231863442,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02418207681365576
    },
    {
      "epoch": 0.4163896276595745,
      "grad_norm": 99.93998301250781,
      "learning_rate": 1.9647328744318092e-07,
      "loss": 0.8724,
      "step": 2505,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.42505133470225875,
      "success_rate.epoch.env.math": 0.8603066439522998,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.6853146853146853,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4864729840299921,
      "success_rate.epoch.global": 0.6394412878787878,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.3666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9899129746835443,
      "tokens_p.mean_in_band": 0.5807904411764706,
      "tokens_rate.above_band": 0.8229166666666666,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17708333333333334
    },
    {
      "epoch": 0.4172207446808511,
      "grad_norm": 122.93054612066635,
      "learning_rate": 1.9645816362077486e-07,
      "loss": 0.6416,
      "step": 2510,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.42505133470225875,
      "success_rate.epoch.env.math": 0.8607809847198642,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.6858927259368112,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4865686550654185,
      "success_rate.epoch.global": 0.6400378161191208,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.98675,
      "tokens_p.mean_in_band": 0.75048828125,
      "tokens_rate.above_band": 0.8389261744966443,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1610738255033557
    },
    {
      "epoch": 0.41805186170212766,
      "grad_norm": 115.9545692365525,
      "learning_rate": 1.9644301058916043e-07,
      "loss": 0.606,
      "step": 2515,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.4262295081967213,
      "success_rate.epoch.env.math": 0.8610169491525423,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6858715596330275,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4862350801928059,
      "success_rate.epoch.global": 0.6399244926852289,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.52,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.986927599009901,
      "tokens_p.mean_below_band": 8.003553375601768e-11,
      "tokens_p.mean_in_band": 0.6374438622754491,
      "tokens_rate.above_band": 0.8278688524590164,
      "tokens_rate.below_band": 0.0010245901639344263,
      "tokens_rate.in_band": 0.1711065573770492
    },
    {
      "epoch": 0.41888297872340424,
      "grad_norm": 111.80414903331769,
      "learning_rate": 1.9642782837523057e-07,
      "loss": 0.8307,
      "step": 2520,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.4262295081967213,
      "success_rate.epoch.env.math": 0.8612521150592216,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6860805860805861,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4862754613159185,
      "success_rate.epoch.global": 0.6401979264844486,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9907608695652174,
      "tokens_p.mean_in_band": 0.6021535773026315,
      "tokens_rate.above_band": 0.8194774346793349,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18052256532066507
    },
    {
      "epoch": 0.4197140957446808,
      "grad_norm": 111.2901167045314,
      "learning_rate": 1.9641261700592996e-07,
      "loss": 0.6871,
      "step": 2525,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.4262295081967213,
      "success_rate.epoch.env.math": 0.8614864864864865,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6864251738016831,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4846445922822678,
      "success_rate.epoch.global": 0.6403859731701577,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7666666666666667,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9832554517133957,
      "tokens_p.mean_in_band": 0.5588900862068965,
      "tokens_rate.above_band": 0.6888412017167382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.3111587982832618
    },
    {
      "epoch": 0.42054521276595747,
      "grad_norm": 206.2463598646136,
      "learning_rate": 1.9639737650825513e-07,
      "loss": 0.625,
      "step": 2530,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.42276422764227645,
      "success_rate.epoch.env.math": 0.8617200674536256,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6867690058479532,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48438205886944635,
      "success_rate.epoch.global": 0.6401221517500587,
      "success_rate.window.env.logic": 0.2,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.55,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9980053191489362,
      "tokens_p.mean_in_band": 0.5351004464285715,
      "tokens_rate.above_band": 0.9622844827586207,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03771551724137931
    },
    {
      "epoch": 0.42137632978723405,
      "grad_norm": 125.83773121134948,
      "learning_rate": 1.9638210690925411e-07,
      "loss": 0.6364,
      "step": 2535,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.42276422764227645,
      "success_rate.epoch.env.math": 0.8617200674536256,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6865889212827988,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48436568754534143,
      "success_rate.epoch.global": 0.6400937866354045,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9952536962365591,
      "tokens_p.mean_in_band": 0.6362060546875,
      "tokens_rate.above_band": 0.9489795918367347,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05102040816326531
    },
    {
      "epoch": 0.42220744680851063,
      "grad_norm": 114.1143029733693,
      "learning_rate": 1.9636680823602678e-07,
      "loss": 0.7121,
      "step": 2540,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.4251012145748988,
      "success_rate.epoch.env.math": 0.8617200674536256,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6870451237263464,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48461961385226604,
      "success_rate.epoch.global": 0.6405993912432686,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9968184389140271,
      "tokens_p.mean_in_band": 0.6865234375,
      "tokens_rate.above_band": 0.9910313901345291,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008968609865470852
    },
    {
      "epoch": 0.4230385638297872,
      "grad_norm": 157.6008947199477,
      "learning_rate": 1.963514805157245e-07,
      "loss": 0.712,
      "step": 2545,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.42655935613682094,
      "success_rate.epoch.env.math": 0.8617200674536256,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.6877269426289034,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4848141557126732,
      "success_rate.epoch.global": 0.6411214953271028,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9939077840112202,
      "tokens_p.mean_in_band": 0.5619255514705882,
      "tokens_rate.above_band": 0.9544846050870147,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04551539491298527
    },
    {
      "epoch": 0.42386968085106386,
      "grad_norm": 195.14534445210265,
      "learning_rate": 1.963361237755503e-07,
      "loss": 0.9004,
      "step": 2550,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.42655935613682094,
      "success_rate.epoch.env.math": 0.8619528619528619,
      "success_rate.epoch.env.sat": 0.0893854748603352,
      "success_rate.epoch.env.science": 0.6876811594202898,
      "success_rate.epoch.env.webshop": 0.2,
      "success_rate.epoch.env_macro_mean": 0.48024005077644777,
      "success_rate.epoch.global": 0.6409419445092096,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9908823529411764,
      "tokens_p.mean_in_band": 0.6134717987804879,
      "tokens_rate.above_band": 0.8382642998027613,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16173570019723865
    },
    {
      "epoch": 0.42470079787234044,
      "grad_norm": 88.0994800677281,
      "learning_rate": 1.9632073804275852e-07,
      "loss": 0.6849,
      "step": 2555,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.42655935613682094,
      "success_rate.epoch.env.math": 0.8626465661641541,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.6871832005792904,
      "success_rate.epoch.env.webshop": 0.2,
      "success_rate.epoch.env_macro_mean": 0.4802127016308883,
      "success_rate.epoch.global": 0.6407450523864959,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9966397849462365,
      "tokens_p.mean_in_band": 0.5589297715053764,
      "tokens_rate.above_band": 0.9285714285714286,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07142857142857142
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 180.6289842904881,
      "learning_rate": 1.9630532334465513e-07,
      "loss": 0.7542,
      "step": 2560,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.42570281124497994,
      "success_rate.epoch.env.math": 0.8626465661641541,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.6878612716763006,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4776515163620584,
      "success_rate.epoch.global": 0.6410315985130112,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942334254143647,
      "tokens_p.mean_in_band": 0.5959256329113924,
      "tokens_rate.above_band": 0.9197154471544715,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08028455284552846
    },
    {
      "epoch": 0.4263630319148936,
      "grad_norm": 200.18281108651172,
      "learning_rate": 1.962898797085974e-07,
      "loss": 0.6978,
      "step": 2565,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.4248496993987976,
      "success_rate.epoch.env.math": 0.8626465661641541,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.6886486486486486,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47764554046443713,
      "success_rate.epoch.global": 0.641465677179963,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9985665137614679,
      "tokens_p.mean_in_band": 0.5060975609756098,
      "tokens_rate.above_band": 0.9410071942446043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.058992805755395686
    },
    {
      "epoch": 0.4271941489361702,
      "grad_norm": 84.51137493470681,
      "learning_rate": 1.9627440716199404e-07,
      "loss": 0.6582,
      "step": 2570,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.4248496993987976,
      "success_rate.epoch.env.math": 0.862876254180602,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.6892086330935252,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47771732887001206,
      "success_rate.epoch.global": 0.6419638721630384,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9918981481481481,
      "tokens_p.mean_in_band": 0.7374131944444444,
      "tokens_rate.above_band": 0.8823529411764706,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11764705882352941
    },
    {
      "epoch": 0.42802526595744683,
      "grad_norm": 144.80915410834996,
      "learning_rate": 1.9625890573230504e-07,
      "loss": 0.6578,
      "step": 2575,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.426,
      "success_rate.epoch.env.math": 0.8631051752921536,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.6890726096333573,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4782879617152301,
      "success_rate.epoch.global": 0.642146657413833,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9919354838709677,
      "tokens_p.mean_below_band": 1.4915713109076023e-10,
      "tokens_p.mean_in_band": 0.7178485576923077,
      "tokens_rate.above_band": 0.9465648854961832,
      "tokens_rate.below_band": 0.003816793893129771,
      "tokens_rate.in_band": 0.04961832061068702
    },
    {
      "epoch": 0.4288563829787234,
      "grad_norm": 232.37504892155536,
      "learning_rate": 1.962433754470416e-07,
      "loss": 0.7746,
      "step": 2580,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.42714570858283435,
      "success_rate.epoch.env.math": 0.8631051752921536,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.6892716182274847,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47841020873131757,
      "success_rate.epoch.global": 0.6424116424116424,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9893558951965066,
      "tokens_p.mean_in_band": 0.5439453125,
      "tokens_rate.above_band": 0.9196787148594378,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08032128514056225
    },
    {
      "epoch": 0.4296875,
      "grad_norm": 171.0714537781909,
      "learning_rate": 1.9622781633376618e-07,
      "loss": 0.6078,
      "step": 2585,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.42714570858283435,
      "success_rate.epoch.env.math": 0.8635607321131448,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.6891117478510028,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47843708931718204,
      "success_rate.epoch.global": 0.6425276752767528,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.8125,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.98575,
      "tokens_p.mean_in_band": 0.7235753676470589,
      "tokens_rate.above_band": 0.8802816901408451,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11971830985915492
    },
    {
      "epoch": 0.4305186170212766,
      "grad_norm": 155.40530701835368,
      "learning_rate": 1.9621222842009239e-07,
      "loss": 0.7472,
      "step": 2590,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4563106796116505,
      "success_rate.epoch.env.logic": 0.4262948207171315,
      "success_rate.epoch.env.math": 0.8642384105960265,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.6891988555078684,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4780225678772006,
      "success_rate.epoch.global": 0.6425776754890679,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.35,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9979628791308285,
      "tokens_p.mean_in_band": 0.5255033052884616,
      "tokens_rate.above_band": 0.9550367488110679,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04496325118893212
    },
    {
      "epoch": 0.43134973404255317,
      "grad_norm": 169.74785476797277,
      "learning_rate": 1.96196611733685e-07,
      "loss": 0.7638,
      "step": 2595,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4074074074074074,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4262948207171315,
      "success_rate.epoch.env.math": 0.8646864686468647,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.6895074946466809,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47769248555911675,
      "success_rate.epoch.global": 0.6428571428571429,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_in_band": 0.6973711993243243,
      "tokens_rate.above_band": 0.8010752688172043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1989247311827957
    },
    {
      "epoch": 0.4321808510638298,
      "grad_norm": 85.2886067688039,
      "learning_rate": 1.9618096630225975e-07,
      "loss": 0.6345,
      "step": 2600,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.41284403669724773,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4262948207171315,
      "success_rate.epoch.env.math": 0.8651315789473685,
      "success_rate.epoch.env.sat": 0.09340659340659341,
      "success_rate.epoch.env.science": 0.6892373485388453,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47815571600960766,
      "success_rate.epoch.global": 0.6428243924805135,
      "success_rate.window.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.997536496350365,
      "tokens_p.mean_in_band": 0.5894191576086957,
      "tokens_rate.above_band": 0.9370725034199726,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06292749658002736
    },
    {
      "epoch": 0.4330119680851064,
      "grad_norm": 940.218283032904,
      "learning_rate": 1.961652921535835e-07,
      "loss": 0.8205,
      "step": 2605,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.41818181818181815,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4262948207171315,
      "success_rate.epoch.env.math": 0.8637110016420362,
      "success_rate.epoch.env.sat": 0.09340659340659341,
      "success_rate.epoch.env.science": 0.6901208244491827,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47859214147229634,
      "success_rate.epoch.global": 0.6434126258005489,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9946395985401459,
      "tokens_p.mean_in_band": 0.7077414772727273,
      "tokens_rate.above_band": 0.9614035087719298,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03859649122807018
    },
    {
      "epoch": 0.433843085106383,
      "grad_norm": 118.2766197085642,
      "learning_rate": 1.9614958931547396e-07,
      "loss": 0.8494,
      "step": 2610,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4274353876739563,
      "success_rate.epoch.env.math": 0.8641571194762684,
      "success_rate.epoch.env.sat": 0.09340659340659341,
      "success_rate.epoch.env.science": 0.6896062433487052,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4783471141925851,
      "success_rate.epoch.global": 0.6432321387811002,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9966322055137845,
      "tokens_p.mean_in_band": 0.49400111607142855,
      "tokens_rate.above_band": 0.9661016949152542,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03389830508474576
    },
    {
      "epoch": 0.43467420212765956,
      "grad_norm": 171.50132031955368,
      "learning_rate": 1.9613385781579986e-07,
      "loss": 0.7923,
      "step": 2615,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4274353876739563,
      "success_rate.epoch.env.math": 0.8643790849673203,
      "success_rate.epoch.env.sat": 0.09289617486338798,
      "success_rate.epoch.env.science": 0.6900212314225053,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4783586173763711,
      "success_rate.epoch.global": 0.643507972665148,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9893973214285714,
      "tokens_p.mean_in_band": 0.6875,
      "tokens_rate.above_band": 0.8936170212765957,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10638297872340426
    },
    {
      "epoch": 0.43550531914893614,
      "grad_norm": 290.17082193721075,
      "learning_rate": 1.9611809768248077e-07,
      "loss": 0.7404,
      "step": 2620,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4274353876739563,
      "success_rate.epoch.env.math": 0.8648208469055375,
      "success_rate.epoch.env.sat": 0.09289617486338798,
      "success_rate.epoch.env.science": 0.690081186021885,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4784042279706981,
      "success_rate.epoch.global": 0.6437826778813367,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9871608527131783,
      "tokens_p.mean_in_band": 0.64044189453125,
      "tokens_rate.above_band": 0.8896551724137931,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1103448275862069
    },
    {
      "epoch": 0.4363364361702128,
      "grad_norm": 100.94327819444389,
      "learning_rate": 1.9610230894348705e-07,
      "loss": 0.7111,
      "step": 2625,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4274353876739563,
      "success_rate.epoch.env.math": 0.8648208469055375,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.6902748414376322,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4783759356888968,
      "success_rate.epoch.global": 0.6438138479001135,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9891902515723271,
      "tokens_p.mean_below_band": 2.1047890186309814e-07,
      "tokens_p.mean_in_band": 0.6842041015625,
      "tokens_rate.above_band": 0.828125,
      "tokens_rate.below_band": 0.005208333333333333,
      "tokens_rate.in_band": 0.16666666666666666
    },
    {
      "epoch": 0.43716755319148937,
      "grad_norm": 107.18524915131678,
      "learning_rate": 1.9608649162683986e-07,
      "loss": 0.7372,
      "step": 2630,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42658730158730157,
      "success_rate.epoch.env.math": 0.8648208469055375,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.6904929577464789,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47831866570909604,
      "success_rate.epoch.global": 0.6438294010889292,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9954336086404066,
      "tokens_p.mean_in_band": 0.6334134615384616,
      "tokens_rate.above_band": 0.9308101714961561,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06918982850384388
    },
    {
      "epoch": 0.43799867021276595,
      "grad_norm": 99.61762381290823,
      "learning_rate": 1.9607064576061101e-07,
      "loss": 0.6751,
      "step": 2635,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.424901185770751,
      "success_rate.epoch.env.math": 0.8648208469055375,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.6912539515279241,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47823456370590467,
      "success_rate.epoch.global": 0.6441023318994793,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9995022753128555,
      "tokens_p.mean_in_band": 0.6292410714285714,
      "tokens_rate.above_band": 0.9617067833698031,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038293216630196934
    },
    {
      "epoch": 0.43882978723404253,
      "grad_norm": 158.99937759046935,
      "learning_rate": 1.9605477137292307e-07,
      "loss": 0.5855,
      "step": 2640,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4251968503937008,
      "success_rate.epoch.env.math": 0.8654781199351702,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.6915789473684211,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4783507394780028,
      "success_rate.epoch.global": 0.6445197740112995,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9983057228915663,
      "tokens_p.mean_in_band": 0.5705818965517241,
      "tokens_rate.above_band": 0.9581529581529582,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04184704184704185
    },
    {
      "epoch": 0.4396609042553192,
      "grad_norm": 94.26411185425887,
      "learning_rate": 1.960388684919492e-07,
      "loss": 0.452,
      "step": 2645,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4251968503937008,
      "success_rate.epoch.env.math": 0.8654781199351702,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.691768826619965,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4783680012281431,
      "success_rate.epoch.global": 0.6446952595936795,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981278801843319,
      "tokens_p.mean_in_band": 0.5857558139534884,
      "tokens_rate.above_band": 0.9380403458213257,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06195965417867435
    },
    {
      "epoch": 0.44049202127659576,
      "grad_norm": 120.37472559932553,
      "learning_rate": 1.960229371459131e-07,
      "loss": 0.5471,
      "step": 2650,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4263261296660118,
      "success_rate.epoch.env.math": 0.8659127625201939,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.6922000699545295,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4785039787495945,
      "success_rate.epoch.global": 0.6451104100946372,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9899017467248908,
      "tokens_p.mean_in_band": 0.7038762019230769,
      "tokens_rate.above_band": 0.8980392156862745,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10196078431372549
    },
    {
      "epoch": 0.44132313829787234,
      "grad_norm": 176.44776534657888,
      "learning_rate": 1.9600697736308897e-07,
      "loss": 0.7269,
      "step": 2655,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42661448140900193,
      "success_rate.epoch.env.math": 0.8661290322580645,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.6926301082780301,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47858894782271827,
      "success_rate.epoch.global": 0.6454443194600675,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978433694181326,
      "tokens_p.mean_in_band": 0.6870404411764706,
      "tokens_rate.above_band": 0.9560155239327296,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04398447606727038
    },
    {
      "epoch": 0.4421542553191489,
      "grad_norm": 106.6329495832436,
      "learning_rate": 1.9599098917180159e-07,
      "loss": 0.605,
      "step": 2660,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42661448140900193,
      "success_rate.epoch.env.math": 0.8663446054750402,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.6925758103868944,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4786036092159764,
      "success_rate.epoch.global": 0.6455525606469003,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9872159090909091,
      "tokens_p.mean_below_band": 1.7229467630386353e-08,
      "tokens_p.mean_in_band": 0.6243106617647058,
      "tokens_rate.above_band": 0.859375,
      "tokens_rate.below_band": 0.0078125,
      "tokens_rate.in_band": 0.1328125
    },
    {
      "epoch": 0.4429853723404255,
      "grad_norm": 130.92137917278285,
      "learning_rate": 1.9597497260042604e-07,
      "loss": 0.6431,
      "step": 2665,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4249512670565302,
      "success_rate.epoch.env.math": 0.8665594855305466,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.6928695652173913,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4784986474462975,
      "success_rate.epoch.global": 0.6455951580363147,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9974032951289399,
      "tokens_p.mean_in_band": 0.5996492346938775,
      "tokens_rate.above_band": 0.9344042838018741,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06559571619812583
    },
    {
      "epoch": 0.44381648936170215,
      "grad_norm": 245.77192990999285,
      "learning_rate": 1.9595892767738783e-07,
      "loss": 0.6653,
      "step": 2670,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42412451361867703,
      "success_rate.epoch.env.math": 0.8665594855305466,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.6929215822345594,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47842821686259884,
      "success_rate.epoch.global": 0.6455582904452898,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977756709451575,
      "tokens_p.mean_in_band": 0.6217105263157895,
      "tokens_rate.above_band": 0.9575418994413408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.042458100558659215
    },
    {
      "epoch": 0.44464760638297873,
      "grad_norm": 163.566667138646,
      "learning_rate": 1.9594285443116272e-07,
      "loss": 0.7178,
      "step": 2675,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42330097087378643,
      "success_rate.epoch.env.math": 0.8665594855305466,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.6936656282450675,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4784209898867459,
      "success_rate.epoch.global": 0.6459682823319187,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9950443097014925,
      "tokens_p.mean_in_band": 0.6382637593283582,
      "tokens_rate.above_band": 0.8888888888888888,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1111111111111111
    },
    {
      "epoch": 0.4454787234042553,
      "grad_norm": 142.7759695604499,
      "learning_rate": 1.9592675289027682e-07,
      "loss": 1.0158,
      "step": 2680,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4144144144144144,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42359767891682787,
      "success_rate.epoch.env.math": 0.8672,
      "success_rate.epoch.env.sat": 0.0913978494623656,
      "success_rate.epoch.env.science": 0.6938775510204082,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4784805446920467,
      "success_rate.epoch.global": 0.6461538461538462,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975429975429976,
      "tokens_p.mean_in_band": 0.6613932291666667,
      "tokens_rate.above_band": 0.931350114416476,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06864988558352403
    },
    {
      "epoch": 0.4463098404255319,
      "grad_norm": 107.37520687521967,
      "learning_rate": 1.9591062308330643e-07,
      "loss": 0.6829,
      "step": 2685,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4107142857142857,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42359767891682787,
      "success_rate.epoch.env.math": 0.8676236044657097,
      "success_rate.epoch.env.sat": 0.0913978494623656,
      "success_rate.epoch.env.science": 0.6941948859709745,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47821152748442375,
      "success_rate.epoch.global": 0.6464039189490092,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9964454976303317,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.7283653846153846,
      "tokens_rate.above_band": 0.9690011481056258,
      "tokens_rate.below_band": 0.001148105625717566,
      "tokens_rate.in_band": 0.029850746268656716
    },
    {
      "epoch": 0.4471409574468085,
      "grad_norm": 99.35581540618682,
      "learning_rate": 1.95894465038878e-07,
      "loss": 0.6909,
      "step": 2690,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4107142857142857,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42359767891682787,
      "success_rate.epoch.env.math": 0.8680445151033387,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.694271911663216,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4782123618277506,
      "success_rate.epoch.global": 0.6465095598043575,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9974798387096774,
      "tokens_p.mean_in_band": 0.5875,
      "tokens_rate.above_band": 0.9316939890710383,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06830601092896176
    },
    {
      "epoch": 0.4479720744680851,
      "grad_norm": 146.93546651455324,
      "learning_rate": 1.958782787856681e-07,
      "loss": 0.7674,
      "step": 2695,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40707964601769914,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.4247104247104247,
      "success_rate.epoch.env.math": 0.8680445151033387,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.694032424974129,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4783548730765623,
      "success_rate.epoch.global": 0.6462358427714857,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.3,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9994692144373672,
      "tokens_p.mean_in_band": 0.5468394886363637,
      "tokens_rate.above_band": 0.9448345035105316,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.055165496489468405
    },
    {
      "epoch": 0.4488031914893617,
      "grad_norm": 169.7037098961248,
      "learning_rate": 1.9586206435240332e-07,
      "loss": 0.7134,
      "step": 2700,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.425,
      "success_rate.epoch.env.math": 0.8680445151033387,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.6943487250172296,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4780853277351806,
      "success_rate.epoch.global": 0.6462630294965624,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9954613590939374,
      "tokens_p.mean_in_band": 0.5613779920212766,
      "tokens_rate.above_band": 0.9696382428940569,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030361757105943153
    },
    {
      "epoch": 0.4496343085106383,
      "grad_norm": 93.71172162719347,
      "learning_rate": 1.9584582176786039e-07,
      "loss": 0.576,
      "step": 2705,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.42610364683301344,
      "success_rate.epoch.env.math": 0.8682539682539683,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.6946354883081155,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47823076985104684,
      "success_rate.epoch.global": 0.6466681425725038,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9904233870967742,
      "tokens_p.mean_in_band": 0.6768973214285714,
      "tokens_rate.above_band": 0.9637305699481865,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03626943005181347
    },
    {
      "epoch": 0.4504654255319149,
      "grad_norm": 97.88861330585847,
      "learning_rate": 1.9582955106086584e-07,
      "loss": 0.6309,
      "step": 2710,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.42610364683301344,
      "success_rate.epoch.env.math": 0.8686708860759493,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.695054945054945,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4787813293772824,
      "success_rate.epoch.global": 0.6472148541114059,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9957495564754583,
      "tokens_p.mean_below_band": 2.6659108698368073e-08,
      "tokens_p.mean_in_band": 0.7765299479166666,
      "tokens_rate.above_band": 0.9917888563049854,
      "tokens_rate.below_band": 0.0011730205278592375,
      "tokens_rate.in_band": 0.007038123167155425
    },
    {
      "epoch": 0.4512965425531915,
      "grad_norm": 279.2356921464699,
      "learning_rate": 1.9581325226029624e-07,
      "loss": 0.7458,
      "step": 2715,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.42610364683301344,
      "success_rate.epoch.env.math": 0.8686708860759493,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.6953392734749828,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47880717741546763,
      "success_rate.epoch.global": 0.6474613686534216,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9769736842105263,
      "tokens_p.mean_below_band": 1.9190338207408786e-10,
      "tokens_p.mean_in_band": 0.49556107954545453,
      "tokens_rate.above_band": 0.8172043010752689,
      "tokens_rate.below_band": 0.005376344086021506,
      "tokens_rate.in_band": 0.1774193548387097
    },
    {
      "epoch": 0.4521276595744681,
      "grad_norm": 87.13322919789367,
      "learning_rate": 1.9579692539507793e-07,
      "loss": 0.6673,
      "step": 2720,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.42610364683301344,
      "success_rate.epoch.env.math": 0.8686708860759493,
      "success_rate.epoch.env.sat": 0.09473684210526316,
      "success_rate.epoch.env.science": 0.6955183031132398,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4787778843705062,
      "success_rate.epoch.global": 0.6474867724867724,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942528735632183,
      "tokens_p.mean_in_band": 0.7026452850877193,
      "tokens_rate.above_band": 0.7532467532467533,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.24675324675324675
    },
    {
      "epoch": 0.4529587765957447,
      "grad_norm": 163.96541388755767,
      "learning_rate": 1.9578057049418716e-07,
      "loss": 0.6901,
      "step": 2725,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.42610364683301344,
      "success_rate.epoch.env.math": 0.8690851735015773,
      "success_rate.epoch.env.sat": 0.09473684210526316,
      "success_rate.epoch.env.science": 0.6960382513661202,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47886281488673427,
      "success_rate.epoch.global": 0.6480299361655294,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9923986486486487,
      "tokens_p.mean_in_band": 0.7625679347826086,
      "tokens_rate.above_band": 0.9061224489795918,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09387755102040816
    },
    {
      "epoch": 0.45378989361702127,
      "grad_norm": 159.28682834799423,
      "learning_rate": 1.9576418758664977e-07,
      "loss": 0.6946,
      "step": 2730,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.4272030651340996,
      "success_rate.epoch.env.math": 0.8690851735015773,
      "success_rate.epoch.env.sat": 0.09473684210526316,
      "success_rate.epoch.env.science": 0.6964529331514324,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4786083995797148,
      "success_rate.epoch.global": 0.6482743460101121,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9918681210691824,
      "tokens_p.mean_in_band": 0.5435842041800643,
      "tokens_rate.above_band": 0.8035375868603917,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19646241313960833
    },
    {
      "epoch": 0.45462101063829785,
      "grad_norm": 99.10923879794716,
      "learning_rate": 1.957477767015415e-07,
      "loss": 0.5883,
      "step": 2735,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.42638623326959846,
      "success_rate.epoch.env.math": 0.8690851735015773,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6965258855585831,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4789159463971499,
      "success_rate.epoch.global": 0.6480140443274084,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.993332262210797,
      "tokens_p.mean_in_band": 0.6842830882352942,
      "tokens_rate.above_band": 0.884090909090909,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1159090909090909
    },
    {
      "epoch": 0.4554521276595745,
      "grad_norm": 176.25272954306467,
      "learning_rate": 1.957313378679876e-07,
      "loss": 0.7942,
      "step": 2740,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.42638623326959846,
      "success_rate.epoch.env.math": 0.8692913385826772,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6971447994561523,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.478990953577029,
      "success_rate.epoch.global": 0.6485539000876425,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.987060546875,
      "tokens_p.mean_in_band": 0.7219122023809523,
      "tokens_rate.above_band": 0.8590604026845637,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14093959731543623
    },
    {
      "epoch": 0.4562832446808511,
      "grad_norm": 140.18723055648027,
      "learning_rate": 1.9571487111516298e-07,
      "loss": 0.578,
      "step": 2745,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.42638623326959846,
      "success_rate.epoch.env.math": 0.8701095461658842,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6976586359009161,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4791120484886627,
      "success_rate.epoch.global": 0.6492455718346818,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9842479674796748,
      "tokens_p.mean_in_band": 0.73984375,
      "tokens_rate.above_band": 0.924812030075188,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07518796992481203
    },
    {
      "epoch": 0.45711436170212766,
      "grad_norm": 106.34718611030647,
      "learning_rate": 1.9569837647229212e-07,
      "loss": 0.6392,
      "step": 2750,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4537037037037037,
      "success_rate.epoch.env.logic": 0.42638623326959846,
      "success_rate.epoch.env.math": 0.8705148205928237,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.698170731707317,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4788099710980626,
      "success_rate.epoch.global": 0.6496398166339227,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.989195865161076,
      "tokens_p.mean_below_band": 4.4517219066619873e-07,
      "tokens_p.mean_in_band": 0.49621433985667035,
      "tokens_rate.above_band": 0.7683082418984435,
      "tokens_rate.below_band": 0.00025516713447307985,
      "tokens_rate.in_band": 0.23143659096708344
    },
    {
      "epoch": 0.45794547872340424,
      "grad_norm": 147.32985372023418,
      "learning_rate": 1.9568185396864895e-07,
      "loss": 0.6131,
      "step": 2755,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4537037037037037,
      "success_rate.epoch.env.logic": 0.42638623326959846,
      "success_rate.epoch.env.math": 0.8709175738724728,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.698477157360406,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4788744419101297,
      "success_rate.epoch.global": 0.6500218054949848,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958029935275081,
      "tokens_p.mean_in_band": 0.6401599702380952,
      "tokens_rate.above_band": 0.9363636363636364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06363636363636363
    },
    {
      "epoch": 0.4587765957446808,
      "grad_norm": 93.31939097639189,
      "learning_rate": 1.9566530363355683e-07,
      "loss": 0.6203,
      "step": 2760,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45871559633027525,
      "success_rate.epoch.env.logic": 0.42638623326959846,
      "success_rate.epoch.env.math": 0.8711180124223602,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6986810957051065,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4793668300484169,
      "success_rate.epoch.global": 0.6503267973856209,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967914908579466,
      "tokens_p.mean_in_band": 0.2386384587020649,
      "tokens_rate.above_band": 0.807495741056218,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19250425894378195
    },
    {
      "epoch": 0.45960771276595747,
      "grad_norm": 153.5048217257842,
      "learning_rate": 1.9564872549638864e-07,
      "loss": 0.7348,
      "step": 2765,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45871559633027525,
      "success_rate.epoch.env.logic": 0.4269449715370019,
      "success_rate.epoch.env.math": 0.8713178294573644,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6986486486486486,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47943283988895774,
      "success_rate.epoch.global": 0.6502827316224445,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9956165158371041,
      "tokens_p.mean_in_band": 0.619140625,
      "tokens_rate.above_band": 0.9525862068965517,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04741379310344827
    },
    {
      "epoch": 0.46043882978723405,
      "grad_norm": 81.5352851126888,
      "learning_rate": 1.9563211958656642e-07,
      "loss": 0.6267,
      "step": 2770,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.4269449715370019,
      "success_rate.epoch.env.math": 0.8713178294573644,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.699055330634278,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4790907071799404,
      "success_rate.epoch.global": 0.650445361720617,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9939828026434364,
      "tokens_p.mean_below_band": 3.265837828318278e-07,
      "tokens_p.mean_in_band": 0.4922722649186257,
      "tokens_rate.above_band": 0.8568854568854569,
      "tokens_rate.below_band": 0.0007722007722007722,
      "tokens_rate.in_band": 0.14234234234234233
    },
    {
      "epoch": 0.46126994680851063,
      "grad_norm": 87.01980633304194,
      "learning_rate": 1.9561548593356166e-07,
      "loss": 0.7436,
      "step": 2775,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.40350877192982454,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.4269449715370019,
      "success_rate.epoch.env.math": 0.871517027863777,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6995621421353991,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47915488989880706,
      "success_rate.epoch.global": 0.6509004122369277,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.998675431711146,
      "tokens_p.mean_in_band": 0.6654146634615384,
      "tokens_rate.above_band": 0.9607843137254902,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0392156862745098
    },
    {
      "epoch": 0.4621010638297872,
      "grad_norm": 121.68498038729926,
      "learning_rate": 1.9559882456689496e-07,
      "loss": 0.8066,
      "step": 2780,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.42613636363636365,
      "success_rate.epoch.env.math": 0.8719135802469136,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.6998654104979811,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47882602089110304,
      "success_rate.epoch.global": 0.6509965337954939,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.35,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9970794392523364,
      "tokens_p.mean_in_band": 0.5094992897727273,
      "tokens_rate.above_band": 0.9547014413177762,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.045298558682223745
    },
    {
      "epoch": 0.46293218085106386,
      "grad_norm": 96.6506725239863,
      "learning_rate": 1.9558213551613622e-07,
      "loss": 0.6055,
      "step": 2785,
      "success_rate.epoch.env.abd": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.42613636363636365,
      "success_rate.epoch.env.math": 0.8719135802469136,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.7002349781805975,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4788596179531591,
      "success_rate.epoch.global": 0.6513086740211984,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.98515625,
      "tokens_p.mean_below_band": 3.097966327914037e-12,
      "tokens_p.mean_in_band": 0.6627987132352942,
      "tokens_rate.above_band": 0.7741935483870968,
      "tokens_rate.below_band": 0.0064516129032258064,
      "tokens_rate.in_band": 0.21935483870967742
    },
    {
      "epoch": 0.46376329787234044,
      "grad_norm": 135.11375940372034,
      "learning_rate": 1.9556541881090437e-07,
      "loss": 0.624,
      "step": 2790,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.42722117202268434,
      "success_rate.epoch.env.math": 0.8719135802469136,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.7006369426751592,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48063412159898306,
      "success_rate.epoch.global": 0.6516198704103672,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942853009259259,
      "tokens_p.mean_in_band": 0.6832853618421053,
      "tokens_rate.above_band": 0.9578713968957872,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04212860310421286
    },
    {
      "epoch": 0.464594414893617,
      "grad_norm": 150.10775642762593,
      "learning_rate": 1.9554867448086747e-07,
      "loss": 0.6595,
      "step": 2795,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4051724137931034,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.42641509433962266,
      "success_rate.epoch.env.math": 0.8721109399075501,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.7004685408299867,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48103369377402905,
      "success_rate.epoch.global": 0.6515739542906425,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7916666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973897911832946,
      "tokens_p.mean_in_band": 0.49883497807017546,
      "tokens_rate.above_band": 0.9379760609357998,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.062023939064200215
    },
    {
      "epoch": 0.4654255319148936,
      "grad_norm": 172.64008702891334,
      "learning_rate": 1.9553190255574263e-07,
      "loss": 0.616,
      "step": 2800,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4051724137931034,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.4266917293233083,
      "success_rate.epoch.env.math": 0.8723076923076923,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.7006348145673238,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.481091844785044,
      "success_rate.epoch.global": 0.6517434352130865,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9911971830985915,
      "tokens_p.mean_in_band": 0.7157258064516129,
      "tokens_rate.above_band": 0.9015873015873016,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09841269841269841
    },
    {
      "epoch": 0.4662566489361702,
      "grad_norm": 105.32749578745384,
      "learning_rate": 1.955151030652959e-07,
      "loss": 0.5412,
      "step": 2805,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4051724137931034,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.4266917293233083,
      "success_rate.epoch.env.math": 0.8725038402457758,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.7009003001000333,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4807615383646612,
      "success_rate.epoch.global": 0.6519123334765793,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9906535388127854,
      "tokens_p.mean_below_band": 5.364418029785156e-07,
      "tokens_p.mean_in_band": 0.6409590871710527,
      "tokens_rate.above_band": 0.8513119533527697,
      "tokens_rate.below_band": 0.0009718172983479105,
      "tokens_rate.in_band": 0.1477162293488824
    },
    {
      "epoch": 0.46708776595744683,
      "grad_norm": 120.6877766221014,
      "learning_rate": 1.954982760393423e-07,
      "loss": 0.5028,
      "step": 2810,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4051724137931034,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.42696629213483145,
      "success_rate.epoch.env.math": 0.8726993865030674,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.7012987012987013,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4807967898844302,
      "success_rate.epoch.global": 0.6520806520806521,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0,
      "tokens_p.mean_in_band": 0.6525548986486487,
      "tokens_rate.above_band": 0.9529262086513995,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047073791348600506
    },
    {
      "epoch": 0.4679188829787234,
      "grad_norm": 200.7677967798599,
      "learning_rate": 1.9548142150774558e-07,
      "loss": 0.8387,
      "step": 2815,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.42696629213483145,
      "success_rate.epoch.env.math": 0.8726993865030674,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.7015619807244932,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4805059050973475,
      "success_rate.epoch.global": 0.6521739130434783,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.16666666666666669,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9935496794871795,
      "tokens_p.mean_in_band": 0.5873125700672646,
      "tokens_rate.above_band": 0.8749298934380259,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1250701065619742
    },
    {
      "epoch": 0.46875,
      "grad_norm": 158.43588397544846,
      "learning_rate": 1.9546453950041847e-07,
      "loss": 0.6887,
      "step": 2820,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.4280373831775701,
      "success_rate.epoch.env.math": 0.8728943338437979,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.701527224435591,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4806178398332172,
      "success_rate.epoch.global": 0.6523320496362859,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9926470588235294,
      "tokens_p.mean_in_band": 0.6404551630434783,
      "tokens_rate.above_band": 0.9057377049180327,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0942622950819672
    },
    {
      "epoch": 0.4695811170212766,
      "grad_norm": 120.2227106073086,
      "learning_rate": 1.954476300473224e-07,
      "loss": 0.6628,
      "step": 2825,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.4280373831775701,
      "success_rate.epoch.env.math": 0.8730886850152905,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.7016904209479615,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4802847188024886,
      "success_rate.epoch.global": 0.652424695577868,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942905211912944,
      "tokens_p.mean_below_band": 1.4371835277415812e-07,
      "tokens_p.mean_in_band": 0.5088764289264414,
      "tokens_rate.above_band": 0.8736552414310733,
      "tokens_rate.below_band": 0.0005003752814610958,
      "tokens_rate.in_band": 0.1258443832874656
    },
    {
      "epoch": 0.47041223404255317,
      "grad_norm": 76.35485117265553,
      "learning_rate": 1.954306931784675e-07,
      "loss": 0.8529,
      "step": 2830,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.4280373831775701,
      "success_rate.epoch.env.math": 0.8732824427480916,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.7018530774321642,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47870646626246244,
      "success_rate.epoch.global": 0.6523779057368309,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9876160990712074,
      "tokens_p.mean_below_band": 2.996789084540473e-07,
      "tokens_p.mean_in_band": 0.1055054440649018,
      "tokens_rate.above_band": 0.12079281974569933,
      "tokens_rate.below_band": 0.0033657442034405387,
      "tokens_rate.in_band": 0.8758414360508602
    },
    {
      "epoch": 0.4712433510638298,
      "grad_norm": 144.8206309987553,
      "learning_rate": 1.9541372892391251e-07,
      "loss": 0.8065,
      "step": 2835,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.42723880597014924,
      "success_rate.epoch.env.math": 0.8732824427480916,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.7021487603305785,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4786607485980073,
      "success_rate.epoch.global": 0.6524611122949073,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9999561095505618,
      "tokens_p.mean_in_band": 0.46010044642857145,
      "tokens_rate.above_band": 0.9442970822281167,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05570291777188329
    },
    {
      "epoch": 0.4720744680851064,
      "grad_norm": 165.1060233513649,
      "learning_rate": 1.9539673731376494e-07,
      "loss": 0.5386,
      "step": 2840,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.42723880597014924,
      "success_rate.epoch.env.math": 0.8736681887366818,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.7027383701748597,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4787494173100865,
      "success_rate.epoch.global": 0.6530525420123378,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.995,
      "tokens_p.mean_in_band": 0.7567471590909091,
      "tokens_rate.above_band": 0.9695290858725761,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030470914127423823
    },
    {
      "epoch": 0.472905585106383,
      "grad_norm": 170.13846986722578,
      "learning_rate": 1.9537971837818063e-07,
      "loss": 0.848,
      "step": 2845,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.42830540037243947,
      "success_rate.epoch.env.math": 0.8736681887366818,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.7030323005932761,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47887310138469613,
      "success_rate.epoch.global": 0.6533475026567481,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9978507565337001,
      "tokens_p.mean_in_band": 0.5649181547619048,
      "tokens_rate.above_band": 0.9453836150845254,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054616384915474644
    },
    {
      "epoch": 0.47373670212765956,
      "grad_norm": 242.3020452725528,
      "learning_rate": 1.9536267214736407e-07,
      "loss": 0.5517,
      "step": 2850,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.42830540037243947,
      "success_rate.epoch.env.math": 0.8738601823708206,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.703227931488801,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.478908339978302,
      "success_rate.epoch.global": 0.6535683942225998,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9847972972972973,
      "tokens_p.mean_below_band": 3.510081114654895e-12,
      "tokens_p.mean_in_band": 0.751171875,
      "tokens_rate.above_band": 0.8409090909090909,
      "tokens_rate.below_band": 0.007575757575757576,
      "tokens_rate.in_band": 0.15151515151515152
    },
    {
      "epoch": 0.47456781914893614,
      "grad_norm": 94.31219636240225,
      "learning_rate": 1.953455986515681e-07,
      "loss": 0.4852,
      "step": 2855,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.42936802973977695,
      "success_rate.epoch.env.math": 0.8742424242424243,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.7035208950312603,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47906632495842927,
      "success_rate.epoch.global": 0.6540093338990242,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.991243961352657,
      "tokens_p.mean_in_band": 0.7763671875,
      "tokens_rate.above_band": 0.9627906976744186,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037209302325581395
    },
    {
      "epoch": 0.4753989361702128,
      "grad_norm": 90.64235639072643,
      "learning_rate": 1.9532849792109408e-07,
      "loss": 0.6207,
      "step": 2860,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.42962962962962964,
      "success_rate.epoch.env.math": 0.8744326777609682,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.7036793692509855,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47912180928825854,
      "success_rate.epoch.global": 0.6541719610334604,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7111111111111111,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.996319018404908,
      "tokens_p.mean_in_band": 0.62421875,
      "tokens_rate.above_band": 0.9532163742690059,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04678362573099415
    },
    {
      "epoch": 0.47623005319148937,
      "grad_norm": 139.52553665825337,
      "learning_rate": 1.9531136998629155e-07,
      "loss": 0.589,
      "step": 2865,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43068391866913125,
      "success_rate.epoch.env.math": 0.8746223564954683,
      "success_rate.epoch.env.sat": 0.10152284263959391,
      "success_rate.epoch.env.science": 0.7038373237126927,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48008699770349583,
      "success_rate.epoch.global": 0.6546184738955824,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.825,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.991870777027027,
      "tokens_p.mean_below_band": 1.4435499906539917e-07,
      "tokens_p.mean_in_band": 0.6512784090909091,
      "tokens_rate.above_band": 0.961038961038961,
      "tokens_rate.below_band": 0.003246753246753247,
      "tokens_rate.in_band": 0.03571428571428571
    },
    {
      "epoch": 0.47706117021276595,
      "grad_norm": 84.48735718121672,
      "learning_rate": 1.9529421487755838e-07,
      "loss": 0.5614,
      "step": 2870,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43068391866913125,
      "success_rate.epoch.env.math": 0.8748114630467572,
      "success_rate.epoch.env.sat": 0.10152284263959391,
      "success_rate.epoch.env.science": 0.7043222003929273,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48014826890636164,
      "success_rate.epoch.global": 0.6550559425796918,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9889380530973452,
      "tokens_p.mean_in_band": 0.7828776041666666,
      "tokens_rate.above_band": 0.904,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.096
    },
    {
      "epoch": 0.47789228723404253,
      "grad_norm": 124.15262435835528,
      "learning_rate": 1.9527703262534075e-07,
      "loss": 0.4833,
      "step": 2875,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43068391866913125,
      "success_rate.epoch.env.math": 0.8748114630467572,
      "success_rate.epoch.env.sat": 0.10152284263959391,
      "success_rate.epoch.env.science": 0.7045380346065948,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48016789019851314,
      "success_rate.epoch.global": 0.6552886641382216,
      "success_rate.window.env.science": 0.7,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9859913793103449,
      "tokens_p.mean_below_band": 2.514570951461792e-08,
      "tokens_p.mean_in_band": 0.7063616071428571,
      "tokens_rate.above_band": 0.8011049723756906,
      "tokens_rate.below_band": 0.0055248618784530384,
      "tokens_rate.in_band": 0.19337016574585636
    },
    {
      "epoch": 0.4787234042553192,
      "grad_norm": 213.58935546013439,
      "learning_rate": 1.9525982326013288e-07,
      "loss": 0.8068,
      "step": 2880,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4017094017094017,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.4317343173431734,
      "success_rate.epoch.env.math": 0.8734939759036144,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.7049233778937072,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.480591164583879,
      "success_rate.epoch.global": 0.6555859457184936,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9963003778337531,
      "tokens_p.mean_in_band": 0.6088709677419355,
      "tokens_rate.above_band": 0.927570093457944,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07242990654205607
    },
    {
      "epoch": 0.47955452127659576,
      "grad_norm": 444.9925838797831,
      "learning_rate": 1.9524258681247724e-07,
      "loss": 0.5465,
      "step": 2885,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.430939226519337,
      "success_rate.epoch.env.math": 0.8734939759036144,
      "success_rate.epoch.env.sat": 0.10552763819095477,
      "success_rate.epoch.env.science": 0.7053077173559101,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.480966304590812,
      "success_rate.epoch.global": 0.655672268907563,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9983069329660239,
      "tokens_p.mean_in_band": 0.5727719907407407,
      "tokens_rate.above_band": 0.952755905511811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047244094488188976
    },
    {
      "epoch": 0.48038563829787234,
      "grad_norm": 226.97986778456246,
      "learning_rate": 1.9522532331296423e-07,
      "loss": 0.5787,
      "step": 2890,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43119266055045874,
      "success_rate.epoch.env.math": 0.8734939759036144,
      "success_rate.epoch.env.sat": 0.10552763819095477,
      "success_rate.epoch.env.science": 0.7052700065061809,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48098591578912037,
      "success_rate.epoch.global": 0.6556138509968521,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.3125,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9996327130264446,
      "tokens_p.mean_below_band": 3.655441105365753e-08,
      "tokens_p.mean_in_band": 0.6320219494047619,
      "tokens_rate.above_band": 0.9595864661654135,
      "tokens_rate.below_band": 0.0009398496240601503,
      "tokens_rate.in_band": 0.039473684210526314
    },
    {
      "epoch": 0.4812167553191489,
      "grad_norm": 162.05922051049942,
      "learning_rate": 1.9520803279223242e-07,
      "loss": 0.7941,
      "step": 2895,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43040293040293043,
      "success_rate.epoch.env.math": 0.8738738738738738,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7054238389087366,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4809146759740596,
      "success_rate.epoch.global": 0.6556346878927524,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9904092071611253,
      "tokens_p.mean_in_band": 0.6719215029761905,
      "tokens_rate.above_band": 0.8231578947368421,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17684210526315788
    },
    {
      "epoch": 0.4820478723404255,
      "grad_norm": 116.64160712247568,
      "learning_rate": 1.9519071528096818e-07,
      "loss": 0.7528,
      "step": 2900,
      "success_rate.epoch.env.abd": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43040293040293043,
      "success_rate.epoch.env.math": 0.8738738738738738,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7050243111831442,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4808783552717331,
      "success_rate.epoch.global": 0.6554393305439331,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.5238095238095238,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9978248898678415,
      "tokens_p.mean_in_band": 0.5424528301886793,
      "tokens_rate.above_band": 0.9553872053872053,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04461279461279461
    },
    {
      "epoch": 0.48287898936170215,
      "grad_norm": 97.81348489544554,
      "learning_rate": 1.9517337080990587e-07,
      "loss": 0.6511,
      "step": 2905,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43040293040293043,
      "success_rate.epoch.env.math": 0.8729446935724963,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7052154195011338,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.479348352907517,
      "success_rate.epoch.global": 0.6554534057668199,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.4,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.27999999999999997,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9918089207048458,
      "tokens_p.mean_below_band": 2.7830537874251604e-10,
      "tokens_p.mean_in_band": 0.19893307062980242,
      "tokens_rate.above_band": 0.42762951334379906,
      "tokens_rate.below_band": 0.0003139717425431711,
      "tokens_rate.in_band": 0.5720565149136577
    },
    {
      "epoch": 0.48371010638297873,
      "grad_norm": 117.5132882873014,
      "learning_rate": 1.951559994098277e-07,
      "loss": 0.6454,
      "step": 2910,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43040293040293043,
      "success_rate.epoch.env.math": 0.8729446935724963,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7050825509873746,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4793362739517207,
      "success_rate.epoch.global": 0.6553884711779449,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9863095238095239,
      "tokens_p.mean_in_band": 0.744735054347826,
      "tokens_rate.above_band": 0.8203125,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1796875
    },
    {
      "epoch": 0.4845412234042553,
      "grad_norm": 155.74678696384868,
      "learning_rate": 1.9513860111156363e-07,
      "loss": 0.6006,
      "step": 2915,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.43040293040293043,
      "success_rate.epoch.env.math": 0.8729446935724963,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7052359405300582,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.479350218455601,
      "success_rate.epoch.global": 0.6555393281869393,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9858774038461539,
      "tokens_p.mean_in_band": 0.7578125,
      "tokens_rate.above_band": 0.8739495798319328,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12605042016806722
    },
    {
      "epoch": 0.4853723404255319,
      "grad_norm": 90.83445935900029,
      "learning_rate": 1.9512117594599135e-07,
      "loss": 0.7775,
      "step": 2920,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.43040293040293043,
      "success_rate.epoch.env.math": 0.8703427719821163,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7052937378954164,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4787597803149284,
      "success_rate.epoch.global": 0.6552083333333333,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9920130272952854,
      "tokens_p.mean_below_band": 4.6798959374427795e-08,
      "tokens_p.mean_in_band": 0.6425382653061225,
      "tokens_rate.above_band": 0.8448637316561844,
      "tokens_rate.below_band": 0.0010482180293501049,
      "tokens_rate.in_band": 0.1540880503144654
    },
    {
      "epoch": 0.4862034574468085,
      "grad_norm": 64.3381634631119,
      "learning_rate": 1.951037239440363e-07,
      "loss": 0.6782,
      "step": 2925,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.43144424131627057,
      "success_rate.epoch.env.math": 0.8703427719821163,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.705446342249436,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4788683180665066,
      "success_rate.epoch.global": 0.6554307116104869,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942620056497176,
      "tokens_p.mean_below_band": 6.007030606269836e-08,
      "tokens_p.mean_in_band": 0.48114224137931033,
      "tokens_rate.above_band": 0.921875,
      "tokens_rate.below_band": 0.0026041666666666665,
      "tokens_rate.in_band": 0.07552083333333333
    },
    {
      "epoch": 0.4870345744680851,
      "grad_norm": 145.6710540873504,
      "learning_rate": 1.9508624513667149e-07,
      "loss": 0.5386,
      "step": 2930,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.43144424131627057,
      "success_rate.epoch.env.math": 0.8703427719821163,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7056931489224831,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47889075503678363,
      "success_rate.epoch.global": 0.6556525353283458,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.981694560669456,
      "tokens_p.mean_in_band": 0.6909398320895522,
      "tokens_rate.above_band": 0.7810457516339869,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21895424836601307
    },
    {
      "epoch": 0.4878656914893617,
      "grad_norm": 81.64995319749673,
      "learning_rate": 1.9506873955491753e-07,
      "loss": 0.612,
      "step": 2935,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.4306569343065693,
      "success_rate.epoch.env.math": 0.8705357142857143,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7061657032755299,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47887968136832393,
      "success_rate.epoch.global": 0.6559452168499689,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9978725416036308,
      "tokens_p.mean_in_band": 0.6726422991071429,
      "tokens_rate.above_band": 0.9218967921896792,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07810320781032078
    },
    {
      "epoch": 0.4886968085106383,
      "grad_norm": 119.2716227190001,
      "learning_rate": 1.9505120722984255e-07,
      "loss": 0.747,
      "step": 2940,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.8707280832095097,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7063543003851092,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4788430020204213,
      "success_rate.epoch.global": 0.6560232220609579,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9949581430745814,
      "tokens_p.mean_in_band": 0.6673677884615384,
      "tokens_rate.above_band": 0.926657263751763,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07334273624823695
    },
    {
      "epoch": 0.4895279255319149,
      "grad_norm": 193.43265281618676,
      "learning_rate": 1.950336481925621e-07,
      "loss": 0.4983,
      "step": 2945,
      "success_rate.epoch.env.abd": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.870919881305638,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.7068247356616469,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4789032050543,
      "success_rate.epoch.global": 0.6564506108925243,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9893229166666667,
      "tokens_p.mean_in_band": 0.8306361607142857,
      "tokens_rate.above_band": 0.8955223880597015,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1044776119402985
    },
    {
      "epoch": 0.4903590425531915,
      "grad_norm": 101.21918161840637,
      "learning_rate": 1.9501606247423918e-07,
      "loss": 0.7732,
      "step": 2950,
      "success_rate.epoch.env.abd": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43859649122807015,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.8711111111111111,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.70656,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4771751455838311,
      "success_rate.epoch.global": 0.6561207609594706,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9938687814421464,
      "tokens_p.mean_below_band": 2.4817381927277893e-07,
      "tokens_p.mean_in_band": 0.33247052599758165,
      "tokens_rate.above_band": 0.8115218870492175,
      "tokens_rate.below_band": 0.0009072352007257881,
      "tokens_rate.in_band": 0.1875708777500567
    },
    {
      "epoch": 0.4911901595744681,
      "grad_norm": 109.71645350827444,
      "learning_rate": 1.9499845010608413e-07,
      "loss": 0.6651,
      "step": 2955,
      "success_rate.epoch.env.abd": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4434782608695652,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.8711111111111111,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.7068414322250639,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4780493217824645,
      "success_rate.epoch.global": 0.6564759347242305,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936067635550587,
      "tokens_p.mean_below_band": 7.82310962677002e-07,
      "tokens_p.mean_in_band": 0.5332463357300885,
      "tokens_rate.above_band": 0.8876209377325726,
      "tokens_rate.below_band": 0.00024807740014884643,
      "tokens_rate.in_band": 0.11213098486727859
    },
    {
      "epoch": 0.4920212765957447,
      "grad_norm": 68.61644436380628,
      "learning_rate": 1.9498081111935464e-07,
      "loss": 0.8812,
      "step": 2960,
      "success_rate.epoch.env.abd": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.871301775147929,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.7064835515809645,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4784702658362935,
      "success_rate.epoch.global": 0.6564176640528271,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.3333333333333333,
      "success_rate.window.env_macro_mean": 0.4666666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9935853769300635,
      "tokens_p.mean_below_band": 5.364418029785156e-07,
      "tokens_p.mean_in_band": 0.7454769736842105,
      "tokens_rate.above_band": 0.934634974533107,
      "tokens_rate.below_band": 0.0008488964346349745,
      "tokens_rate.in_band": 0.06451612903225806
    },
    {
      "epoch": 0.49285239361702127,
      "grad_norm": 131.15530033218207,
      "learning_rate": 1.9496314554535549e-07,
      "loss": 0.6283,
      "step": 2965,
      "success_rate.epoch.env.abd": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.8716814159292036,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.7067645181876197,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.47853032105337795,
      "success_rate.epoch.global": 0.6567717996289425,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966299019607843,
      "tokens_p.mean_in_band": 0.6950334821428571,
      "tokens_rate.above_band": 0.9622641509433962,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03773584905660377
    },
    {
      "epoch": 0.49368351063829785,
      "grad_norm": 121.2542322405226,
      "learning_rate": 1.9494545341543883e-07,
      "loss": 0.3931,
      "step": 2970,
      "success_rate.epoch.env.abd": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.42987249544626593,
      "success_rate.epoch.env.math": 0.8718703976435935,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.7064073956008926,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4785150355195291,
      "success_rate.epoch.global": 0.6566426364572605,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9964895546659995,
      "tokens_p.mean_in_band": 0.7262931034482759,
      "tokens_rate.above_band": 0.9856966707768188,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014303329223181258
    },
    {
      "epoch": 0.4945146276595745,
      "grad_norm": 109.7852704933942,
      "learning_rate": 1.949277347610038e-07,
      "loss": 0.5924,
      "step": 2975,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.4301270417422868,
      "success_rate.epoch.env.math": 0.8724340175953079,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.7065944568333864,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4801643377244766,
      "success_rate.epoch.global": 0.6570018507094386,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7916666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971774193548387,
      "tokens_p.mean_in_band": 0.6062127976190477,
      "tokens_rate.above_band": 0.9485924112607099,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.051407588739290085
    },
    {
      "epoch": 0.4953457446808511,
      "grad_norm": 88.73715716732671,
      "learning_rate": 1.9490998961349673e-07,
      "loss": 0.6279,
      "step": 2980,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.452991452991453,
      "success_rate.epoch.env.logic": 0.4301270417422868,
      "success_rate.epoch.env.math": 0.8724340175953079,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.7068362480127186,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4806150088246421,
      "success_rate.epoch.global": 0.6572895277207392,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970418689320388,
      "tokens_p.mean_in_band": 0.657421875,
      "tokens_rate.above_band": 0.9321266968325792,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06787330316742081
    },
    {
      "epoch": 0.49617686170212766,
      "grad_norm": 180.1899567193848,
      "learning_rate": 1.9489221800441086e-07,
      "loss": 0.7333,
      "step": 2985,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4491525423728814,
      "success_rate.epoch.env.logic": 0.4311594202898551,
      "success_rate.epoch.env.math": 0.8724340175953079,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7070225611693677,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48032754844794634,
      "success_rate.epoch.global": 0.6572307692307693,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9870590490797546,
      "tokens_p.mean_in_band": 0.6593611725663717,
      "tokens_rate.above_band": 0.8522875816993464,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1477124183006536
    },
    {
      "epoch": 0.49700797872340424,
      "grad_norm": 68.7296333699883,
      "learning_rate": 1.948744199652865e-07,
      "loss": 0.7045,
      "step": 2990,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.453781512605042,
      "success_rate.epoch.env.logic": 0.43037974683544306,
      "success_rate.epoch.env.math": 0.8726207906295754,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7068527918781726,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.48067903031347553,
      "success_rate.epoch.global": 0.6571779643661684,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.52,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9972319347319347,
      "tokens_p.mean_below_band": 4.917383193969727e-07,
      "tokens_p.mean_in_band": 0.1843357669213974,
      "tokens_rate.above_band": 0.7366914710933028,
      "tokens_rate.below_band": 0.0011448196908986834,
      "tokens_rate.in_band": 0.2621637092157985
    },
    {
      "epoch": 0.4978390957446808,
      "grad_norm": 198.43959583424723,
      "learning_rate": 1.9485659552771073e-07,
      "loss": 0.6389,
      "step": 2995,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4067796610169492,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.43243243243243246,
      "success_rate.epoch.env.math": 0.8726207906295754,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7071315372424722,
      "success_rate.epoch.env.webshop": 0.16666666666666666,
      "success_rate.epoch.env_macro_mean": 0.4752441744064677,
      "success_rate.epoch.global": 0.6574642126789366,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9964516932270916,
      "tokens_p.mean_in_band": 0.49622691761363635,
      "tokens_rate.above_band": 0.9716129032258064,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02838709677419355
    },
    {
      "epoch": 0.49867021276595747,
      "grad_norm": 81.84898694035189,
      "learning_rate": 1.948387447233176e-07,
      "loss": 0.7499,
      "step": 3000,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.40336134453781514,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.43243243243243246,
      "success_rate.epoch.env.math": 0.8726207906295754,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.707409753008233,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4857324481775213,
      "success_rate.epoch.global": 0.6574754901960784,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9977814401622718,
      "tokens_p.mean_below_band": 3.0547380447387695e-07,
      "tokens_p.mean_in_band": 0.6332839439655172,
      "tokens_rate.above_band": 0.9426386233269598,
      "tokens_rate.below_band": 0.0019120458891013384,
      "tokens_rate.in_band": 0.055449330783938815
    },
    {
      "epoch": 0.49950132978723405,
      "grad_norm": 162.8283417155497,
      "learning_rate": 1.9482086758378793e-07,
      "loss": 0.5524,
      "step": 3005,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.40336134453781514,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.43243243243243246,
      "success_rate.epoch.env.math": 0.8726207906295754,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.7069238065128043,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48568827122339137,
      "success_rate.epoch.global": 0.6572128137114874,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.science": 0.5555555555555556,
      "success_rate.window.env_macro_mean": 0.2777777777777778,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9899929775280899,
      "tokens_p.mean_below_band": 7.566995918750763e-10,
      "tokens_p.mean_in_band": 0.48077713815789475,
      "tokens_rate.above_band": 0.8202764976958525,
      "tokens_rate.below_band": 0.004608294930875576,
      "tokens_rate.in_band": 0.17511520737327188
    },
    {
      "epoch": 0.5003324468085106,
      "grad_norm": 85.24720237975545,
      "learning_rate": 1.9480296414084925e-07,
      "loss": 0.6139,
      "step": 3010,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.40336134453781514,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.4326750448833034,
      "success_rate.epoch.env.math": 0.8715328467153285,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.7070707070707071,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.485624777504712,
      "success_rate.epoch.global": 0.6572301425661915,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9974302496328928,
      "tokens_p.mean_in_band": 0.6077724358974359,
      "tokens_rate.above_band": 0.9458333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05416666666666667
    },
    {
      "epoch": 0.5011635638297872,
      "grad_norm": 129.16856847399177,
      "learning_rate": 1.9478503442627576e-07,
      "loss": 0.8013,
      "step": 3015,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.40336134453781514,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.43189964157706096,
      "success_rate.epoch.env.math": 0.8717201166180758,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.706717123935667,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48553916691029975,
      "success_rate.epoch.global": 0.6569684638860631,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.65,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9954268292682927,
      "tokens_p.mean_in_band": 0.5942925347222222,
      "tokens_rate.above_band": 0.9458375125376128,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05416248746238716
    },
    {
      "epoch": 0.5019946808510638,
      "grad_norm": 142.34257098649343,
      "learning_rate": 1.9476707847188836e-07,
      "loss": 0.5914,
      "step": 3020,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.40336134453781514,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.43189964157706096,
      "success_rate.epoch.env.math": 0.872093023255814,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.7072710103871577,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4856234208275023,
      "success_rate.epoch.global": 0.6575258988421694,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9832677165354331,
      "tokens_p.mean_below_band": 1.1874362826347351e-08,
      "tokens_p.mean_in_band": 0.7096354166666666,
      "tokens_rate.above_band": 0.8698630136986302,
      "tokens_rate.below_band": 0.00684931506849315,
      "tokens_rate.in_band": 0.1232876712328767
    },
    {
      "epoch": 0.5028257978723404,
      "grad_norm": 71.54630062438862,
      "learning_rate": 1.9474909630955443e-07,
      "loss": 0.7388,
      "step": 3025,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.40336134453781514,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.43112701252236135,
      "success_rate.epoch.env.math": 0.872093023255814,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.707639107198994,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48599360735288194,
      "success_rate.epoch.global": 0.6577399066747819,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9966107871720117,
      "tokens_p.mean_in_band": 0.6602376302083334,
      "tokens_rate.above_band": 0.9469906129210381,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0530093870789619
    },
    {
      "epoch": 0.503656914893617,
      "grad_norm": 254.72011399752955,
      "learning_rate": 1.9473108797118788e-07,
      "loss": 0.6623,
      "step": 3030,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.43137254901960786,
      "success_rate.epoch.env.math": 0.872278664731495,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7080062794348508,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4857123126882836,
      "success_rate.epoch.global": 0.6577561765897124,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9990269461077844,
      "tokens_p.mean_in_band": 0.5681537828947368,
      "tokens_rate.above_band": 0.9564719358533792,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043528064146620846
    },
    {
      "epoch": 0.5044880319148937,
      "grad_norm": 138.31030230057533,
      "learning_rate": 1.947130534887492e-07,
      "loss": 0.6561,
      "step": 3035,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.4306049822064057,
      "success_rate.epoch.env.math": 0.8726483357452967,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7083725305738476,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4857094359009741,
      "success_rate.epoch.global": 0.6580384226491406,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952088100686499,
      "tokens_p.mean_in_band": 0.6116727941176471,
      "tokens_rate.above_band": 0.9625550660792952,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037444933920704845
    },
    {
      "epoch": 0.5053191489361702,
      "grad_norm": 132.76839341716322,
      "learning_rate": 1.9469499289424506e-07,
      "loss": 0.7476,
      "step": 3040,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4049586776859504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.4306049822064057,
      "success_rate.epoch.env.math": 0.8726483357452967,
      "success_rate.epoch.env.sat": 0.1073170731707317,
      "success_rate.epoch.env.science": 0.7084246789852803,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4861171415385389,
      "success_rate.epoch.global": 0.6580488790143405,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9920753588516746,
      "tokens_p.mean_in_band": 0.6683693910256411,
      "tokens_rate.above_band": 0.9414414414414415,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05855855855855856
    },
    {
      "epoch": 0.5061502659574468,
      "grad_norm": 110.40179907659918,
      "learning_rate": 1.9467690621972868e-07,
      "loss": 0.4889,
      "step": 3045,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4049586776859504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.4306049822064057,
      "success_rate.epoch.env.math": 0.8726483357452967,
      "success_rate.epoch.env.sat": 0.1073170731707317,
      "success_rate.epoch.env.science": 0.7092442223610244,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4861916454817884,
      "success_rate.epoch.global": 0.6586693548387097,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9875,
      "tokens_p.mean_in_band": 0.7915296052631579,
      "tokens_rate.above_band": 0.8680555555555556,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13194444444444445
    },
    {
      "epoch": 0.5069813829787234,
      "grad_norm": 91.20474456042156,
      "learning_rate": 1.946587934972994e-07,
      "loss": 0.5502,
      "step": 3050,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4049586776859504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.4308510638297872,
      "success_rate.epoch.env.math": 0.8726483357452967,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7090739008419084,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4861511730670964,
      "success_rate.epoch.global": 0.65841384863124,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9927805280528053,
      "tokens_p.mean_in_band": 0.6816761363636363,
      "tokens_rate.above_band": 0.8463687150837989,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15363128491620112
    },
    {
      "epoch": 0.5078125,
      "grad_norm": 75.37530930954513,
      "learning_rate": 1.9464065475910295e-07,
      "loss": 0.5729,
      "step": 3055,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4049586776859504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2727272727272727,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.43209876543209874,
      "success_rate.epoch.env.math": 0.8726483357452967,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7090342679127726,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4862609974919305,
      "success_rate.epoch.global": 0.6584238037796541,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9980395232120451,
      "tokens_p.mean_in_band": 0.6196933962264151,
      "tokens_rate.above_band": 0.9376470588235294,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06235294117647059
    },
    {
      "epoch": 0.5086436170212766,
      "grad_norm": 143.9155011548668,
      "learning_rate": 1.9462249003733106e-07,
      "loss": 0.6431,
      "step": 3060,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4049586776859504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.43133802816901406,
      "success_rate.epoch.env.math": 0.8728323699421965,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7093963907902925,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4841753744995726,
      "success_rate.epoch.global": 0.6585023087733387,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9960570141065831,
      "tokens_p.mean_in_band": 0.6301339285714286,
      "tokens_rate.above_band": 0.9239681390296887,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07603186097031137
    },
    {
      "epoch": 0.5094747340425532,
      "grad_norm": 67.32241724482296,
      "learning_rate": 1.9460429936422172e-07,
      "loss": 0.7247,
      "step": 3065,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4016393442622951,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43133802816901406,
      "success_rate.epoch.env.math": 0.8728323699421965,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7092264678471575,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48351330356506905,
      "success_rate.epoch.global": 0.6581796311146753,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.19047619047619047,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9932995495495496,
      "tokens_p.mean_below_band": 9.424984455108643e-07,
      "tokens_p.mean_in_band": 0.4953420538651316,
      "tokens_rate.above_band": 0.784452296819788,
      "tokens_rate.below_band": 0.0007067137809187279,
      "tokens_rate.in_band": 0.21484098939929328
    },
    {
      "epoch": 0.5103058510638298,
      "grad_norm": 1513.0141409476253,
      "learning_rate": 1.945860827720589e-07,
      "loss": 0.706,
      "step": 3070,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4016393442622951,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43133802816901406,
      "success_rate.epoch.env.math": 0.8728323699421965,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7094573643410853,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4835342941554261,
      "success_rate.epoch.global": 0.6583900680816981,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9825858778625954,
      "tokens_p.mean_in_band": 0.6908967391304348,
      "tokens_rate.above_band": 0.8506493506493507,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14935064935064934
    },
    {
      "epoch": 0.5111369680851063,
      "grad_norm": 107.26116424799214,
      "learning_rate": 1.9456784029317258e-07,
      "loss": 0.852,
      "step": 3075,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4016393442622951,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4305799648506151,
      "success_rate.epoch.env.math": 0.873015873015873,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7097772277227723,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4835111398951501,
      "success_rate.epoch.global": 0.6586048370977413,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975043402777778,
      "tokens_p.mean_in_band": 0.5502604166666667,
      "tokens_rate.above_band": 0.9624060150375939,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03759398496240601
    },
    {
      "epoch": 0.511968085106383,
      "grad_norm": 68.83960272206484,
      "learning_rate": 1.9454957195993872e-07,
      "loss": 0.5301,
      "step": 3080,
      "success_rate.epoch.env.abd": 0.46875,
      "success_rate.epoch.env.agentgym:alfworld": 0.4016393442622951,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4305799648506151,
      "success_rate.epoch.env.math": 0.873015873015873,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7100061766522545,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.483531953434194,
      "success_rate.epoch.global": 0.6588141345577959,
      "success_rate.window.env.science": 0.7,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_below_band": 2.066371962428093e-09,
      "tokens_p.mean_in_band": 0.5927734375,
      "tokens_rate.above_band": 0.8943089430894309,
      "tokens_rate.below_band": 0.008130081300813009,
      "tokens_rate.in_band": 0.0975609756097561
    },
    {
      "epoch": 0.5127992021276596,
      "grad_norm": 76.3543828841282,
      "learning_rate": 1.945312778047791e-07,
      "loss": 0.5208,
      "step": 3085,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4065040650406504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4305799648506151,
      "success_rate.epoch.env.math": 0.8731988472622478,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7102746066029003,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4827239152088149,
      "success_rate.epoch.global": 0.6590229312063809,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9876771907216495,
      "tokens_p.mean_in_band": 0.6369310461956522,
      "tokens_rate.above_band": 0.8083333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19166666666666668
    },
    {
      "epoch": 0.5136303191489362,
      "grad_norm": 195.15299431435912,
      "learning_rate": 1.9451295786016137e-07,
      "loss": 0.6438,
      "step": 3090,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4065040650406504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4305799648506151,
      "success_rate.epoch.env.math": 0.8735632183908046,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7105020018478596,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4827777121518619,
      "success_rate.epoch.global": 0.6593669122038622,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99625,
      "tokens_p.mean_in_band": 0.6681189903846154,
      "tokens_rate.above_band": 0.9615384615384616,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038461538461538464
    },
    {
      "epoch": 0.5144614361702128,
      "grad_norm": 83.95661236784456,
      "learning_rate": 1.9449461215859897e-07,
      "loss": 0.6049,
      "step": 3095,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4065040650406504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43157894736842106,
      "success_rate.epoch.env.math": 0.8737446197991392,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7106802092951677,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48290122045853906,
      "success_rate.epoch.global": 0.659637955042769,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983148060548723,
      "tokens_p.mean_in_band": 0.6614583333333334,
      "tokens_rate.above_band": 0.9832558139534884,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01674418604651163
    },
    {
      "epoch": 0.5152925531914894,
      "grad_norm": 226.40219895590317,
      "learning_rate": 1.94476240732651e-07,
      "loss": 0.6722,
      "step": 3100,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4065040650406504,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43157894736842106,
      "success_rate.epoch.env.math": 0.8737446197991392,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7111247695144438,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4817262728459987,
      "success_rate.epoch.global": 0.6598450228491953,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9881365740740741,
      "tokens_p.mean_in_band": 0.627858231707317,
      "tokens_rate.above_band": 0.9133192389006343,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08668076109936575
    },
    {
      "epoch": 0.516123670212766,
      "grad_norm": 113.09732536535843,
      "learning_rate": 1.9445784361492222e-07,
      "loss": 0.7517,
      "step": 3105,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43157894736842106,
      "success_rate.epoch.env.math": 0.8741058655221745,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.710995085995086,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4821824382772416,
      "success_rate.epoch.global": 0.6599841206828106,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.52,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.991117125984252,
      "tokens_p.mean_in_band": 0.47296091573816157,
      "tokens_rate.above_band": 0.7796193984039288,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2203806015960712
    },
    {
      "epoch": 0.5169547872340425,
      "grad_norm": 348.2089233710818,
      "learning_rate": 1.9443942083806308e-07,
      "loss": 0.6984,
      "step": 3110,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4308231173380035,
      "success_rate.epoch.env.math": 0.8742857142857143,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7111724984653162,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48214620475027364,
      "success_rate.epoch.global": 0.660055533518445,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9999247592295345,
      "tokens_p.mean_in_band": 0.5881453804347826,
      "tokens_rate.above_band": 0.9643962848297214,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03560371517027864
    },
    {
      "epoch": 0.5177859042553191,
      "grad_norm": 145.8757977490526,
      "learning_rate": 1.9442097243476943e-07,
      "loss": 0.6476,
      "step": 3115,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43006993006993005,
      "success_rate.epoch.env.math": 0.8744650499286734,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7108249003373198,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4820624365909,
      "success_rate.epoch.global": 0.6597978997424212,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.5238095238095238,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9943340306834031,
      "tokens_p.mean_in_band": 0.6067266949152542,
      "tokens_rate.above_band": 0.9239690721649485,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07603092783505154
    },
    {
      "epoch": 0.5186170212765957,
      "grad_norm": 88.38912368014553,
      "learning_rate": 1.9440249843778268e-07,
      "loss": 0.5705,
      "step": 3120,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43006993006993005,
      "success_rate.epoch.env.math": 0.8744650499286734,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7108323133414932,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48206311050037026,
      "success_rate.epoch.global": 0.6598733676296004,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9937580541237113,
      "tokens_p.mean_in_band": 0.4886623475609756,
      "tokens_rate.above_band": 0.9498164014687882,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05018359853121175
    },
    {
      "epoch": 0.5194481382978723,
      "grad_norm": 91.8427462985612,
      "learning_rate": 1.9438399887988967e-07,
      "loss": 0.6048,
      "step": 3125,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43006993006993005,
      "success_rate.epoch.env.math": 0.8746438746438746,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7105745721271394,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4820559362731746,
      "success_rate.epoch.global": 0.6598141925281676,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9938186813186813,
      "tokens_p.mean_in_band": 0.5875355113636364,
      "tokens_rate.above_band": 0.8921568627450981,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10784313725490197
    },
    {
      "epoch": 0.520279255319149,
      "grad_norm": 113.82402542440803,
      "learning_rate": 1.9436547379392255e-07,
      "loss": 0.5084,
      "step": 3130,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43031358885017423,
      "success_rate.epoch.env.math": 0.8746438746438746,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.710927960927961,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48211021332599874,
      "success_rate.epoch.global": 0.6600197433366239,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982169669669669,
      "tokens_p.mean_in_band": 0.5188078703703703,
      "tokens_rate.above_band": 0.961038961038961,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03896103896103896
    },
    {
      "epoch": 0.5211103723404256,
      "grad_norm": 136.74885881233408,
      "learning_rate": 1.9434692321275885e-07,
      "loss": 0.6728,
      "step": 3135,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43130434782608695,
      "success_rate.epoch.env.math": 0.875,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7108470444850701,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48222530131592123,
      "success_rate.epoch.global": 0.6602286164761529,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9907142857142858,
      "tokens_p.mean_in_band": 0.690047554347826,
      "tokens_rate.above_band": 0.8838383838383839,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11616161616161616
    },
    {
      "epoch": 0.5219414893617021,
      "grad_norm": 189.61915445833725,
      "learning_rate": 1.9432834716932128e-07,
      "loss": 0.5548,
      "step": 3140,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43130434782608695,
      "success_rate.epoch.env.math": 0.8753541076487252,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7112868877395802,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4822974786707608,
      "success_rate.epoch.global": 0.6606967132454241,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9886363636363636,
      "tokens_p.mean_in_band": 0.85546875,
      "tokens_rate.above_band": 0.934640522875817,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06535947712418301
    },
    {
      "epoch": 0.5227726063829787,
      "grad_norm": 105.52806631381361,
      "learning_rate": 1.9430974569657777e-07,
      "loss": 0.4033,
      "step": 3145,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43130434782608695,
      "success_rate.epoch.env.math": 0.8755304101838756,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7112462006079028,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4823098073438038,
      "success_rate.epoch.global": 0.6607669616519174,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9957975679542204,
      "tokens_p.mean_in_band": 0.6809303977272727,
      "tokens_rate.above_band": 0.9694868238557559,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030513176144244106
    },
    {
      "epoch": 0.5236037234042553,
      "grad_norm": 220.24522055233118,
      "learning_rate": 1.9429111882754138e-07,
      "loss": 0.7186,
      "step": 3150,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.4112903225806452,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43327556325823224,
      "success_rate.epoch.env.math": 0.8755304101838756,
      "success_rate.epoch.env.sat": 0.10628019323671498,
      "success_rate.epoch.env.science": 0.7115092620710598,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4824660213099095,
      "success_rate.epoch.global": 0.6609703398153605,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9936507936507937,
      "tokens_p.mean_in_band": 0.60595703125,
      "tokens_rate.above_band": 0.8873239436619719,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11267605633802817
    },
    {
      "epoch": 0.5244348404255319,
      "grad_norm": 138.71029122122607,
      "learning_rate": 1.9427246659527022e-07,
      "loss": 0.7992,
      "step": 3155,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4342560553633218,
      "success_rate.epoch.env.math": 0.8757062146892656,
      "success_rate.epoch.env.sat": 0.10628019323671498,
      "success_rate.epoch.env.science": 0.7115559599636033,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48300353693921655,
      "success_rate.epoch.global": 0.6612397018438604,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9966492663656885,
      "tokens_p.mean_in_band": 0.5879480698529411,
      "tokens_rate.above_band": 0.9630434782608696,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03695652173913044
    },
    {
      "epoch": 0.5252659574468085,
      "grad_norm": 120.43567329335224,
      "learning_rate": 1.9425378903286744e-07,
      "loss": 0.582,
      "step": 3160,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4342560553633218,
      "success_rate.epoch.env.math": 0.8758815232722144,
      "success_rate.epoch.env.sat": 0.10628019323671498,
      "success_rate.epoch.env.science": 0.711864406779661,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4830475147027626,
      "success_rate.epoch.global": 0.6615746180963572,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9911114221724524,
      "tokens_p.mean_in_band": 0.6971344449626866,
      "tokens_rate.above_band": 0.8695228821811101,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13047711781888996
    },
    {
      "epoch": 0.5260970744680851,
      "grad_norm": 96.6958608439252,
      "learning_rate": 1.9423508617348117e-07,
      "loss": 0.6411,
      "step": 3165,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43523316062176165,
      "success_rate.epoch.env.math": 0.8760563380281691,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7118234048986998,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48305604950198583,
      "success_rate.epoch.global": 0.6614512028163505,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.55,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9928977272727273,
      "tokens_p.mean_in_band": 0.2745674070247934,
      "tokens_rate.above_band": 0.5217391304347826,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.4782608695652174
    },
    {
      "epoch": 0.5269281914893617,
      "grad_norm": 119.54343371979893,
      "learning_rate": 1.9421635805030436e-07,
      "loss": 0.6658,
      "step": 3170,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43448275862068964,
      "success_rate.epoch.env.math": 0.8762306610407876,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7121715493808517,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48303532818323114,
      "success_rate.epoch.global": 0.6616526665364328,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978797935103245,
      "tokens_p.mean_in_band": 0.636953125,
      "tokens_rate.above_band": 0.9313186813186813,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06868131868131869
    },
    {
      "epoch": 0.5277593085106383,
      "grad_norm": 62.26544055916979,
      "learning_rate": 1.9419760469657488e-07,
      "loss": 0.5262,
      "step": 3175,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4354561101549053,
      "success_rate.epoch.env.math": 0.876577840112202,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7125188536953243,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4831869495396041,
      "success_rate.epoch.global": 0.6621147093250097,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9949292452830188,
      "tokens_p.mean_below_band": 9.049472282640636e-11,
      "tokens_p.mean_in_band": 0.78515625,
      "tokens_rate.above_band": 0.9706959706959707,
      "tokens_rate.below_band": 0.003663003663003663,
      "tokens_rate.in_band": 0.02564102564102564
    },
    {
      "epoch": 0.5285904255319149,
      "grad_norm": 230.32432476908042,
      "learning_rate": 1.9417882614557533e-07,
      "loss": 0.7394,
      "step": 3180,
      "success_rate.epoch.env.abd": 0.4411764705882353,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4339622641509434,
      "success_rate.epoch.env.math": 0.876577840112202,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7126921917395237,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4830669033614438,
      "success_rate.epoch.global": 0.6619883040935672,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9970193740685543,
      "tokens_p.mean_in_band": 0.5698962602459017,
      "tokens_rate.above_band": 0.9428571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05714285714285714
    },
    {
      "epoch": 0.5294215425531915,
      "grad_norm": 131.47905877378923,
      "learning_rate": 1.9416002243063302e-07,
      "loss": 0.6955,
      "step": 3185,
      "success_rate.epoch.env.abd": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4324786324786325,
      "success_rate.epoch.env.math": 0.876750700280112,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.713038241493526,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48443069107091874,
      "success_rate.epoch.global": 0.662125340599455,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965521015761821,
      "tokens_p.mean_in_band": 0.5602430555555555,
      "tokens_rate.above_band": 0.962089300758214,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037910699241786014
    },
    {
      "epoch": 0.5302526595744681,
      "grad_norm": 153.3635923514554,
      "learning_rate": 1.941411935851199e-07,
      "loss": 0.7419,
      "step": 3190,
      "success_rate.epoch.env.abd": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43270868824531517,
      "success_rate.epoch.env.math": 0.876750700280112,
      "success_rate.epoch.env.sat": 0.10476190476190476,
      "success_rate.epoch.env.science": 0.7133834586466166,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4844374201424589,
      "success_rate.epoch.global": 0.6621963070942662,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950487012987013,
      "tokens_p.mean_in_band": 0.5748697916666666,
      "tokens_rate.above_band": 0.9553349875930521,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04466501240694789
    },
    {
      "epoch": 0.5310837765957447,
      "grad_norm": 178.19935137659635,
      "learning_rate": 1.9412233964245266e-07,
      "loss": 0.5919,
      "step": 3195,
      "success_rate.epoch.env.abd": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:alfworld": 0.416,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.4336734693877551,
      "success_rate.epoch.env.math": 0.876750700280112,
      "success_rate.epoch.env.sat": 0.10426540284360189,
      "success_rate.epoch.env.science": 0.7138138138138138,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4845191141780347,
      "success_rate.epoch.global": 0.6624611801242236,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988259668508287,
      "tokens_p.mean_in_band": 0.48353794642857145,
      "tokens_rate.above_band": 0.969989281886388,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030010718113612004
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 88.08463558337269,
      "learning_rate": 1.9410346063609236e-07,
      "loss": 0.5676,
      "step": 3200,
      "success_rate.epoch.env.abd": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43463497453310695,
      "success_rate.epoch.env.math": 0.8772663877266388,
      "success_rate.epoch.env.sat": 0.10426540284360189,
      "success_rate.epoch.env.science": 0.713985594237695,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4850903772371875,
      "success_rate.epoch.global": 0.662919170381857,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982893061744113,
      "tokens_p.mean_in_band": 0.6092006138392857,
      "tokens_rate.above_band": 0.9655808236017209,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034419176398279044
    },
    {
      "epoch": 0.5327460106382979,
      "grad_norm": 232.53031082896106,
      "learning_rate": 1.940845565995446e-07,
      "loss": 0.6129,
      "step": 3205,
      "success_rate.epoch.env.abd": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.43485617597292725,
      "success_rate.epoch.env.math": 0.8776077885952712,
      "success_rate.epoch.env.sat": 0.10426540284360189,
      "success_rate.epoch.env.science": 0.7142428785607197,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48516491238550363,
      "success_rate.epoch.global": 0.6631823461091754,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992517605633803,
      "tokens_p.mean_in_band": 0.6482514880952381,
      "tokens_rate.above_band": 0.9712722298221614,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028727770177838577
    },
    {
      "epoch": 0.5335771276595744,
      "grad_norm": 377.2234128007386,
      "learning_rate": 1.9406562756635946e-07,
      "loss": 0.79,
      "step": 3210,
      "success_rate.epoch.env.abd": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.433389544688027,
      "success_rate.epoch.env.math": 0.8776077885952712,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.7144567494762047,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4850063143575621,
      "success_rate.epoch.global": 0.6629951690821256,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.2777777777777778,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9983662868632708,
      "tokens_p.mean_in_band": 0.5758770636792453,
      "tokens_rate.above_band": 0.9336670838548186,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06633291614518148
    },
    {
      "epoch": 0.534408244680851,
      "grad_norm": 108.34155735487911,
      "learning_rate": 1.9404667357013128e-07,
      "loss": 0.6534,
      "step": 3215,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4634146341463415,
      "success_rate.epoch.env.logic": 0.43434343434343436,
      "success_rate.epoch.env.math": 0.8776077885952712,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.7147129186602871,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4843617586161798,
      "success_rate.epoch.global": 0.6631924338930708,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9955275229357798,
      "tokens_p.mean_in_band": 0.2726796468098958,
      "tokens_rate.above_band": 0.5866523143164694,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.4133476856835307
    },
    {
      "epoch": 0.5352393617021277,
      "grad_norm": 196.82178498878054,
      "learning_rate": 1.9402769464449882e-07,
      "loss": 0.6372,
      "step": 3220,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4634146341463415,
      "success_rate.epoch.env.logic": 0.4336134453781513,
      "success_rate.epoch.env.math": 0.8779472954230236,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.7148834429169157,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4843417624451887,
      "success_rate.epoch.global": 0.6633243347473968,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.993702440304382,
      "tokens_p.mean_in_band": 0.5337826236263736,
      "tokens_rate.above_band": 0.8567895683453237,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14321043165467626
    },
    {
      "epoch": 0.5360704787234043,
      "grad_norm": 171.26493342908842,
      "learning_rate": 1.94008690823145e-07,
      "loss": 0.5479,
      "step": 3225,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4634146341463415,
      "success_rate.epoch.env.logic": 0.4336134453781513,
      "success_rate.epoch.env.math": 0.8767313019390581,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.7154786758127051,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48428532966444543,
      "success_rate.epoch.global": 0.6636503658067,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9938650306748467,
      "tokens_p.mean_in_band": 0.6644965277777778,
      "tokens_rate.above_band": 0.9602356406480118,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039764359351988215
    },
    {
      "epoch": 0.5369015957446809,
      "grad_norm": 114.42520006426773,
      "learning_rate": 1.939896621397969e-07,
      "loss": 0.5981,
      "step": 3230,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4634146341463415,
      "success_rate.epoch.env.logic": 0.43288590604026844,
      "success_rate.epoch.env.math": 0.8770718232044199,
      "success_rate.epoch.env.sat": 0.10328638497652583,
      "success_rate.epoch.env.science": 0.7155198093535895,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48420959471346625,
      "success_rate.epoch.global": 0.6635909265667052,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9956124641833811,
      "tokens_p.mean_in_band": 0.5901884191176471,
      "tokens_rate.above_band": 0.953551912568306,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04644808743169399
    },
    {
      "epoch": 0.5377327127659575,
      "grad_norm": 106.87530993936028,
      "learning_rate": 1.9397060862822585e-07,
      "loss": 0.5171,
      "step": 3235,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4634146341463415,
      "success_rate.epoch.env.logic": 0.43288590604026844,
      "success_rate.epoch.env.math": 0.8758620689655172,
      "success_rate.epoch.env.sat": 0.10328638497652583,
      "success_rate.epoch.env.science": 0.7158583754834871,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4841303957944658,
      "success_rate.epoch.global": 0.6637219128096793,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9959766313932981,
      "tokens_p.mean_in_band": 0.5585186298076923,
      "tokens_rate.above_band": 0.9561551433389545,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04384485666104553
    },
    {
      "epoch": 0.538563829787234,
      "grad_norm": 120.9381389992513,
      "learning_rate": 1.9395153032224712e-07,
      "loss": 0.6498,
      "step": 3240,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4634146341463415,
      "success_rate.epoch.env.logic": 0.4331103678929766,
      "success_rate.epoch.env.math": 0.8760330578512396,
      "success_rate.epoch.env.sat": 0.102803738317757,
      "success_rate.epoch.env.science": 0.7160273565269105,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4841378308056553,
      "success_rate.epoch.global": 0.6637253021292921,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9943310657596371,
      "tokens_p.mean_in_band": 0.6790916313559322,
      "tokens_rate.above_band": 0.882,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.118
    },
    {
      "epoch": 0.5393949468085106,
      "grad_norm": 117.5764329206785,
      "learning_rate": 1.9393242725572005e-07,
      "loss": 0.675,
      "step": 3245,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46774193548387094,
      "success_rate.epoch.env.logic": 0.4331103678929766,
      "success_rate.epoch.env.math": 0.8762035763411279,
      "success_rate.epoch.env.sat": 0.10232558139534884,
      "success_rate.epoch.env.science": 0.7163647163647163,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48589892514727634,
      "success_rate.epoch.global": 0.6640490327523463,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973137535816619,
      "tokens_p.mean_in_band": 0.6428571428571429,
      "tokens_rate.above_band": 0.9432432432432433,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05675675675675676
    },
    {
      "epoch": 0.5402260638297872,
      "grad_norm": 116.71089826451538,
      "learning_rate": 1.9391329946254788e-07,
      "loss": 0.582,
      "step": 3250,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46774193548387094,
      "success_rate.epoch.env.logic": 0.4331103678929766,
      "success_rate.epoch.env.math": 0.8765432098765432,
      "success_rate.epoch.env.sat": 0.10232558139534884,
      "success_rate.epoch.env.science": 0.7158956109134045,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48588715497310386,
      "success_rate.epoch.global": 0.6639250191277736,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9881889763779528,
      "tokens_p.mean_below_band": 1.525040715932846e-08,
      "tokens_p.mean_in_band": 0.58984375,
      "tokens_rate.above_band": 0.8881118881118881,
      "tokens_rate.below_band": 0.006993006993006993,
      "tokens_rate.in_band": 0.1048951048951049
    },
    {
      "epoch": 0.5410571808510638,
      "grad_norm": 87.75839838589815,
      "learning_rate": 1.9389414697667777e-07,
      "loss": 0.7757,
      "step": 3255,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46774193548387094,
      "success_rate.epoch.env.logic": 0.43333333333333335,
      "success_rate.epoch.env.math": 0.8768809849521204,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.7161481481481482,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4859180229919385,
      "success_rate.epoch.global": 0.6640565317035906,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9939018777614138,
      "tokens_p.mean_in_band": 0.5779109589041096,
      "tokens_rate.above_band": 0.8611287254280279,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1388712745719721
    },
    {
      "epoch": 0.5418882978723404,
      "grad_norm": 117.2183827307503,
      "learning_rate": 1.938749698321007e-07,
      "loss": 0.6221,
      "step": 3260,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.42063492063492064,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46774193548387094,
      "success_rate.epoch.env.logic": 0.43333333333333335,
      "success_rate.epoch.env.math": 0.8770491803278688,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.7161042036708112,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48592931852815774,
      "success_rate.epoch.global": 0.6641221374045801,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9831349206349206,
      "tokens_p.mean_in_band": 0.5756655092592593,
      "tokens_rate.above_band": 0.8235294117647058,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17647058823529413
    },
    {
      "epoch": 0.542719414893617,
      "grad_norm": 98.40761766824093,
      "learning_rate": 1.9385576806285137e-07,
      "loss": 0.8351,
      "step": 3265,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4251968503937008,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46774193548387094,
      "success_rate.epoch.env.logic": 0.43333333333333335,
      "success_rate.epoch.env.math": 0.8770491803278688,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.7161442933175636,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48634768392866073,
      "success_rate.epoch.global": 0.6642516682554814,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950211864406779,
      "tokens_p.mean_below_band": 1.8189894035458565e-09,
      "tokens_p.mean_in_band": 0.7270972842261905,
      "tokens_rate.above_band": 0.9305993690851735,
      "tokens_rate.below_band": 0.0031545741324921135,
      "tokens_rate.in_band": 0.06624605678233439
    },
    {
      "epoch": 0.5435505319148937,
      "grad_norm": 393.78041537958535,
      "learning_rate": 1.9383654170300825e-07,
      "loss": 0.641,
      "step": 3270,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4251968503937008,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46774193548387094,
      "success_rate.epoch.env.logic": 0.43261231281198004,
      "success_rate.epoch.env.math": 0.8772169167803547,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.7163518299881936,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48631625234700276,
      "success_rate.epoch.global": 0.664382257757472,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982727465986394,
      "tokens_p.mean_in_band": 0.630859375,
      "tokens_rate.above_band": 0.9735099337748344,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026490066225165563
    },
    {
      "epoch": 0.5443816489361702,
      "grad_norm": 125.13192048028029,
      "learning_rate": 1.938172907866934e-07,
      "loss": 0.5023,
      "step": 3275,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4251968503937008,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.464,
      "success_rate.epoch.env.logic": 0.43283582089552236,
      "success_rate.epoch.env.math": 0.8772169167803547,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7166863207547169,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48598413416460323,
      "success_rate.epoch.global": 0.6643223721725907,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9917733089579525,
      "tokens_p.mean_in_band": 0.6948275862068966,
      "tokens_rate.above_band": 0.8829701372074253,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11702986279257466
    },
    {
      "epoch": 0.5452127659574468,
      "grad_norm": 176.9919449863871,
      "learning_rate": 1.937980153480725e-07,
      "loss": 0.6543,
      "step": 3280,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4251968503937008,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.464,
      "success_rate.epoch.env.logic": 0.43211920529801323,
      "success_rate.epoch.env.math": 0.8772169167803547,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7170588235294117,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.485952851180711,
      "success_rate.epoch.global": 0.6645161290322581,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9940591190108191,
      "tokens_p.mean_in_band": 0.65640625,
      "tokens_rate.above_band": 0.9627976190476191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03720238095238095
    },
    {
      "epoch": 0.5460438829787234,
      "grad_norm": 278.81311177224,
      "learning_rate": 1.9377871542135472e-07,
      "loss": 0.6573,
      "step": 3285,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4251968503937008,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.464,
      "success_rate.epoch.env.logic": 0.43211920529801323,
      "success_rate.epoch.env.math": 0.8772169167803547,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7170975323149236,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4859563701612121,
      "success_rate.epoch.global": 0.6645809632157755,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.990516571724495,
      "tokens_p.mean_in_band": 0.5702287467838765,
      "tokens_rate.above_band": 0.8688413948256468,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1311586051743532
    },
    {
      "epoch": 0.546875,
      "grad_norm": 124.55345609261471,
      "learning_rate": 1.9375939104079268e-07,
      "loss": 0.5882,
      "step": 3290,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4296875,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.464,
      "success_rate.epoch.env.logic": 0.4306930693069307,
      "success_rate.epoch.env.math": 0.8775510204081632,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7171806167400882,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.486272888494684,
      "success_rate.epoch.global": 0.6645833333333333,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9975209243085881,
      "tokens_p.mean_in_band": 0.4116053427419355,
      "tokens_rate.above_band": 0.9779359430604982,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02206405693950178
    },
    {
      "epoch": 0.5477061170212766,
      "grad_norm": 201.7107469896585,
      "learning_rate": 1.9374004224068246e-07,
      "loss": 0.7538,
      "step": 3295,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.43410852713178294,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.464,
      "success_rate.epoch.env.logic": 0.4306930693069307,
      "success_rate.epoch.env.math": 0.8778833107191316,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7173466392720869,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4867201012196612,
      "success_rate.epoch.global": 0.6649006622516557,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965431415929203,
      "tokens_p.mean_in_band": 0.6985193888346354,
      "tokens_rate.above_band": 0.9377593360995851,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06224066390041494
    },
    {
      "epoch": 0.5485372340425532,
      "grad_norm": 117.16934693105219,
      "learning_rate": 1.937206690553634e-07,
      "loss": 0.4866,
      "step": 3300,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.43410852713178294,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.464,
      "success_rate.epoch.env.logic": 0.4299835255354201,
      "success_rate.epoch.env.math": 0.878213802435724,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7170917619466433,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.486662471275992,
      "success_rate.epoch.global": 0.6647770219198791,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.997624269005848,
      "tokens_p.mean_in_band": 0.5042818509615384,
      "tokens_rate.above_band": 0.9293478260869565,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07065217391304347
    },
    {
      "epoch": 0.5493683510638298,
      "grad_norm": 167.2840586285636,
      "learning_rate": 1.9370127151921817e-07,
      "loss": 0.7433,
      "step": 3305,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.43410852713178294,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4603174603174603,
      "success_rate.epoch.env.logic": 0.4299835255354201,
      "success_rate.epoch.env.math": 0.8783783783783784,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7173403632103105,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48636525650542667,
      "success_rate.epoch.global": 0.664904663016802,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9896875,
      "tokens_p.mean_in_band": 0.6246939804147466,
      "tokens_rate.above_band": 0.8216926869350862,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17830731306491374
    },
    {
      "epoch": 0.5501994680851063,
      "grad_norm": 197.12579536218755,
      "learning_rate": 1.936818496666727e-07,
      "loss": 0.5641,
      "step": 3310,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.43410852713178294,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4299835255354201,
      "success_rate.epoch.env.math": 0.8783783783783784,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7178362573099415,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48679665313415654,
      "success_rate.epoch.global": 0.6653469079939668,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9896599264705882,
      "tokens_p.mean_in_band": 0.7979910714285714,
      "tokens_rate.above_band": 0.9872958257713249,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012704174228675136
    },
    {
      "epoch": 0.551030585106383,
      "grad_norm": 114.70664501060222,
      "learning_rate": 1.9366240353219595e-07,
      "loss": 0.6868,
      "step": 3315,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4307692307692308,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4309210526315789,
      "success_rate.epoch.env.math": 0.8787061994609164,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7181658878504673,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4866380788029448,
      "success_rate.epoch.global": 0.6656626506024096,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.996684350132626,
      "tokens_p.mean_in_band": 0.7360026041666666,
      "tokens_rate.above_band": 0.9843342036553525,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015665796344647518
    },
    {
      "epoch": 0.5518617021276596,
      "grad_norm": 111.47568696410329,
      "learning_rate": 1.9364293315030004e-07,
      "loss": 0.5449,
      "step": 3320,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4307692307692308,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4320785597381342,
      "success_rate.epoch.env.math": 0.8787061994609164,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7184947491248541,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48677320320121226,
      "success_rate.epoch.global": 0.6659146456100771,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9995216836734694,
      "tokens_p.mean_in_band": 0.52294921875,
      "tokens_rate.above_band": 0.9702970297029703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0297029702970297
    },
    {
      "epoch": 0.5526928191489362,
      "grad_norm": 85.21180144163797,
      "learning_rate": 1.9362343855554018e-07,
      "loss": 0.5307,
      "step": 3325,
      "success_rate.epoch.env.abd": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:alfworld": 0.4307692307692308,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4320785597381342,
      "success_rate.epoch.env.math": 0.8787061994609164,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7186953989516599,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48679144409455827,
      "success_rate.epoch.global": 0.6661032863849765,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9920908658420552,
      "tokens_p.mean_below_band": 2.9976945370435715e-09,
      "tokens_p.mean_in_band": 0.7104223901098901,
      "tokens_rate.above_band": 0.9195100612423447,
      "tokens_rate.below_band": 0.0008748906386701663,
      "tokens_rate.in_band": 0.07961504811898512
    },
    {
      "epoch": 0.5535239361702128,
      "grad_norm": 130.87655122855932,
      "learning_rate": 1.9360391978251446e-07,
      "loss": 0.5872,
      "step": 3330,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.43300653594771243,
      "success_rate.epoch.env.math": 0.8788694481830417,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7189409368635438,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4874969930009358,
      "success_rate.epoch.global": 0.66641665104069,
      "success_rate.window.env.abd": 0.5,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973012111637704,
      "tokens_p.mean_in_band": 0.1284136446156571,
      "tokens_rate.above_band": 0.40216010165184246,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.5978398983481575
    },
    {
      "epoch": 0.5543550531914894,
      "grad_norm": 88.45651137642601,
      "learning_rate": 1.9358437686586398e-07,
      "loss": 0.4208,
      "step": 3335,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.433931484502447,
      "success_rate.epoch.env.math": 0.8793565683646113,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7187318208260617,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48760635233719235,
      "success_rate.epoch.global": 0.6665417759460472,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.993140243902439,
      "tokens_p.mean_in_band": 0.6883680555555556,
      "tokens_rate.above_band": 0.9647058823529412,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03529411764705882
    },
    {
      "epoch": 0.555186170212766,
      "grad_norm": 132.64204714576977,
      "learning_rate": 1.9356480984027253e-07,
      "loss": 0.407,
      "step": 3340,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.433931484502447,
      "success_rate.epoch.env.math": 0.8793565683646113,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7193033381712627,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48765830845948327,
      "success_rate.epoch.global": 0.6669784845650141,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9902836134453782,
      "tokens_p.mean_in_band": 0.7677083333333333,
      "tokens_rate.above_band": 0.8880597014925373,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11194029850746269
    },
    {
      "epoch": 0.5560172872340425,
      "grad_norm": 124.2666115329214,
      "learning_rate": 1.9354521874046689e-07,
      "loss": 0.5664,
      "step": 3345,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.433931484502447,
      "success_rate.epoch.env.math": 0.8798397863818425,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7197913648217907,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4877466034292796,
      "success_rate.epoch.global": 0.6675382891296228,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9945255474452555,
      "tokens_p.mean_in_band": 0.8627232142857143,
      "tokens_rate.above_band": 0.9513888888888888,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04861111111111111
    },
    {
      "epoch": 0.5568484042553191,
      "grad_norm": 108.21322101755437,
      "learning_rate": 1.9352560360121636e-07,
      "loss": 0.6237,
      "step": 3350,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.433931484502447,
      "success_rate.epoch.env.math": 0.8801597869507324,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7197452229299363,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48777149967264644,
      "success_rate.epoch.global": 0.6676618772158985,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9998031496062992,
      "tokens_p.mean_in_band": 0.5998114224137931,
      "tokens_rate.above_band": 0.9563253012048193,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043674698795180725
    },
    {
      "epoch": 0.5576795212765957,
      "grad_norm": 64.96612927227478,
      "learning_rate": 1.935059644573331e-07,
      "loss": 0.5518,
      "step": 3355,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.43322475570032576,
      "success_rate.epoch.env.math": 0.8801597869507324,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7199074074074074,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48772199564313284,
      "success_rate.epoch.global": 0.6676613204028348,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976851851851852,
      "tokens_p.mean_in_band": 0.6111328125,
      "tokens_rate.above_band": 0.9440559440559441,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.055944055944055944
    },
    {
      "epoch": 0.5585106382978723,
      "grad_norm": 306.3571322516184,
      "learning_rate": 1.9348630134367173e-07,
      "loss": 0.6717,
      "step": 3360,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.43344155844155846,
      "success_rate.epoch.env.math": 0.8801597869507324,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.7201503324660307,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48776378907948337,
      "success_rate.epoch.global": 0.6677846096515745,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995844414893617,
      "tokens_p.mean_in_band": 0.5966996173469388,
      "tokens_rate.above_band": 0.9388264669163545,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06117353308364544
    },
    {
      "epoch": 0.559341755319149,
      "grad_norm": 97.70276225776648,
      "learning_rate": 1.9346661429512946e-07,
      "loss": 0.4693,
      "step": 3365,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4351145038167939,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.43344155844155846,
      "success_rate.epoch.env.math": 0.8804780876494024,
      "success_rate.epoch.env.sat": 0.1004566210045662,
      "success_rate.epoch.env.science": 0.7201848108576379,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4877116901354453,
      "success_rate.epoch.global": 0.6677209302325582,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9966216216216216,
      "tokens_p.mean_below_band": 9.74978320300579e-10,
      "tokens_p.mean_in_band": 0.58798828125,
      "tokens_rate.above_band": 0.844106463878327,
      "tokens_rate.below_band": 0.0038022813688212928,
      "tokens_rate.in_band": 0.1520912547528517
    },
    {
      "epoch": 0.5601728723404256,
      "grad_norm": 137.23799338425331,
      "learning_rate": 1.9344690334664603e-07,
      "loss": 0.6915,
      "step": 3370,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.43344155844155846,
      "success_rate.epoch.env.math": 0.8807947019867549,
      "success_rate.epoch.env.sat": 0.1004566210045662,
      "success_rate.epoch.env.science": 0.7203463203463204,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4874554903015746,
      "success_rate.epoch.global": 0.6678438661710037,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.32,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9976302941922394,
      "tokens_p.mean_in_band": 0.4926228350903614,
      "tokens_rate.above_band": 0.959600876125578,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040399123874422
    },
    {
      "epoch": 0.5610039893617021,
      "grad_norm": 111.91847726305173,
      "learning_rate": 1.9342716853320343e-07,
      "loss": 0.5506,
      "step": 3375,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4336569579288026,
      "success_rate.epoch.env.math": 0.8811096433289299,
      "success_rate.epoch.env.sat": 0.1004566210045662,
      "success_rate.epoch.env.science": 0.7204610951008645,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.487514137172844,
      "success_rate.epoch.global": 0.6680274633512711,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965679190751445,
      "tokens_p.mean_in_band": 0.533797554347826,
      "tokens_rate.above_band": 0.9376693766937669,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06233062330623306
    },
    {
      "epoch": 0.5618351063829787,
      "grad_norm": 67.75984462274953,
      "learning_rate": 1.9340740988982625e-07,
      "loss": 0.6136,
      "step": 3380,
      "success_rate.epoch.env.abd": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4345718901453958,
      "success_rate.epoch.env.math": 0.8811096433289299,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7202877697841726,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4875400449815108,
      "success_rate.epoch.global": 0.6679021497405485,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.996171875,
      "tokens_p.mean_in_band": 0.6792879971590909,
      "tokens_rate.above_band": 0.9009009009009009,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0990990990990991
    },
    {
      "epoch": 0.5626662234042553,
      "grad_norm": 156.51334171989987,
      "learning_rate": 1.9338762745158114e-07,
      "loss": 0.6024,
      "step": 3385,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4345718901453958,
      "success_rate.epoch.env.math": 0.8812664907651715,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7206093705087668,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48653458921990844,
      "success_rate.epoch.global": 0.6680858941132913,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9924273574561403,
      "tokens_p.mean_in_band": 0.6706665917266187,
      "tokens_rate.above_band": 0.8677450047573739,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13225499524262607
    },
    {
      "epoch": 0.5634973404255319,
      "grad_norm": 142.80790309139422,
      "learning_rate": 1.9336782125357715e-07,
      "loss": 0.6905,
      "step": 3390,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4338709677419355,
      "success_rate.epoch.env.math": 0.8814229249011858,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.7206896551724138,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4864512535570374,
      "success_rate.epoch.global": 0.6679615242323345,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9947773972602739,
      "tokens_p.mean_in_band": 0.49404761904761907,
      "tokens_rate.above_band": 0.9205548549810845,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07944514501891552
    },
    {
      "epoch": 0.5643284574468085,
      "grad_norm": 110.51663173220152,
      "learning_rate": 1.933479913309654e-07,
      "loss": 0.6003,
      "step": 3395,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4333868378812199,
      "success_rate.epoch.env.math": 0.881578947368421,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.7209302325581395,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48644329628360516,
      "success_rate.epoch.global": 0.6680214298910031,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.0000704887218046,
      "tokens_p.mean_in_band": 0.5375532670454546,
      "tokens_rate.above_band": 0.9679767103347889,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03202328966521106
    },
    {
      "epoch": 0.5651595744680851,
      "grad_norm": 102.08720236173353,
      "learning_rate": 1.9332813771893914e-07,
      "loss": 0.5505,
      "step": 3400,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4645669291338583,
      "success_rate.epoch.env.logic": 0.4333868378812199,
      "success_rate.epoch.env.math": 0.8817345597897503,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.7210435779816514,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48646774699677253,
      "success_rate.epoch.global": 0.6682044657685919,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9925508720930233,
      "tokens_p.mean_in_band": 0.73486328125,
      "tokens_rate.above_band": 0.8775510204081632,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12244897959183673
    },
    {
      "epoch": 0.5659906914893617,
      "grad_norm": 190.68819095292852,
      "learning_rate": 1.933082604527337e-07,
      "loss": 0.4331,
      "step": 3405,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.4333868378812199,
      "success_rate.epoch.env.math": 0.8817345597897503,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.7215226101888953,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48689157454889853,
      "success_rate.epoch.global": 0.6686325101363804,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9989992721979621,
      "tokens_p.mean_in_band": 0.61953125,
      "tokens_rate.above_band": 0.9717114568599717,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028288543140028287
    },
    {
      "epoch": 0.5668218085106383,
      "grad_norm": 103.43171487259264,
      "learning_rate": 1.932883595676263e-07,
      "loss": 0.6614,
      "step": 3410,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.4333868378812199,
      "success_rate.epoch.env.math": 0.8817345597897503,
      "success_rate.epoch.env.sat": 0.0990990990990991,
      "success_rate.epoch.env.science": 0.7217615098655991,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.486872527954679,
      "success_rate.epoch.global": 0.6686924493554328,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9904698581560284,
      "tokens_p.mean_in_band": 0.69484375,
      "tokens_rate.above_band": 0.8493975903614458,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15060240963855423
    },
    {
      "epoch": 0.5676529255319149,
      "grad_norm": 208.40341949456763,
      "learning_rate": 1.9326843509893617e-07,
      "loss": 0.4698,
      "step": 3415,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.4333868378812199,
      "success_rate.epoch.env.math": 0.8820445609436435,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.7220794058840332,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4865588721058767,
      "success_rate.epoch.global": 0.6688120632585509,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9868259803921569,
      "tokens_p.mean_in_band": 0.5959795947488584,
      "tokens_rate.above_band": 0.7884057971014493,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21159420289855072
    },
    {
      "epoch": 0.5684840425531915,
      "grad_norm": 123.54851256069378,
      "learning_rate": 1.932484870820244e-07,
      "loss": 0.3822,
      "step": 3420,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46511627906976744,
      "success_rate.epoch.env.logic": 0.4333868378812199,
      "success_rate.epoch.env.math": 0.8821989528795812,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.7219846022241232,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4865642892218792,
      "success_rate.epoch.global": 0.668870523415978,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9903474903474904,
      "tokens_p.mean_in_band": 0.6338975694444444,
      "tokens_rate.above_band": 0.9664179104477612,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033582089552238806
    },
    {
      "epoch": 0.5693151595744681,
      "grad_norm": 431.58645055561846,
      "learning_rate": 1.9322851555229373e-07,
      "loss": 0.601,
      "step": 3425,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.4342948717948718,
      "success_rate.epoch.env.math": 0.8821989528795812,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.7223804100227791,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48635756414742487,
      "success_rate.epoch.global": 0.669112252384446,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9900081566068516,
      "tokens_p.mean_in_band": 0.664296875,
      "tokens_rate.above_band": 0.8909883720930233,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10901162790697674
    },
    {
      "epoch": 0.5701462765957447,
      "grad_norm": 115.4163781656245,
      "learning_rate": 1.9320852054518884e-07,
      "loss": 0.615,
      "step": 3430,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.4352,
      "success_rate.epoch.env.math": 0.8821989528795812,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.7226173541963016,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48646138890912033,
      "success_rate.epoch.global": 0.6693548387096774,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9948593073593074,
      "tokens_p.mean_in_band": 0.64171875,
      "tokens_rate.above_band": 0.90234375,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09765625
    },
    {
      "epoch": 0.5709773936170213,
      "grad_norm": 217.45249092490982,
      "learning_rate": 1.931885020961959e-07,
      "loss": 0.5385,
      "step": 3435,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.43610223642172524,
      "success_rate.epoch.env.math": 0.8821989528795812,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.7227272727272728,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4865534029957292,
      "success_rate.epoch.global": 0.6695349688758696,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9968251088534107,
      "tokens_p.mean_in_band": 0.6231026785714285,
      "tokens_rate.above_band": 0.9516574585635359,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04834254143646409
    },
    {
      "epoch": 0.5718085106382979,
      "grad_norm": 94.78379157521786,
      "learning_rate": 1.9316846024084278e-07,
      "loss": 0.6162,
      "step": 3440,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.43610223642172524,
      "success_rate.epoch.env.math": 0.8821989528795812,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.7227105188545506,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4865518799163908,
      "success_rate.epoch.global": 0.6695922472115561,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995872641509434,
      "tokens_p.mean_in_band": 0.6285807291666666,
      "tokens_rate.above_band": 0.9298245614035088,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07017543859649122
    },
    {
      "epoch": 0.5726396276595744,
      "grad_norm": 136.5194251574622,
      "learning_rate": 1.9314839501469886e-07,
      "loss": 0.685,
      "step": 3445,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.43610223642172524,
      "success_rate.epoch.env.math": 0.8821989528795812,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7229461756373937,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48653326482338616,
      "success_rate.epoch.global": 0.6696510140690664,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977341389728097,
      "tokens_p.mean_in_band": 0.580109126984127,
      "tokens_rate.above_band": 0.9131034482758621,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08689655172413793
    },
    {
      "epoch": 0.573470744680851,
      "grad_norm": 105.46169193868766,
      "learning_rate": 1.93128306453375e-07,
      "loss": 0.8601,
      "step": 3450,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.43610223642172524,
      "success_rate.epoch.env.math": 0.8825065274151436,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7233380480905234,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48659685091326726,
      "success_rate.epoch.global": 0.67007299270073,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9887867647058823,
      "tokens_p.mean_in_band": 0.7763671875,
      "tokens_rate.above_band": 0.8947368421052632,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10526315789473684
    },
    {
      "epoch": 0.5743018617021277,
      "grad_norm": 101.24033812462726,
      "learning_rate": 1.931081945925235e-07,
      "loss": 0.458,
      "step": 3455,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.25,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.43610223642172524,
      "success_rate.epoch.env.math": 0.8825065274151436,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7238068342276193,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4866394678348214,
      "success_rate.epoch.global": 0.6704338315712723,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988755622188905,
      "tokens_p.mean_in_band": 0.5683001893939394,
      "tokens_rate.above_band": 0.9528571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047142857142857146
    },
    {
      "epoch": 0.5751329787234043,
      "grad_norm": 118.34969737607743,
      "learning_rate": 1.9308805946783794e-07,
      "loss": 0.5792,
      "step": 3460,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.3076923076923077,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46564885496183206,
      "success_rate.epoch.env.logic": 0.4354066985645933,
      "success_rate.epoch.env.math": 0.8826597131681877,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7241184767277856,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4922369216086175,
      "success_rate.epoch.global": 0.6707317073170732,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7666666666666667,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9987827145465612,
      "tokens_p.mean_in_band": 0.6183035714285714,
      "tokens_rate.above_band": 0.9750741839762611,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024925816023738872
    },
    {
      "epoch": 0.5759640957446809,
      "grad_norm": 128.50248204797833,
      "learning_rate": 1.9306790111505326e-07,
      "loss": 0.7503,
      "step": 3465,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.3076923076923077,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46564885496183206,
      "success_rate.epoch.env.logic": 0.4354066985645933,
      "success_rate.epoch.env.math": 0.8828125,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7243517474633596,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4922720177511071,
      "success_rate.epoch.global": 0.6709712622771917,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9971802566225165,
      "tokens_p.mean_in_band": 0.5270432692307693,
      "tokens_rate.above_band": 0.9489395129615082,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05106048703849175
    },
    {
      "epoch": 0.5767952127659575,
      "grad_norm": 124.11961737165471,
      "learning_rate": 1.9304771956994556e-07,
      "loss": 0.6193,
      "step": 3470,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.3076923076923077,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46564885496183206,
      "success_rate.epoch.env.logic": 0.43630573248407645,
      "success_rate.epoch.env.math": 0.8828125,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7248945147679325,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4924030905896577,
      "success_rate.epoch.global": 0.6714493280058118,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.98765625,
      "tokens_p.mean_in_band": 0.71640625,
      "tokens_rate.above_band": 0.9090909090909091,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09090909090909091
    },
    {
      "epoch": 0.577626329787234,
      "grad_norm": 80.91745340051162,
      "learning_rate": 1.930275148683322e-07,
      "loss": 0.4208,
      "step": 3475,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.3076923076923077,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46564885496183206,
      "success_rate.epoch.env.logic": 0.43720190779014306,
      "success_rate.epoch.env.math": 0.88296488946684,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7248454187745925,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4924939513878001,
      "success_rate.epoch.global": 0.6715659589911087,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9953520569620253,
      "tokens_p.mean_in_band": 0.6641927083333333,
      "tokens_rate.above_band": 0.9132947976878613,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08670520231213873
    },
    {
      "epoch": 0.5784574468085106,
      "grad_norm": 138.64385863583678,
      "learning_rate": 1.9300728704607154e-07,
      "loss": 0.6964,
      "step": 3480,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.43720190779014306,
      "success_rate.epoch.env.math": 0.88296488946684,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7253856942496494,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4902243705383833,
      "success_rate.epoch.global": 0.6717391304347826,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9919088866338069,
      "tokens_p.mean_in_band": 0.5242947048611111,
      "tokens_rate.above_band": 0.8272967138402495,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17270328615975053
    },
    {
      "epoch": 0.5792885638297872,
      "grad_norm": 139.8773584252811,
      "learning_rate": 1.9298703613906301e-07,
      "loss": 0.6539,
      "step": 3485,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.43670886075949367,
      "success_rate.epoch.env.math": 0.8831168831168831,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7253363228699552,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.490188877378356,
      "success_rate.epoch.global": 0.6716120861226705,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7111111111111111,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.996934253915911,
      "tokens_p.mean_in_band": 0.5658318014705882,
      "tokens_rate.above_band": 0.9596518987341772,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040348101265822785
    },
    {
      "epoch": 0.5801196808510638,
      "grad_norm": 103.1866269871044,
      "learning_rate": 1.9296676218324702e-07,
      "loss": 0.562,
      "step": 3490,
      "success_rate.epoch.env.abd": 0.45,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.43601895734597157,
      "success_rate.epoch.env.math": 0.8835705045278137,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7255670680481657,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.490188374030685,
      "success_rate.epoch.global": 0.6718467654499458,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9976766748366013,
      "tokens_p.mean_in_band": 0.5767045454545454,
      "tokens_rate.above_band": 0.9737470167064439,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026252983293556086
    },
    {
      "epoch": 0.5809507978723404,
      "grad_norm": 106.91551104646285,
      "learning_rate": 1.9294646521460488e-07,
      "loss": 0.6432,
      "step": 3495,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4318181818181818,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.43601895734597157,
      "success_rate.epoch.env.math": 0.884020618556701,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7257974258533856,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48925245240141313,
      "success_rate.epoch.global": 0.6720808518317993,
      "success_rate.window.env.abd": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9864296636085627,
      "tokens_p.mean_in_band": 0.7404364224137931,
      "tokens_rate.above_band": 0.8493506493506493,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15064935064935064
    },
    {
      "epoch": 0.581781914893617,
      "grad_norm": 112.86493227324142,
      "learning_rate": 1.9292614526915868e-07,
      "loss": 0.5273,
      "step": 3500,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.43601895734597157,
      "success_rate.epoch.env.math": 0.8841698841698842,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7263334264172019,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4897031169398429,
      "success_rate.epoch.global": 0.6726126126126126,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9960171568627451,
      "tokens_p.mean_in_band": 0.73515625,
      "tokens_rate.above_band": 0.9878934624697336,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012106537530266344
    },
    {
      "epoch": 0.5826130319148937,
      "grad_norm": 144.12948655184826,
      "learning_rate": 1.9290580238297146e-07,
      "loss": 0.6722,
      "step": 3505,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.43601895734597157,
      "success_rate.epoch.env.math": 0.884318766066838,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.7263861799944274,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48972144743749557,
      "success_rate.epoch.global": 0.672782874617737,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9891129032258065,
      "tokens_p.mean_in_band": 0.6759868421052632,
      "tokens_rate.above_band": 0.8908045977011494,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10919540229885058
    },
    {
      "epoch": 0.5834441489361702,
      "grad_norm": 153.49025215579306,
      "learning_rate": 1.9288543659214672e-07,
      "loss": 0.6542,
      "step": 3510,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4621212121212121,
      "success_rate.epoch.env.logic": 0.4353312302839117,
      "success_rate.epoch.env.math": 0.883183568677792,
      "success_rate.epoch.env.sat": 0.09777777777777778,
      "success_rate.epoch.env.science": 0.7264124686891177,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.48951843437450254,
      "success_rate.epoch.global": 0.6724757455982753,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.21428571428571427,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9941964285714285,
      "tokens_p.mean_in_band": 0.603125,
      "tokens_rate.above_band": 0.9333333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06666666666666667
    },
    {
      "epoch": 0.5842752659574468,
      "grad_norm": 170.75337095885664,
      "learning_rate": 1.9286504793282885e-07,
      "loss": 0.7141,
      "step": 3515,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46616541353383456,
      "success_rate.epoch.env.logic": 0.43622047244094486,
      "success_rate.epoch.env.math": 0.8833333333333333,
      "success_rate.epoch.env.sat": 0.09777777777777778,
      "success_rate.epoch.env.science": 0.7265646731571628,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4899943809829791,
      "success_rate.epoch.global": 0.6727697002333513,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947587025316456,
      "tokens_p.mean_in_band": 0.7180347711267606,
      "tokens_rate.above_band": 0.9468164794007491,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05318352059925094
    },
    {
      "epoch": 0.5851063829787234,
      "grad_norm": 44.56486602665988,
      "learning_rate": 1.928446364412027e-07,
      "loss": 0.5004,
      "step": 3520,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46616541353383456,
      "success_rate.epoch.env.logic": 0.43622047244094486,
      "success_rate.epoch.env.math": 0.8836317135549873,
      "success_rate.epoch.env.sat": 0.10176991150442478,
      "success_rate.epoch.env.science": 0.7270202721466259,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4904258457955031,
      "success_rate.epoch.global": 0.6732974910394265,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9877485795454546,
      "tokens_p.mean_below_band": 5.20230969414115e-10,
      "tokens_p.mean_in_band": 0.8055555555555556,
      "tokens_rate.above_band": 0.946236559139785,
      "tokens_rate.below_band": 0.005376344086021506,
      "tokens_rate.in_band": 0.04838709677419355
    },
    {
      "epoch": 0.5859375,
      "grad_norm": 161.7931973496787,
      "learning_rate": 1.9282420215349364e-07,
      "loss": 0.6611,
      "step": 3525,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46616541353383456,
      "success_rate.epoch.env.logic": 0.43622047244094486,
      "success_rate.epoch.env.math": 0.8839285714285714,
      "success_rate.epoch.env.sat": 0.10176991150442478,
      "success_rate.epoch.env.science": 0.7270457697642164,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49045515084015534,
      "success_rate.epoch.global": 0.673469387755102,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9953871587030717,
      "tokens_p.mean_in_band": 0.5174005681818182,
      "tokens_rate.above_band": 0.9551752241238793,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04482477587612062
    },
    {
      "epoch": 0.5867686170212766,
      "grad_norm": 137.6124261657743,
      "learning_rate": 1.9280374510596754e-07,
      "loss": 0.534,
      "step": 3530,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46616541353383456,
      "success_rate.epoch.env.logic": 0.43622047244094486,
      "success_rate.epoch.env.math": 0.8840764331210191,
      "success_rate.epoch.env.sat": 0.10176991150442478,
      "success_rate.epoch.env.science": 0.7270210409745294,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4904663447404063,
      "success_rate.epoch.global": 0.6735788344654987,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9962908011869436,
      "tokens_p.mean_in_band": 0.6245404411764706,
      "tokens_rate.above_band": 0.9519774011299436,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0480225988700565
    },
    {
      "epoch": 0.5875997340425532,
      "grad_norm": 113.38972715269938,
      "learning_rate": 1.9278326533493067e-07,
      "loss": 0.5121,
      "step": 3535,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43609022556390975,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.43622047244094486,
      "success_rate.epoch.env.math": 0.8840764331210191,
      "success_rate.epoch.env.sat": 0.1013215859030837,
      "success_rate.epoch.env.science": 0.7268454520320707,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49009336647554674,
      "success_rate.epoch.global": 0.6732726298875201,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.17857142857142858,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9933806960440661,
      "tokens_p.mean_below_band": 2.5331974029541016e-07,
      "tokens_p.mean_in_band": 0.5725612017804155,
      "tokens_rate.above_band": 0.8552462526766595,
      "tokens_rate.below_band": 0.00042826552462526765,
      "tokens_rate.in_band": 0.1443254817987152
    },
    {
      "epoch": 0.5884308510638298,
      "grad_norm": 75.89376074218096,
      "learning_rate": 1.9276276287672958e-07,
      "loss": 0.6275,
      "step": 3540,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.44029850746268656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.4371069182389937,
      "success_rate.epoch.env.math": 0.8840764331210191,
      "success_rate.epoch.env.sat": 0.1013215859030837,
      "success_rate.epoch.env.science": 0.7272225289895086,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.490590803262298,
      "success_rate.epoch.global": 0.6736804564907275,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9939304461942258,
      "tokens_p.mean_in_band": 0.7470703125,
      "tokens_rate.above_band": 0.9407407407407408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05925925925925926
    },
    {
      "epoch": 0.5892619680851063,
      "grad_norm": 165.31117024930202,
      "learning_rate": 1.9274223776775115e-07,
      "loss": 0.5662,
      "step": 3545,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.44029850746268656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.4371069182389937,
      "success_rate.epoch.env.math": 0.8840764331210191,
      "success_rate.epoch.env.sat": 0.10087719298245613,
      "success_rate.epoch.env.science": 0.727448275862069,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49057092634883737,
      "success_rate.epoch.global": 0.6737348538845331,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.2708333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9960091538289797,
      "tokens_p.mean_below_band": 2.632538477579753e-07,
      "tokens_p.mean_in_band": 0.5725049407114624,
      "tokens_rate.above_band": 0.9459345300950369,
      "tokens_rate.below_band": 0.0006335797254487857,
      "tokens_rate.in_band": 0.05343189017951425
    },
    {
      "epoch": 0.590093085106383,
      "grad_norm": 72.27471814405673,
      "learning_rate": 1.9272169004442236e-07,
      "loss": 0.6105,
      "step": 3550,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.44029850746268656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.438871473354232,
      "success_rate.epoch.env.math": 0.8842239185750637,
      "success_rate.epoch.env.sat": 0.10043668122270742,
      "success_rate.epoch.env.science": 0.7277486910994765,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49073201217128654,
      "success_rate.epoch.global": 0.6740213523131673,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99619140625,
      "tokens_p.mean_in_band": 0.5677083333333334,
      "tokens_rate.above_band": 0.898876404494382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10112359550561797
    },
    {
      "epoch": 0.5909242021276596,
      "grad_norm": 371.0554446926751,
      "learning_rate": 1.927011197432104e-07,
      "loss": 0.7198,
      "step": 3555,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.44029850746268656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.438871473354232,
      "success_rate.epoch.env.math": 0.8842239185750637,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.7280484448114506,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4911148211327614,
      "success_rate.epoch.global": 0.6743111111111111,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964387464387464,
      "tokens_p.mean_in_band": 0.669921875,
      "tokens_rate.above_band": 0.9564032697547684,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043596730245231606
    },
    {
      "epoch": 0.5917553191489362,
      "grad_norm": 161.67648638252908,
      "learning_rate": 1.9268052690062256e-07,
      "loss": 0.5927,
      "step": 3560,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43703703703703706,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.440625,
      "success_rate.epoch.env.math": 0.8845177664974619,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.727997799779978,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4909998446883108,
      "success_rate.epoch.global": 0.6744186046511628,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9962912087912088,
      "tokens_p.mean_in_band": 0.7169744318181818,
      "tokens_rate.above_band": 0.9763948497854077,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023605150214592276
    },
    {
      "epoch": 0.5925864361702128,
      "grad_norm": 146.5230316945275,
      "learning_rate": 1.9265991155320603e-07,
      "loss": 0.5661,
      "step": 3565,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43703703703703706,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.440809968847352,
      "success_rate.epoch.env.math": 0.8846641318124208,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.7279472382522671,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49102536947327446,
      "success_rate.epoch.global": 0.6744103564461784,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9964041095890411,
      "tokens_p.mean_in_band": 0.60875,
      "tokens_rate.above_band": 0.9668874172185431,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033112582781456956
    },
    {
      "epoch": 0.5934175531914894,
      "grad_norm": 79.66714075094525,
      "learning_rate": 1.9263927373754806e-07,
      "loss": 0.5814,
      "step": 3570,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43703703703703706,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4626865671641791,
      "success_rate.epoch.env.logic": 0.4409937888198758,
      "success_rate.epoch.env.math": 0.8846641318124208,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.728171334431631,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4910624527598097,
      "success_rate.epoch.global": 0.6745216158752658,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9975215517241379,
      "tokens_p.mean_in_band": 0.6535073138297872,
      "tokens_rate.above_band": 0.9610604805302403,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03893951946975974
    },
    {
      "epoch": 0.594248670212766,
      "grad_norm": 152.75395104851907,
      "learning_rate": 1.9261861349027565e-07,
      "loss": 0.6894,
      "step": 3575,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43703703703703706,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45925925925925926,
      "success_rate.epoch.env.logic": 0.44031007751937984,
      "success_rate.epoch.env.math": 0.8846641318124208,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.7286184210526315,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49072936797940836,
      "success_rate.epoch.global": 0.6746284501061571,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9930287263210369,
      "tokens_p.mean_in_band": 0.5168019923580786,
      "tokens_rate.above_band": 0.8975391498881432,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10246085011185682
    },
    {
      "epoch": 0.5950797872340425,
      "grad_norm": 96.2735204423041,
      "learning_rate": 1.9259793084805577e-07,
      "loss": 0.6407,
      "step": 3580,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4338235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44049459041731065,
      "success_rate.epoch.env.math": 0.8848101265822785,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.7284931506849315,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49014889737547507,
      "success_rate.epoch.global": 0.6743240855274784,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9932492253209385,
      "tokens_p.mean_below_band": 8.307397365570068e-07,
      "tokens_p.mean_in_band": 0.5261439087759815,
      "tokens_rate.above_band": 0.8388414407723728,
      "tokens_rate.below_band": 0.0003713330857779428,
      "tokens_rate.in_band": 0.16078722614184923
    },
    {
      "epoch": 0.5959109042553191,
      "grad_norm": 103.96724978949956,
      "learning_rate": 1.9257722584759494e-07,
      "loss": 0.5468,
      "step": 3585,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4338235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44135802469135804,
      "success_rate.epoch.env.math": 0.8848101265822785,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.7287903667214012,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49025441104006756,
      "success_rate.epoch.global": 0.674611581920904,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917328042328042,
      "tokens_p.mean_in_band": 0.7561383928571429,
      "tokens_rate.above_band": 0.9310344827586207,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06896551724137931
    },
    {
      "epoch": 0.5967420212765957,
      "grad_norm": 123.2539519863408,
      "learning_rate": 1.9255649852563953e-07,
      "loss": 0.5635,
      "step": 3590,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4338235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.4406779661016949,
      "success_rate.epoch.env.math": 0.8852459016393442,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.7286652078774617,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49017975971575933,
      "success_rate.epoch.global": 0.6744842179509787,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9985950272479565,
      "tokens_p.mean_in_band": 0.6500264830508474,
      "tokens_rate.above_band": 0.9255989911727617,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07440100882723834
    },
    {
      "epoch": 0.5975731382978723,
      "grad_norm": 72.45022684216352,
      "learning_rate": 1.9253574891897544e-07,
      "loss": 0.7369,
      "step": 3595,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.4406779661016949,
      "success_rate.epoch.env.math": 0.8844221105527639,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.7289617486338797,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49050752559190797,
      "success_rate.epoch.global": 0.6747666842754007,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950358072916666,
      "tokens_p.mean_below_band": 1.7848833522293717e-11,
      "tokens_p.mean_in_band": 0.7866908482142857,
      "tokens_rate.above_band": 0.9297820823244553,
      "tokens_rate.below_band": 0.002421307506053269,
      "tokens_rate.in_band": 0.06779661016949153
    },
    {
      "epoch": 0.598404255319149,
      "grad_norm": 213.8381891051392,
      "learning_rate": 1.9251497706442813e-07,
      "loss": 0.623,
      "step": 3600,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.8845671267252195,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.7290586630286494,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49054608736638927,
      "success_rate.epoch.global": 0.6748725162651662,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9940130624092888,
      "tokens_p.mean_below_band": 9.74978320300579e-10,
      "tokens_p.mean_in_band": 0.6457868303571429,
      "tokens_rate.above_band": 0.9596100278551533,
      "tokens_rate.below_band": 0.001392757660167131,
      "tokens_rate.in_band": 0.03899721448467967
    },
    {
      "epoch": 0.5992353723404256,
      "grad_norm": 675.4946975536126,
      "learning_rate": 1.9249418299886257e-07,
      "loss": 0.5597,
      "step": 3605,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.8836045056320401,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.728956687551076,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49044930585995716,
      "success_rate.epoch.global": 0.6748024582967516,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9929288321167883,
      "tokens_p.mean_below_band": 5.995204332975845e-15,
      "tokens_p.mean_in_band": 0.6825884650735294,
      "tokens_rate.above_band": 0.8838709677419355,
      "tokens_rate.below_band": 0.0064516129032258064,
      "tokens_rate.in_band": 0.10967741935483871
    },
    {
      "epoch": 0.6000664893617021,
      "grad_norm": 119.74339944984386,
      "learning_rate": 1.9247336675918312e-07,
      "loss": 0.5385,
      "step": 3610,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.88375,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.728905824714208,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4904171970869623,
      "success_rate.epoch.global": 0.6747368421052632,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9932291666666667,
      "tokens_p.mean_in_band": 0.6618381076388888,
      "tokens_rate.above_band": 0.8695652173913043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13043478260869565
    },
    {
      "epoch": 0.6008976063829787,
      "grad_norm": 115.92246519737863,
      "learning_rate": 1.924525283823335e-07,
      "loss": 0.6864,
      "step": 3615,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.8838951310861424,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.7292006525285482,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49045719335064253,
      "success_rate.epoch.global": 0.6750219106047327,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9928482587064676,
      "tokens_p.mean_in_band": 0.6117788461538461,
      "tokens_rate.above_band": 0.9392523364485982,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06074766355140187
    },
    {
      "epoch": 0.6017287234042553,
      "grad_norm": 121.2137720974078,
      "learning_rate": 1.9243166790529677e-07,
      "loss": 0.577,
      "step": 3620,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.8840399002493765,
      "success_rate.epoch.env.sat": 0.10300429184549356,
      "success_rate.epoch.env.science": 0.7292232482346551,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49043204615543945,
      "success_rate.epoch.global": 0.675013132551217,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9884588068181818,
      "tokens_p.mean_in_band": 0.6744342672413793,
      "tokens_rate.above_band": 0.8585365853658536,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14146341463414633
    },
    {
      "epoch": 0.6025598404255319,
      "grad_norm": 141.7195189438846,
      "learning_rate": 1.924107853650951e-07,
      "loss": 0.4776,
      "step": 3625,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.8841843088418431,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7293192297260646,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.490413882592029,
      "success_rate.epoch.global": 0.6750612102133613,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9870065789473684,
      "tokens_p.mean_in_band": 0.7389547413793104,
      "tokens_rate.above_band": 0.867579908675799,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1324200913242009
    },
    {
      "epoch": 0.6033909574468085,
      "grad_norm": 63.784874024937196,
      "learning_rate": 1.923898807987899e-07,
      "loss": 0.6139,
      "step": 3630,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.44086021505376344,
      "success_rate.epoch.env.math": 0.8841843088418431,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7296346414073072,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49044255638123285,
      "success_rate.epoch.global": 0.6753405518686693,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9925742574257426,
      "tokens_p.mean_in_band": 0.5678013392857143,
      "tokens_rate.above_band": 0.9351851851851852,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06481481481481481
    },
    {
      "epoch": 0.6042220744680851,
      "grad_norm": 152.52185517281163,
      "learning_rate": 1.923689542434817e-07,
      "loss": 0.7242,
      "step": 3635,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45588235294117646,
      "success_rate.epoch.env.logic": 0.4401840490797546,
      "success_rate.epoch.env.math": 0.8843283582089553,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7295325587679006,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49038490190429623,
      "success_rate.epoch.global": 0.6752703174049529,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0001420454545455,
      "tokens_p.mean_in_band": 0.5144159226190477,
      "tokens_rate.above_band": 0.9401709401709402,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05982905982905983
    },
    {
      "epoch": 0.6050531914893617,
      "grad_norm": 87.9277490668122,
      "learning_rate": 1.9234800573630993e-07,
      "loss": 0.6643,
      "step": 3640,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4401840490797546,
      "success_rate.epoch.env.math": 0.8843283582089553,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7297516198704104,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4907658767006483,
      "success_rate.epoch.global": 0.6754966887417219,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9951847484276729,
      "tokens_p.mean_in_band": 0.6398111979166666,
      "tokens_rate.above_band": 0.9814814814814815,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018518518518518517
    },
    {
      "epoch": 0.6058843085106383,
      "grad_norm": 223.88203659517015,
      "learning_rate": 1.9232703531445314e-07,
      "loss": 0.6119,
      "step": 3645,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43795620437956206,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4401840490797546,
      "success_rate.epoch.env.math": 0.8843283582089553,
      "success_rate.epoch.env.sat": 0.10212765957446808,
      "success_rate.epoch.env.science": 0.7301159342140738,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49075931955101465,
      "success_rate.epoch.global": 0.6757180156657964,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9978387998982965,
      "tokens_p.mean_below_band": 2.890825271606445e-07,
      "tokens_p.mean_in_band": 0.5030677356020943,
      "tokens_rate.above_band": 0.9525308791474933,
      "tokens_rate.below_band": 0.001210946960523129,
      "tokens_rate.in_band": 0.04625817389198353
    },
    {
      "epoch": 0.6067154255319149,
      "grad_norm": 92.89720607815259,
      "learning_rate": 1.9230604301512864e-07,
      "loss": 0.4645,
      "step": 3650,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4418960244648318,
      "success_rate.epoch.env.math": 0.8843283582089553,
      "success_rate.epoch.env.sat": 0.10212765957446808,
      "success_rate.epoch.env.science": 0.7300646551724138,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49128054477566024,
      "success_rate.epoch.global": 0.6758824552251782,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958784448818898,
      "tokens_p.mean_in_band": 0.7098858173076923,
      "tokens_rate.above_band": 0.9287020109689214,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0712979890310786
    },
    {
      "epoch": 0.6075465425531915,
      "grad_norm": 106.10799138425385,
      "learning_rate": 1.9228502887559265e-07,
      "loss": 0.6484,
      "step": 3655,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.44274809160305345,
      "success_rate.epoch.env.math": 0.8847583643122676,
      "success_rate.epoch.env.sat": 0.1016949152542373,
      "success_rate.epoch.env.science": 0.7300134589502019,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49135310229375945,
      "success_rate.epoch.global": 0.6759854141343984,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9937688821752266,
      "tokens_p.mean_in_band": 0.6847098214285714,
      "tokens_rate.above_band": 0.8552971576227391,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14470284237726097
    },
    {
      "epoch": 0.6083776595744681,
      "grad_norm": 122.77511212718184,
      "learning_rate": 1.9226399293314007e-07,
      "loss": 0.7303,
      "step": 3660,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.44274809160305345,
      "success_rate.epoch.env.math": 0.8851851851851852,
      "success_rate.epoch.env.sat": 0.1016949152542373,
      "success_rate.epoch.env.science": 0.7302313071543841,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4914117085734958,
      "success_rate.epoch.global": 0.6763226366001734,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9999175461741425,
      "tokens_p.mean_in_band": 0.498046875,
      "tokens_rate.above_band": 0.9467110741049126,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05328892589508743
    },
    {
      "epoch": 0.6092087765957447,
      "grad_norm": 143.2044258195269,
      "learning_rate": 1.9224293522510458e-07,
      "loss": 0.6125,
      "step": 3665,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4420731707317073,
      "success_rate.epoch.env.math": 0.8851851851851852,
      "success_rate.epoch.env.sat": 0.1016949152542373,
      "success_rate.epoch.env.science": 0.730593607305936,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49138328850805996,
      "success_rate.epoch.global": 0.676485877664183,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9969251093294461,
      "tokens_p.mean_in_band": 0.47508138020833335,
      "tokens_rate.above_band": 0.8511166253101737,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1488833746898263
    },
    {
      "epoch": 0.6100398936170213,
      "grad_norm": 164.88449834660247,
      "learning_rate": 1.9222185578885845e-07,
      "loss": 0.5198,
      "step": 3670,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.441400304414003,
      "success_rate.epoch.env.math": 0.8851851851851852,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.730738255033557,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4912575796253448,
      "success_rate.epoch.global": 0.6762465373961218,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4166666666666667,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9983226102941176,
      "tokens_p.mean_in_band": 0.6216517857142857,
      "tokens_rate.above_band": 0.951048951048951,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04895104895104895
    },
    {
      "epoch": 0.6108710106382979,
      "grad_norm": 66.91480454845104,
      "learning_rate": 1.9220075466181254e-07,
      "loss": 0.4978,
      "step": 3675,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.441400304414003,
      "success_rate.epoch.env.math": 0.8851851851851852,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7311712677566337,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49129694441835176,
      "success_rate.epoch.global": 0.676582497405742,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9906639004149378,
      "tokens_p.mean_in_band": 0.70546875,
      "tokens_rate.above_band": 0.9796747967479674,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02032520325203252
    },
    {
      "epoch": 0.6117021276595744,
      "grad_norm": 99.20867828128162,
      "learning_rate": 1.9217963188141613e-07,
      "loss": 0.5511,
      "step": 3680,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.441400304414003,
      "success_rate.epoch.env.math": 0.8853267570900123,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7312633832976445,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49131818873160976,
      "success_rate.epoch.global": 0.676744989633725,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9877300613496932,
      "tokens_p.mean_in_band": 0.5225694444444444,
      "tokens_rate.above_band": 0.8190954773869347,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18090452261306533
    },
    {
      "epoch": 0.612533244680851,
      "grad_norm": 163.61691224293878,
      "learning_rate": 1.92158487485157e-07,
      "loss": 0.642,
      "step": 3685,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.44072948328267475,
      "success_rate.epoch.env.math": 0.8854679802955665,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7310879443998931,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49125409447492563,
      "success_rate.epoch.global": 0.6766177739430543,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.0001052188552189,
      "tokens_p.mean_in_band": 0.49451622596153844,
      "tokens_rate.above_band": 0.9580645161290322,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041935483870967745
    },
    {
      "epoch": 0.6133643617021277,
      "grad_norm": 173.99193286802117,
      "learning_rate": 1.921373215105613e-07,
      "loss": 0.4622,
      "step": 3690,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.44072948328267475,
      "success_rate.epoch.env.math": 0.8854679802955665,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7315185481718708,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49129324027237814,
      "success_rate.epoch.global": 0.6769522496121358,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9890202702702703,
      "tokens_p.mean_in_band": 0.8125,
      "tokens_rate.above_band": 0.961038961038961,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03896103896103896
    },
    {
      "epoch": 0.6141954787234043,
      "grad_norm": 107.5133753495482,
      "learning_rate": 1.921161339951934e-07,
      "loss": 0.5603,
      "step": 3695,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4409090909090909,
      "success_rate.epoch.env.math": 0.8856088560885609,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7316617764737263,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4913353958834023,
      "success_rate.epoch.global": 0.6770582156389942,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9947321428571428,
      "tokens_p.mean_in_band": 0.6891927083333333,
      "tokens_rate.above_band": 0.958904109589041,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0410958904109589
    },
    {
      "epoch": 0.6150265957446809,
      "grad_norm": 95.2283550244856,
      "learning_rate": 1.9209492497665603e-07,
      "loss": 0.6047,
      "step": 3700,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4409090909090909,
      "success_rate.epoch.env.math": 0.8857493857493858,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7314148681055156,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49132572509182176,
      "success_rate.epoch.global": 0.6769919118912407,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9940900259067358,
      "tokens_p.mean_in_band": 0.6203835227272727,
      "tokens_rate.above_band": 0.9212410501193318,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07875894988066826
    },
    {
      "epoch": 0.6158577127659575,
      "grad_norm": 75.2000304208048,
      "learning_rate": 1.920736944925899e-07,
      "loss": 0.5378,
      "step": 3705,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45985401459854014,
      "success_rate.epoch.env.logic": 0.4409090909090909,
      "success_rate.epoch.env.math": 0.8857493857493858,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.7317008251264306,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4913517211846323,
      "success_rate.epoch.global": 0.6772141014617369,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9958912768647282,
      "tokens_p.mean_below_band": 2.2118911147117615e-08,
      "tokens_p.mean_in_band": 0.5446671195652174,
      "tokens_rate.above_band": 0.9705521472392638,
      "tokens_rate.below_band": 0.001226993865030675,
      "tokens_rate.in_band": 0.02822085889570552
    },
    {
      "epoch": 0.616688829787234,
      "grad_norm": 162.23841033236585,
      "learning_rate": 1.9205244258067398e-07,
      "loss": 0.7912,
      "step": 3710,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4402420574886536,
      "success_rate.epoch.env.math": 0.8858895705521472,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7317202871576708,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4916230656086722,
      "success_rate.epoch.global": 0.6771423664777606,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9940029373368147,
      "tokens_p.mean_in_band": 0.5142435213414634,
      "tokens_rate.above_band": 0.9033018867924528,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09669811320754718
    },
    {
      "epoch": 0.6175199468085106,
      "grad_norm": 114.93962276721412,
      "learning_rate": 1.920311692786252e-07,
      "loss": 0.5944,
      "step": 3715,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4395770392749245,
      "success_rate.epoch.env.math": 0.8858895705521472,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7320053120849933,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4915885207644534,
      "success_rate.epoch.global": 0.6772477693891558,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9943773234200743,
      "tokens_p.mean_in_band": 0.6384055397727273,
      "tokens_rate.above_band": 0.9385903698534543,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061409630146545706
    },
    {
      "epoch": 0.6183510638297872,
      "grad_norm": 90.1475398015592,
      "learning_rate": 1.9200987462419843e-07,
      "loss": 0.6889,
      "step": 3720,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43891402714932126,
      "success_rate.epoch.env.math": 0.8860294117647058,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7322186836518046,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4915603571875232,
      "success_rate.epoch.global": 0.67735299159952,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.999224748966332,
      "tokens_p.mean_in_band": 0.5221047794117647,
      "tokens_rate.above_band": 0.952193475815523,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047806524184476944
    },
    {
      "epoch": 0.6191821808510638,
      "grad_norm": 73.21077156621745,
      "learning_rate": 1.9198855865518652e-07,
      "loss": 0.509,
      "step": 3725,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4397590361445783,
      "success_rate.epoch.env.math": 0.8863080684596577,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7325026511134677,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4916883238376934,
      "success_rate.epoch.global": 0.6777397260273973,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9948248407643312,
      "tokens_p.mean_below_band": 5.3085386753082275e-08,
      "tokens_p.mean_in_band": 0.490234375,
      "tokens_rate.above_band": 0.9874213836477987,
      "tokens_rate.below_band": 0.006289308176100629,
      "tokens_rate.in_band": 0.006289308176100629
    },
    {
      "epoch": 0.6200132978723404,
      "grad_norm": 161.44616468919048,
      "learning_rate": 1.9196722140942007e-07,
      "loss": 0.4854,
      "step": 3730,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4397590361445783,
      "success_rate.epoch.env.math": 0.8865853658536585,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7328567646280116,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4917457248293793,
      "success_rate.epoch.global": 0.6781255344621173,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9880845323741008,
      "tokens_p.mean_in_band": 0.7252604166666666,
      "tokens_rate.above_band": 0.86875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13125
    },
    {
      "epoch": 0.620844414893617,
      "grad_norm": 156.63237383293176,
      "learning_rate": 1.9194586292476743e-07,
      "loss": 0.5393,
      "step": 3735,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4397590361445783,
      "success_rate.epoch.env.math": 0.8867235079171741,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7325396825396825,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49172945755439623,
      "success_rate.epoch.global": 0.6780037600410186,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9927995391705069,
      "tokens_p.mean_below_band": 8.585629984736443e-10,
      "tokens_p.mean_in_band": 0.7116477272727273,
      "tokens_rate.above_band": 0.9041666666666667,
      "tokens_rate.below_band": 0.004166666666666667,
      "tokens_rate.in_band": 0.09166666666666666
    },
    {
      "epoch": 0.6216755319148937,
      "grad_norm": 187.7736773086645,
      "learning_rate": 1.9192448323913468e-07,
      "loss": 0.4984,
      "step": 3740,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4397590361445783,
      "success_rate.epoch.env.math": 0.8867235079171741,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.732892998678996,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4917615772034247,
      "success_rate.epoch.global": 0.6782786885245902,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.98125,
      "tokens_p.mean_in_band": 0.7797475961538461,
      "tokens_rate.above_band": 0.9022556390977443,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09774436090225563
    },
    {
      "epoch": 0.6225066489361702,
      "grad_norm": 103.11421192987977,
      "learning_rate": 1.9190308239046557e-07,
      "loss": 0.5473,
      "step": 3745,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4420289855072464,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.4397590361445783,
      "success_rate.epoch.env.math": 0.8871359223300971,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.7327700026406126,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49178788796474643,
      "success_rate.epoch.global": 0.6783825285787408,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9946120689655172,
      "tokens_p.mean_in_band": 0.7087053571428571,
      "tokens_rate.above_band": 0.9193083573487032,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08069164265129683
    },
    {
      "epoch": 0.6233377659574468,
      "grad_norm": 159.40804030395597,
      "learning_rate": 1.9188166041674136e-07,
      "loss": 0.6599,
      "step": 3750,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43909774436090226,
      "success_rate.epoch.env.math": 0.8871359223300971,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7330519651806912,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4914262694257123,
      "success_rate.epoch.global": 0.678254942058623,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.36,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9982612055641422,
      "tokens_p.mean_in_band": 0.5913514254385965,
      "tokens_rate.above_band": 0.9578090303478904,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04219096965210955
    },
    {
      "epoch": 0.6241688829787234,
      "grad_norm": 15644.068519740118,
      "learning_rate": 1.9186021735598078e-07,
      "loss": 0.6034,
      "step": 3755,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43909774436090226,
      "success_rate.epoch.env.math": 0.8871359223300971,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7332104292862787,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.491440675253493,
      "success_rate.epoch.global": 0.6784133469526727,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9862372819767442,
      "tokens_p.mean_in_band": 0.5831383689839572,
      "tokens_rate.above_band": 0.7862857142857143,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21371428571428572
    },
    {
      "epoch": 0.625,
      "grad_norm": 129.76246222390404,
      "learning_rate": 1.9183875324624e-07,
      "loss": 0.7045,
      "step": 3760,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43993993993993996,
      "success_rate.epoch.env.math": 0.8872727272727273,
      "success_rate.epoch.env.sat": 0.0995850622406639,
      "success_rate.epoch.env.science": 0.7335612835349816,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49152384952722344,
      "success_rate.epoch.global": 0.6786807208432506,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9924879807692307,
      "tokens_p.mean_in_band": 0.6262122844827587,
      "tokens_rate.above_band": 0.8776371308016878,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12236286919831224
    },
    {
      "epoch": 0.6258311170212766,
      "grad_norm": 64.69679973892326,
      "learning_rate": 1.9181726812561257e-07,
      "loss": 0.7835,
      "step": 3765,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43993993993993996,
      "success_rate.epoch.env.math": 0.8872727272727273,
      "success_rate.epoch.env.sat": 0.09917355371900827,
      "success_rate.epoch.env.science": 0.733841303205465,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49151189599529865,
      "success_rate.epoch.global": 0.6787837608289451,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.989453125,
      "tokens_p.mean_in_band": 0.5915364583333333,
      "tokens_rate.above_band": 0.8421052631578947,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15789473684210525
    },
    {
      "epoch": 0.6266622340425532,
      "grad_norm": 138.6439542434078,
      "learning_rate": 1.917957620322293e-07,
      "loss": 0.6185,
      "step": 3770,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43993993993993996,
      "success_rate.epoch.env.math": 0.8875453446191052,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.7340509320031504,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49189274607359584,
      "success_rate.epoch.global": 0.6791108094349227,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9896496815286624,
      "tokens_p.mean_in_band": 0.6415441176470589,
      "tokens_rate.above_band": 0.9022988505747126,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09770114942528736
    },
    {
      "epoch": 0.6274933510638298,
      "grad_norm": 101.2355630812104,
      "learning_rate": 1.9177423500425829e-07,
      "loss": 0.4772,
      "step": 3775,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.463768115942029,
      "success_rate.epoch.env.logic": 0.43993993993993996,
      "success_rate.epoch.env.math": 0.8875453446191052,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.7343995804929209,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4919244413908477,
      "success_rate.epoch.global": 0.6793828416412343,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9876302083333334,
      "tokens_p.mean_in_band": 0.8818359375,
      "tokens_rate.above_band": 0.972972972972973,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02702702702702703
    },
    {
      "epoch": 0.6283244680851063,
      "grad_norm": 65.2223923537964,
      "learning_rate": 1.9175268707990468e-07,
      "loss": 0.5602,
      "step": 3780,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.43993993993993996,
      "success_rate.epoch.env.math": 0.8876811594202898,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.7345549738219895,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49164760019670983,
      "success_rate.epoch.global": 0.6794784964442939,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9937316536203522,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.7114534198113207,
      "tokens_rate.above_band": 0.949814126394052,
      "tokens_rate.below_band": 0.0009293680297397769,
      "tokens_rate.in_band": 0.04925650557620818
    },
    {
      "epoch": 0.629155585106383,
      "grad_norm": 108.4156628420998,
      "learning_rate": 1.917311182974108e-07,
      "loss": 0.5019,
      "step": 3785,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.43993993993993996,
      "success_rate.epoch.env.math": 0.8880866425992779,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.7347632749149883,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49170339876689045,
      "success_rate.epoch.global": 0.6798037889039242,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9850206611570248,
      "tokens_p.mean_in_band": 0.76953125,
      "tokens_rate.above_band": 0.9029850746268657,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09701492537313433
    },
    {
      "epoch": 0.6299867021276596,
      "grad_norm": 90.50173293620142,
      "learning_rate": 1.917095286950559e-07,
      "loss": 0.4909,
      "step": 3790,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.43928035982008995,
      "success_rate.epoch.env.math": 0.8880866425992779,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.7351097178683386,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49163660065695675,
      "success_rate.epoch.global": 0.6798445683392464,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9951644974692697,
      "tokens_p.mean_in_band": 0.7150974025974026,
      "tokens_rate.above_band": 0.9472602739726027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05273972602739726
    },
    {
      "epoch": 0.6308178191489362,
      "grad_norm": 80.86148737903343,
      "learning_rate": 1.9168791831115632e-07,
      "loss": 0.6606,
      "step": 3795,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.43884892086330934,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.43928035982008995,
      "success_rate.epoch.env.math": 0.8882211538461539,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.735317149569303,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49166768637948777,
      "success_rate.epoch.global": 0.68006078001013,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9923406862745098,
      "tokens_p.mean_in_band": 0.5731336805555556,
      "tokens_rate.above_band": 0.85,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15
    },
    {
      "epoch": 0.6316489361702128,
      "grad_norm": 88.64463313960053,
      "learning_rate": 1.9166628718406513e-07,
      "loss": 0.6239,
      "step": 3800,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4357142857142857,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.43862275449101795,
      "success_rate.epoch.env.math": 0.8883553421368547,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.735263432446531,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49133025280583625,
      "success_rate.epoch.global": 0.6798785629954461,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9982160433070866,
      "tokens_p.mean_below_band": 8.754432201385498e-08,
      "tokens_p.mean_in_band": 0.516812193627451,
      "tokens_rate.above_band": 0.9670050761421319,
      "tokens_rate.below_band": 0.0006345177664974619,
      "tokens_rate.in_band": 0.03236040609137056
    },
    {
      "epoch": 0.6324800531914894,
      "grad_norm": 161.27649080880607,
      "learning_rate": 1.9164463535217228e-07,
      "loss": 0.6293,
      "step": 3805,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4357142857142857,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.43946188340807174,
      "success_rate.epoch.env.math": 0.888622754491018,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.735539343408025,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4914559302815373,
      "success_rate.epoch.global": 0.680256064690027,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9848214285714286,
      "tokens_p.mean_below_band": 4.731118679046631e-07,
      "tokens_p.mean_in_band": 0.1667052801724138,
      "tokens_rate.above_band": 0.30230326295585414,
      "tokens_rate.below_band": 0.0019193857965451055,
      "tokens_rate.in_band": 0.6957773512476008
    },
    {
      "epoch": 0.633311170212766,
      "grad_norm": 141.82728281625657,
      "learning_rate": 1.9162296285390452e-07,
      "loss": 0.4345,
      "step": 3810,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4357142857142857,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.44029850746268656,
      "success_rate.epoch.env.math": 0.8888888888888888,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.7358146798542425,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.4919315806913698,
      "success_rate.epoch.global": 0.6806864064602961,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9961062300319489,
      "tokens_p.mean_in_band": 0.8236177884615384,
      "tokens_rate.above_band": 0.9796557120500783,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02034428794992175
    },
    {
      "epoch": 0.6341422872340425,
      "grad_norm": 44.44347192656521,
      "learning_rate": 1.9160126972772515e-07,
      "loss": 0.3665,
      "step": 3815,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4326241134751773,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.44029850746268656,
      "success_rate.epoch.env.math": 0.8888888888888888,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.7357607282184655,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49164575124819837,
      "success_rate.epoch.global": 0.6805648957632818,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9934731012658228,
      "tokens_p.mean_in_band": 0.7404296875,
      "tokens_rate.above_band": 0.9693251533742331,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03067484662576687
    },
    {
      "epoch": 0.6349734042553191,
      "grad_norm": 101.34778655927114,
      "learning_rate": 1.9157955601213423e-07,
      "loss": 0.3338,
      "step": 3820,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4326241134751773,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.4396423248882265,
      "success_rate.epoch.env.math": 0.8890214797136038,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.7361038961038961,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49162934907871525,
      "success_rate.epoch.global": 0.6807724601175483,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9990834497206704,
      "tokens_p.mean_in_band": 0.6033528645833334,
      "tokens_rate.above_band": 0.9675675675675676,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.032432432432432434
    },
    {
      "epoch": 0.6358045212765957,
      "grad_norm": 96.80033436536117,
      "learning_rate": 1.9155782174566824e-07,
      "loss": 0.5536,
      "step": 3825,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4295774647887324,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.4396423248882265,
      "success_rate.epoch.env.math": 0.8890214797136038,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.7359273670557718,
      "success_rate.epoch.env.webshop": 0.2857142857142857,
      "success_rate.epoch.env_macro_mean": 0.49133633292102713,
      "success_rate.epoch.global": 0.6805905049488341,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.17857142857142858,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9995021446078431,
      "tokens_p.mean_in_band": 0.627197265625,
      "tokens_rate.above_band": 0.9532710280373832,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04672897196261682
    },
    {
      "epoch": 0.6366356382978723,
      "grad_norm": 91.36916820260075,
      "learning_rate": 1.9153606696690016e-07,
      "loss": 0.6951,
      "step": 3830,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.4396423248882265,
      "success_rate.epoch.env.math": 0.8890214797136038,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.736132711249352,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48783515294502605,
      "success_rate.epoch.global": 0.6805229634596044,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9973214285714286,
      "tokens_p.mean_in_band": 0.4593385686528497,
      "tokens_rate.above_band": 0.8886324293133295,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11136757068667051
    },
    {
      "epoch": 0.637466755319149,
      "grad_norm": 71.62693560785094,
      "learning_rate": 1.9151429171443947e-07,
      "loss": 0.4961,
      "step": 3835,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.44047619047619047,
      "success_rate.epoch.env.math": 0.8891537544696066,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.7362694300518134,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48759804863550066,
      "success_rate.epoch.global": 0.680509042196919,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9948992286638467,
      "tokens_p.mean_below_band": 1.4528632164001465e-07,
      "tokens_p.mean_in_band": 0.5574793198529412,
      "tokens_rate.above_band": 0.9215776198119697,
      "tokens_rate.below_band": 0.00045861041045631735,
      "tokens_rate.in_band": 0.07796376977757395
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 112.22480690159027,
      "learning_rate": 1.9149249602693181e-07,
      "loss": 0.5474,
      "step": 3840,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.44047619047619047,
      "success_rate.epoch.env.math": 0.8894173602853745,
      "success_rate.epoch.env.sat": 0.1016260162601626,
      "success_rate.epoch.env.science": 0.7364060072501295,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48759671981256575,
      "success_rate.epoch.global": 0.6806090011711561,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9932397959183673,
      "tokens_p.mean_in_band": 0.5771484375,
      "tokens_rate.above_band": 0.8477508650519031,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1522491349480969
    },
    {
      "epoch": 0.6391289893617021,
      "grad_norm": 226.38365982216172,
      "learning_rate": 1.914706799430593e-07,
      "loss": 0.5598,
      "step": 3845,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.44047619047619047,
      "success_rate.epoch.env.math": 0.8894173602853745,
      "success_rate.epoch.env.sat": 0.1016260162601626,
      "success_rate.epoch.env.science": 0.7368829154820367,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4876400751063755,
      "success_rate.epoch.global": 0.6809826203208557,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9802389705882353,
      "tokens_p.mean_in_band": 0.8001302083333334,
      "tokens_rate.above_band": 0.9006622516556292,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09933774834437085
    },
    {
      "epoch": 0.6399601063829787,
      "grad_norm": 120.31993467942212,
      "learning_rate": 1.9144884350154004e-07,
      "loss": 0.803,
      "step": 3850,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.4406528189910979,
      "success_rate.epoch.env.math": 0.8895486935866983,
      "success_rate.epoch.env.sat": 0.10121457489878542,
      "success_rate.epoch.env.science": 0.7370188581761818,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48764302630173906,
      "success_rate.epoch.global": 0.6809682804674457,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983684738955824,
      "tokens_p.mean_in_band": 0.6465320121951219,
      "tokens_rate.above_band": 0.9479695431472082,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05203045685279188
    },
    {
      "epoch": 0.6407912234042553,
      "grad_norm": 101.31314982561518,
      "learning_rate": 1.914269867411284e-07,
      "loss": 0.5003,
      "step": 3855,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.4414814814814815,
      "success_rate.epoch.env.math": 0.8898104265402843,
      "success_rate.epoch.env.sat": 0.10080645161290322,
      "success_rate.epoch.env.science": 0.7372903225806452,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4877297296256073,
      "success_rate.epoch.global": 0.6812270756918973,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9858732876712328,
      "tokens_p.mean_in_band": 0.6571969696969697,
      "tokens_rate.above_band": 0.8690476190476191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13095238095238096
    },
    {
      "epoch": 0.6416223404255319,
      "grad_norm": 106.63928488169368,
      "learning_rate": 1.9140510970061482e-07,
      "loss": 0.6351,
      "step": 3860,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.4414814814814815,
      "success_rate.epoch.env.math": 0.8900709219858156,
      "success_rate.epoch.env.sat": 0.10080645161290322,
      "success_rate.epoch.env.science": 0.7374935533780299,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48777188655678144,
      "success_rate.epoch.global": 0.6814925870398134,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.986359126984127,
      "tokens_p.mean_in_band": 0.765625,
      "tokens_rate.above_band": 0.8936170212765957,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10638297872340426
    },
    {
      "epoch": 0.6424534574468085,
      "grad_norm": 96.55301546646024,
      "learning_rate": 1.913832124188256e-07,
      "loss": 0.7434,
      "step": 3865,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.4408284023668639,
      "success_rate.epoch.env.math": 0.8902007083825265,
      "success_rate.epoch.env.sat": 0.10080645161290322,
      "success_rate.epoch.env.science": 0.7378315735256246,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48775504359584404,
      "success_rate.epoch.global": 0.6816971713810316,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952064896755162,
      "tokens_p.mean_below_band": 6.230038707144558e-11,
      "tokens_p.mean_in_band": 0.5353954081632653,
      "tokens_rate.above_band": 0.9313186813186813,
      "tokens_rate.below_band": 0.0013736263736263737,
      "tokens_rate.in_band": 0.0673076923076923
    },
    {
      "epoch": 0.6432845744680851,
      "grad_norm": 144.2228275344213,
      "learning_rate": 1.9136129493462309e-07,
      "loss": 0.6964,
      "step": 3870,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.4408284023668639,
      "success_rate.epoch.env.math": 0.8902007083825265,
      "success_rate.epoch.env.sat": 0.10040160642570281,
      "success_rate.epoch.env.science": 0.73823605039856,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4881000850757243,
      "success_rate.epoch.global": 0.6819541375872383,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9892592592592593,
      "tokens_p.mean_in_band": 0.7662464488636364,
      "tokens_rate.above_band": 0.8846657929226737,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11533420707732635
    },
    {
      "epoch": 0.6441156914893617,
      "grad_norm": 65.89080473833339,
      "learning_rate": 1.913393572869055e-07,
      "loss": 0.5515,
      "step": 3875,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.4410029498525074,
      "success_rate.epoch.env.math": 0.8903301886792453,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7379912663755459,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4880689611969648,
      "success_rate.epoch.global": 0.6817125788250913,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9902912621359223,
      "tokens_p.mean_below_band": 1.6079866327345371e-09,
      "tokens_p.mean_in_band": 0.72109375,
      "tokens_rate.above_band": 0.8704225352112676,
      "tokens_rate.below_band": 0.0028169014084507044,
      "tokens_rate.in_band": 0.1267605633802817
    },
    {
      "epoch": 0.6449468085106383,
      "grad_norm": 145.92265464986508,
      "learning_rate": 1.9131739951460672e-07,
      "loss": 0.4791,
      "step": 3880,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.4410029498525074,
      "success_rate.epoch.env.math": 0.8903301886792453,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7380035925070567,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4880700817543748,
      "success_rate.epoch.global": 0.6817578772802654,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9855769230769231,
      "tokens_p.mean_in_band": 0.69375,
      "tokens_rate.above_band": 0.9122807017543859,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08771929824561403
    },
    {
      "epoch": 0.6457779255319149,
      "grad_norm": 68.93279303730233,
      "learning_rate": 1.9129542165669648e-07,
      "loss": 0.5836,
      "step": 3885,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.4410029498525074,
      "success_rate.epoch.env.math": 0.8905882352941177,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7382051282051282,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4881118619646424,
      "success_rate.epoch.global": 0.6820215410107705,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994921875,
      "tokens_p.mean_in_band": 0.8056640625,
      "tokens_rate.above_band": 0.975609756097561,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024390243902439025
    },
    {
      "epoch": 0.6466090425531915,
      "grad_norm": 85.7485280071227,
      "learning_rate": 1.9127342375218e-07,
      "loss": 0.4951,
      "step": 3890,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42657342657342656,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8909730363423212,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7384733606557377,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48845243294240837,
      "success_rate.epoch.global": 0.6823295830575777,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.997413217623498,
      "tokens_p.mean_in_band": 0.7876674107142857,
      "tokens_rate.above_band": 0.981651376146789,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01834862385321101
    },
    {
      "epoch": 0.6474401595744681,
      "grad_norm": 58.550751599675415,
      "learning_rate": 1.9125140584009825e-07,
      "loss": 0.5233,
      "step": 3895,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4236111111111111,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8912280701754386,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.7388078792530058,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4882005084509146,
      "success_rate.epoch.global": 0.682471501734677,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9989583333333333,
      "tokens_p.mean_in_band": 0.6354325457317073,
      "tokens_rate.above_band": 0.9500609013398295,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049939098660170524
    },
    {
      "epoch": 0.6482712765957447,
      "grad_norm": 108.31204408618932,
      "learning_rate": 1.912293679595276e-07,
      "loss": 0.5418,
      "step": 3900,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4236111111111111,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8912280701754386,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.7390081799591002,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4882187176060141,
      "success_rate.epoch.global": 0.6826287978863936,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9990649606299212,
      "tokens_p.mean_in_band": 0.6065027573529411,
      "tokens_rate.above_band": 0.9491778774289985,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05082212257100149
    },
    {
      "epoch": 0.6491023936170213,
      "grad_norm": 87.44474154576085,
      "learning_rate": 1.912073101495799e-07,
      "loss": 0.6512,
      "step": 3905,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4236111111111111,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8913551401869159,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.7394078611536499,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4882666040792893,
      "success_rate.epoch.global": 0.6829952168893287,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9930862831858407,
      "tokens_p.mean_in_band": 0.677734375,
      "tokens_rate.above_band": 0.9890590809628009,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010940919037199124
    },
    {
      "epoch": 0.6499335106382979,
      "grad_norm": 74.53925459060798,
      "learning_rate": 1.9118523244940233e-07,
      "loss": 0.4681,
      "step": 3910,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4236111111111111,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8913551401869159,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.7393630573248408,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48826253100394296,
      "success_rate.epoch.global": 0.6830313014827019,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.7380952380952381,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982358870967742,
      "tokens_p.mean_in_band": 0.6105385638297872,
      "tokens_rate.above_band": 0.9405815423514539,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05941845764854614
    },
    {
      "epoch": 0.6507646276595744,
      "grad_norm": 182.68350725199667,
      "learning_rate": 1.9116313489817744e-07,
      "loss": 0.5028,
      "step": 3915,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.42758620689655175,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8914819136522754,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.7396284041740901,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48865955064940203,
      "success_rate.epoch.global": 0.6833443054641212,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9949152542372881,
      "tokens_p.mean_in_band": 0.8297991071428571,
      "tokens_rate.above_band": 0.9768211920529801,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023178807947019868
    },
    {
      "epoch": 0.651595744680851,
      "grad_norm": 109.99655061927714,
      "learning_rate": 1.9114101753512292e-07,
      "loss": 0.6521,
      "step": 3920,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4315068493150685,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4652777777777778,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8914819136522754,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.7395727365208545,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.488715121923183,
      "success_rate.epoch.global": 0.6832757770103601,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4285714285714286,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9901678356713427,
      "tokens_p.mean_in_band": 0.721448131443299,
      "tokens_rate.above_band": 0.9114155251141552,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08858447488584476
    },
    {
      "epoch": 0.6524268617021277,
      "grad_norm": 293.44204816833684,
      "learning_rate": 1.9111888039949173e-07,
      "loss": 0.4753,
      "step": 3925,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4315068493150685,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4652777777777778,
      "success_rate.epoch.env.logic": 0.44035346097201766,
      "success_rate.epoch.env.math": 0.8916083916083916,
      "success_rate.epoch.env.sat": 0.0992063492063492,
      "success_rate.epoch.env.science": 0.7397712833545108,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4887087383205124,
      "success_rate.epoch.global": 0.683371672691423,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9880401234567902,
      "tokens_p.mean_in_band": 0.6696134868421053,
      "tokens_rate.above_band": 0.8950276243093923,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10497237569060773
    },
    {
      "epoch": 0.6532579787234043,
      "grad_norm": 386.87634800785116,
      "learning_rate": 1.910967235305718e-07,
      "loss": 0.6982,
      "step": 3930,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4315068493150685,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4689655172413793,
      "success_rate.epoch.env.logic": 0.43970588235294117,
      "success_rate.epoch.env.math": 0.8916083916083916,
      "success_rate.epoch.env.sat": 0.0992063492063492,
      "success_rate.epoch.env.science": 0.7399034798069596,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4889971344384192,
      "success_rate.epoch.global": 0.683415435139573,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9969915305873751,
      "tokens_p.mean_below_band": 8.866190910339355e-07,
      "tokens_p.mean_in_band": 0.5332154605263157,
      "tokens_rate.above_band": 0.945173923059203,
      "tokens_rate.below_band": 0.0001151808339092375,
      "tokens_rate.in_band": 0.05471089610688781
    },
    {
      "epoch": 0.6540890957446809,
      "grad_norm": 249.61237126243276,
      "learning_rate": 1.9107454696768623e-07,
      "loss": 0.5429,
      "step": 3935,
      "success_rate.epoch.env.abd": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:alfworld": 0.4315068493150685,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4689655172413793,
      "success_rate.epoch.env.logic": 0.43841642228739003,
      "success_rate.epoch.env.math": 0.8916083916083916,
      "success_rate.epoch.env.sat": 0.0992063492063492,
      "success_rate.epoch.env.science": 0.7399137274803349,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48888084240276675,
      "success_rate.epoch.global": 0.6832349081364829,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976532567049808,
      "tokens_p.mean_in_band": 0.6016090029761905,
      "tokens_rate.above_band": 0.9688195991091314,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.031180400890868598
    },
    {
      "epoch": 0.6549202127659575,
      "grad_norm": 139.10537974662594,
      "learning_rate": 1.9105235075019292e-07,
      "loss": 0.4462,
      "step": 3940,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4315068493150685,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4689655172413793,
      "success_rate.epoch.env.logic": 0.43841642228739003,
      "success_rate.epoch.env.math": 0.8916083916083916,
      "success_rate.epoch.env.sat": 0.10276679841897234,
      "success_rate.epoch.env.science": 0.7401115618661258,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.488272235305125,
      "success_rate.epoch.global": 0.683330601540731,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9884143286573146,
      "tokens_p.mean_in_band": 0.7771080280172413,
      "tokens_rate.above_band": 0.895870736086176,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10412926391382406
    },
    {
      "epoch": 0.655751329787234,
      "grad_norm": 640.7779559156587,
      "learning_rate": 1.9103013491748472e-07,
      "loss": 0.5635,
      "step": 3945,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4657534246575342,
      "success_rate.epoch.env.logic": 0.43841642228739003,
      "success_rate.epoch.env.math": 0.8916083916083916,
      "success_rate.epoch.env.sat": 0.10276679841897234,
      "success_rate.epoch.env.science": 0.7399898631525595,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4883207361276144,
      "success_rate.epoch.global": 0.6832104832104832,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9880862329803328,
      "tokens_p.mean_below_band": 3.413297235965729e-07,
      "tokens_p.mean_in_band": 0.6906184348739496,
      "tokens_rate.above_band": 0.8452685421994884,
      "tokens_rate.below_band": 0.0025575447570332483,
      "tokens_rate.in_band": 0.15217391304347827
    },
    {
      "epoch": 0.6565824468085106,
      "grad_norm": 171.08655331607352,
      "learning_rate": 1.910078995089893e-07,
      "loss": 0.5363,
      "step": 3950,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4657534246575342,
      "success_rate.epoch.env.logic": 0.43841642228739003,
      "success_rate.epoch.env.math": 0.8917345750873108,
      "success_rate.epoch.env.sat": 0.10196078431372549,
      "success_rate.epoch.env.science": 0.7400557385355967,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48826492201458804,
      "success_rate.epoch.global": 0.6830905221803896,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9956268221574344,
      "tokens_p.mean_in_band": 0.6408991228070176,
      "tokens_rate.above_band": 0.8575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1425
    },
    {
      "epoch": 0.6574135638297872,
      "grad_norm": 94.74577963310192,
      "learning_rate": 1.9098564456416907e-07,
      "loss": 0.593,
      "step": 3955,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43841642228739003,
      "success_rate.epoch.env.math": 0.891860465116279,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.7401215805471124,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48421160798979845,
      "success_rate.epoch.global": 0.6829108748977923,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9968823070927514,
      "tokens_p.mean_below_band": 1.418811734765768e-09,
      "tokens_p.mean_in_band": 0.6426886792452831,
      "tokens_rate.above_band": 0.9596110695587136,
      "tokens_rate.below_band": 0.0007479431563201197,
      "tokens_rate.in_band": 0.039640987284966345
    },
    {
      "epoch": 0.6582446808510638,
      "grad_norm": 102.38102897865964,
      "learning_rate": 1.9096337012252107e-07,
      "loss": 0.4952,
      "step": 3960,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43841642228739003,
      "success_rate.epoch.env.math": 0.8921113689095128,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.7403846153846154,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4842583296835018,
      "success_rate.epoch.global": 0.6832216958013396,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7619047619047619,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9856687898089171,
      "tokens_p.mean_below_band": 3.4051481634378433e-09,
      "tokens_p.mean_in_band": 0.677734375,
      "tokens_rate.above_band": 0.9691358024691358,
      "tokens_rate.below_band": 0.006172839506172839,
      "tokens_rate.in_band": 0.024691358024691357
    },
    {
      "epoch": 0.6590757978723404,
      "grad_norm": 140.89190384657059,
      "learning_rate": 1.9094107622357705e-07,
      "loss": 0.5041,
      "step": 3965,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4377745241581259,
      "success_rate.epoch.env.math": 0.8910776361529548,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.7405815423514539,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48412390205450323,
      "success_rate.epoch.global": 0.6831537708129285,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995164641943734,
      "tokens_p.mean_in_band": 0.6110983455882353,
      "tokens_rate.above_band": 0.9583333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041666666666666664
    },
    {
      "epoch": 0.659906914893617,
      "grad_norm": 126.38315906716801,
      "learning_rate": 1.9091876290690317e-07,
      "loss": 0.591,
      "step": 3970,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4371345029239766,
      "success_rate.epoch.env.math": 0.8912037037037037,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.74077817079333,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48409505430527383,
      "success_rate.epoch.global": 0.6832490621432067,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9975,
      "tokens_p.mean_in_band": 0.5703876201923077,
      "tokens_rate.above_band": 0.9600614439324117,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039938556067588324
    },
    {
      "epoch": 0.6607380319148937,
      "grad_norm": 123.67867687147924,
      "learning_rate": 1.9089643021210006e-07,
      "loss": 0.6887,
      "step": 3975,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4371345029239766,
      "success_rate.epoch.env.math": 0.8912037037037037,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.7410398788490661,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4840478264204319,
      "success_rate.epoch.global": 0.6832328499266743,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9948694029850746,
      "tokens_p.mean_in_band": 0.6282848011363636,
      "tokens_rate.above_band": 0.8204081632653061,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17959183673469387
    },
    {
      "epoch": 0.6615691489361702,
      "grad_norm": 101.74676999248933,
      "learning_rate": 1.9087407817880287e-07,
      "loss": 0.5793,
      "step": 3980,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43731778425655976,
      "success_rate.epoch.env.math": 0.8912037037037037,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.7410489157841654,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48406530989931207,
      "success_rate.epoch.global": 0.6832166693797819,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.7380952380952381,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9931483957219251,
      "tokens_p.mean_below_band": 1.318767317570746e-10,
      "tokens_p.mean_in_band": 0.59796142578125,
      "tokens_rate.above_band": 0.9577464788732394,
      "tokens_rate.below_band": 0.0012804097311139564,
      "tokens_rate.in_band": 0.040973111395646605
    },
    {
      "epoch": 0.6624002659574468,
      "grad_norm": 103.0603904471768,
      "learning_rate": 1.9085170684668094e-07,
      "loss": 0.5177,
      "step": 3985,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43731778425655976,
      "success_rate.epoch.env.math": 0.8912037037037037,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.7413098236775819,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4840890287987136,
      "success_rate.epoch.global": 0.6834228078737595,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9912551440329218,
      "tokens_p.mean_in_band": 0.7557870370370371,
      "tokens_rate.above_band": 0.9,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1
    },
    {
      "epoch": 0.6632313829787234,
      "grad_norm": 98.10774888228319,
      "learning_rate": 1.908293162554379e-07,
      "loss": 0.6219,
      "step": 3990,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4366812227074236,
      "success_rate.epoch.env.math": 0.8913294797687862,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.741570206341218,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4840662649059484,
      "success_rate.epoch.global": 0.6835689907362262,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992447129909365,
      "tokens_p.mean_in_band": 0.644287109375,
      "tokens_rate.above_band": 0.976401179941003,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02359882005899705
    },
    {
      "epoch": 0.6640625,
      "grad_norm": 199.4790131893835,
      "learning_rate": 1.9080690644481157e-07,
      "loss": 0.5238,
      "step": 3995,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4366812227074236,
      "success_rate.epoch.env.math": 0.8905529953917051,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.7412622579834046,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.483967680111867,
      "success_rate.epoch.global": 0.68339016074038,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9889520202020202,
      "tokens_p.mean_in_band": 0.603125,
      "tokens_rate.above_band": 0.868421052631579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13157894736842105
    },
    {
      "epoch": 0.6648936170212766,
      "grad_norm": 293.33099379260904,
      "learning_rate": 1.9078447745457387e-07,
      "loss": 0.3631,
      "step": 4000,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4366812227074236,
      "success_rate.epoch.env.math": 0.8908045977011494,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.7415871421396283,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48402008797238233,
      "success_rate.epoch.global": 0.6837495945507622,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9904255319148936,
      "tokens_p.mean_in_band": 0.5379464285714286,
      "tokens_rate.above_band": 0.91796875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08203125
    },
    {
      "epoch": 0.6657247340425532,
      "grad_norm": 105.69049519167355,
      "learning_rate": 1.9076202932453077e-07,
      "loss": 0.4943,
      "step": 4005,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4366812227074236,
      "success_rate.epoch.env.math": 0.8908045977011494,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7419759277833501,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4840203320867115,
      "success_rate.epoch.global": 0.6839462173983476,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9895833333333334,
      "tokens_p.mean_in_band": 0.7537802419354839,
      "tokens_rate.above_band": 0.848780487804878,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15121951219512195
    },
    {
      "epoch": 0.6665558510638298,
      "grad_norm": 132.2764567849794,
      "learning_rate": 1.9073956209452218e-07,
      "loss": 0.5579,
      "step": 4010,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43537414965986393,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.436046511627907,
      "success_rate.epoch.env.math": 0.8908045977011494,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.7421052631578947,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.483974388840805,
      "success_rate.epoch.global": 0.6839378238341969,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.20833333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.986351569713758,
      "tokens_p.mean_in_band": 0.5285650589330024,
      "tokens_rate.above_band": 0.7288021534320323,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2711978465679677
    },
    {
      "epoch": 0.6673869680851063,
      "grad_norm": 111.09571279472186,
      "learning_rate": 1.9071707580442196e-07,
      "loss": 0.6301,
      "step": 4015,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43623188405797103,
      "success_rate.epoch.env.math": 0.8908045977011494,
      "success_rate.epoch.env.sat": 0.09961685823754789,
      "success_rate.epoch.env.science": 0.7421131697546319,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4843039503675027,
      "success_rate.epoch.global": 0.6838615782664942,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0000566123188406,
      "tokens_p.mean_in_band": 0.5877130681818182,
      "tokens_rate.above_band": 0.9616724738675958,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03832752613240418
    },
    {
      "epoch": 0.668218085106383,
      "grad_norm": 85.2019425538384,
      "learning_rate": 1.9069457049413774e-07,
      "loss": 0.5406,
      "step": 4020,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4370477568740955,
      "success_rate.epoch.env.math": 0.8908045977011494,
      "success_rate.epoch.env.sat": 0.09961685823754789,
      "success_rate.epoch.env.science": 0.7421855463865966,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48438470031732894,
      "success_rate.epoch.global": 0.6840064620355412,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.0006323433420365,
      "tokens_p.mean_in_band": 0.6402994791666666,
      "tokens_rate.above_band": 0.9909443725743855,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009055627425614488
    },
    {
      "epoch": 0.6690492021276596,
      "grad_norm": 188.8013827027474,
      "learning_rate": 1.9067204620361098e-07,
      "loss": 0.5383,
      "step": 4025,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43641618497109824,
      "success_rate.epoch.env.math": 0.8909299655568312,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.74225,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48465695726669655,
      "success_rate.epoch.global": 0.6840490797546013,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7916666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9975243506493506,
      "tokens_p.mean_below_band": 2.868473529815674e-07,
      "tokens_p.mean_in_band": 0.7132161458333334,
      "tokens_rate.above_band": 0.9685534591194969,
      "tokens_rate.below_band": 0.0012578616352201257,
      "tokens_rate.in_band": 0.03018867924528302
    },
    {
      "epoch": 0.6698803191489362,
      "grad_norm": 102.0986881966108,
      "learning_rate": 1.906495029728167e-07,
      "loss": 0.4231,
      "step": 4030,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43641618497109824,
      "success_rate.epoch.env.math": 0.8909299655568312,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7427002745195908,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4846978913139321,
      "success_rate.epoch.global": 0.6844057410095146,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9860819327731093,
      "tokens_p.mean_in_band": 0.7477678571428571,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05555555555555555
    },
    {
      "epoch": 0.6707114361702128,
      "grad_norm": 106.92810365587096,
      "learning_rate": 1.9062694084176369e-07,
      "loss": 0.6378,
      "step": 4035,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.43641618497109824,
      "success_rate.epoch.env.math": 0.8911798396334479,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7428286355699676,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.484732276325477,
      "success_rate.epoch.global": 0.6846091861402095,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9979983987189752,
      "tokens_p.mean_in_band": 0.23298816568047337,
      "tokens_rate.above_band": 0.7870195337114052,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21298046628859482
    },
    {
      "epoch": 0.6715425531914894,
      "grad_norm": 45.515915553187185,
      "learning_rate": 1.9060435985049412e-07,
      "loss": 0.5529,
      "step": 4040,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.4357864357864358,
      "success_rate.epoch.env.math": 0.8913043478260869,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7430209371884346,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4847038272915173,
      "success_rate.epoch.global": 0.6847020933977456,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970544918998527,
      "tokens_p.mean_in_band": 0.5982142857142857,
      "tokens_rate.above_band": 0.9603960396039604,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039603960396039604
    },
    {
      "epoch": 0.672373670212766,
      "grad_norm": 100.32203937573648,
      "learning_rate": 1.905817600390838e-07,
      "loss": 0.6918,
      "step": 4045,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.4357864357864358,
      "success_rate.epoch.env.math": 0.8914285714285715,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7429708882806668,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48503649934293996,
      "success_rate.epoch.global": 0.6848367904807847,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9959615384615385,
      "tokens_p.mean_below_band": 3.0547380447387695e-07,
      "tokens_p.mean_in_band": 0.7211371527777778,
      "tokens_rate.above_band": 0.9447674418604651,
      "tokens_rate.below_band": 0.0029069767441860465,
      "tokens_rate.in_band": 0.05232558139534884
    },
    {
      "epoch": 0.6732047872340425,
      "grad_norm": 106.78735977629269,
      "learning_rate": 1.905591414476418e-07,
      "loss": 0.5212,
      "step": 4050,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.4357864357864358,
      "success_rate.epoch.env.math": 0.8914285714285715,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7430987316587914,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.485048121468224,
      "success_rate.epoch.global": 0.6849887495981999,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9951105937136205,
      "tokens_p.mean_in_band": 0.5305278675766284,
      "tokens_rate.above_band": 0.8916337969690679,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10836620303093211
    },
    {
      "epoch": 0.6740359042553191,
      "grad_norm": 109.54933582165962,
      "learning_rate": 1.9053650411631063e-07,
      "loss": 0.4465,
      "step": 4055,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.4365994236311239,
      "success_rate.epoch.env.math": 0.8916761687571265,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7428571428571429,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48512257568382355,
      "success_rate.epoch.global": 0.6850216728206775,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9876237623762376,
      "tokens_p.mean_in_band": 0.638671875,
      "tokens_rate.above_band": 0.926605504587156,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07339449541284404
    },
    {
      "epoch": 0.6748670212765957,
      "grad_norm": 120.08273657092438,
      "learning_rate": 1.9051384808526595e-07,
      "loss": 0.4838,
      "step": 4060,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.4367816091954023,
      "success_rate.epoch.env.math": 0.8916761687571265,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7428642343013154,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4851397826845918,
      "success_rate.epoch.global": 0.6850040096230954,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4523809523809524,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9994904891304348,
      "tokens_p.mean_in_band": 0.5050027412280702,
      "tokens_rate.above_band": 0.9281210592686002,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07187894073139975
    },
    {
      "epoch": 0.6756981382978723,
      "grad_norm": 210.45913665194897,
      "learning_rate": 1.9049117339471675e-07,
      "loss": 0.4688,
      "step": 4065,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.43615494978479197,
      "success_rate.epoch.env.math": 0.8917995444191344,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7428713116786512,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4850946730144766,
      "success_rate.epoch.global": 0.6849863803877584,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.999384236453202,
      "tokens_p.mean_below_band": 6.693881005048752e-10,
      "tokens_p.mean_in_band": 0.6322443181818181,
      "tokens_rate.above_band": 0.9157894736842105,
      "tokens_rate.below_band": 0.0015037593984962407,
      "tokens_rate.in_band": 0.08270676691729323
    },
    {
      "epoch": 0.676529255319149,
      "grad_norm": 1694.8536667082376,
      "learning_rate": 1.9046848008490494e-07,
      "loss": 0.5703,
      "step": 4070,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.4357142857142857,
      "success_rate.epoch.env.math": 0.8919226393629124,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7430624380574826,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48508317821921326,
      "success_rate.epoch.global": 0.6850192061459667,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.997749162479062,
      "tokens_p.mean_in_band": 0.5606897865853658,
      "tokens_rate.above_band": 0.9668016194331984,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03319838056680162
    },
    {
      "epoch": 0.6773603723404256,
      "grad_norm": 103.43872808155407,
      "learning_rate": 1.9044576819610567e-07,
      "loss": 0.5774,
      "step": 4075,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.4357142857142857,
      "success_rate.epoch.env.math": 0.8920454545454546,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7433803513981687,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48512324444859767,
      "success_rate.epoch.global": 0.6853213943076432,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9860248447204969,
      "tokens_p.mean_in_band": 0.6422991071428571,
      "tokens_rate.above_band": 0.9583333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041666666666666664
    },
    {
      "epoch": 0.6781914893617021,
      "grad_norm": 150.63548353513985,
      "learning_rate": 1.9042303776862693e-07,
      "loss": 0.5108,
      "step": 4080,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8920454545454546,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7436974789915967,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4850955686811588,
      "success_rate.epoch.global": 0.6854632587859425,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9990693573667712,
      "tokens_p.mean_in_band": 0.6998487903225806,
      "tokens_rate.above_band": 0.953662182361734,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04633781763826607
    },
    {
      "epoch": 0.6790226063829787,
      "grad_norm": 163.39862280927537,
      "learning_rate": 1.904002888428097e-07,
      "loss": 0.4932,
      "step": 4085,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8920454545454546,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7435770750988142,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.485084622872724,
      "success_rate.epoch.global": 0.6854040242733951,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950079872204473,
      "tokens_p.mean_below_band": 9.255018085241318e-09,
      "tokens_p.mean_in_band": 0.7715692934782609,
      "tokens_rate.above_band": 0.9287833827893175,
      "tokens_rate.below_band": 0.002967359050445104,
      "tokens_rate.in_band": 0.06824925816023739
    },
    {
      "epoch": 0.6798537234042553,
      "grad_norm": 127.01809273104085,
      "learning_rate": 1.9037752145902772e-07,
      "loss": 0.4974,
      "step": 4090,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.4391891891891892,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8920454545454546,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7437669711182424,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4851018861472175,
      "success_rate.epoch.global": 0.6855546687948922,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0001947040498442,
      "tokens_p.mean_in_band": 0.5637276785714286,
      "tokens_rate.above_band": 0.948301329394387,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.051698670605613
    },
    {
      "epoch": 0.6806848404255319,
      "grad_norm": 91.43701807536345,
      "learning_rate": 1.9035473565768752e-07,
      "loss": 0.6868,
      "step": 4095,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47297297297297297,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8920454545454546,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.7436529455262509,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4848235585069515,
      "success_rate.epoch.global": 0.6854272959183674,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9899649784482759,
      "tokens_p.mean_in_band": 0.4842621026011561,
      "tokens_rate.above_band": 0.728414442700157,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.271585557299843
    },
    {
      "epoch": 0.6815159574468085,
      "grad_norm": 109.57505582230853,
      "learning_rate": 1.9033193147922832e-07,
      "loss": 0.5969,
      "step": 4100,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8921679909194098,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.7438423645320197,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4845277223222736,
      "success_rate.epoch.global": 0.6854093660401401,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.994237385321101,
      "tokens_p.mean_in_band": 0.7079093992248062,
      "tokens_rate.above_band": 0.8941755537325676,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10582444626743231
    },
    {
      "epoch": 0.6823470744680851,
      "grad_norm": 82.24666777988774,
      "learning_rate": 1.9030910896412197e-07,
      "loss": 0.4774,
      "step": 4105,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8922902494331065,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.7440315038149151,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4845560312128729,
      "success_rate.epoch.global": 0.6856096784463547,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9970738295318127,
      "tokens_p.mean_below_band": 2.7008354663848877e-07,
      "tokens_p.mean_in_band": 0.7067708333333333,
      "tokens_rate.above_band": 0.9476678043230944,
      "tokens_rate.below_band": 0.0011376564277588168,
      "tokens_rate.in_band": 0.051194539249146756
    },
    {
      "epoch": 0.6831781914893617,
      "grad_norm": 79.78910842548002,
      "learning_rate": 1.9028626815287283e-07,
      "loss": 0.5331,
      "step": 4110,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.43509272467902993,
      "success_rate.epoch.env.math": 0.8924122310305775,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.7441002949852508,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48457337419176444,
      "success_rate.epoch.global": 0.6857506361323156,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9860668789808917,
      "tokens_p.mean_in_band": 0.810302734375,
      "tokens_rate.above_band": 0.8971428571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10285714285714286
    },
    {
      "epoch": 0.6840093085106383,
      "grad_norm": 84.37397367831892,
      "learning_rate": 1.9026340908601772e-07,
      "loss": 0.5112,
      "step": 4115,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.4358974358974359,
      "success_rate.epoch.env.math": 0.8927765237020316,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.7441631850577537,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4846853645519792,
      "success_rate.epoch.global": 0.6860003178134435,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9939720812182741,
      "tokens_p.mean_in_band": 0.6252055921052632,
      "tokens_rate.above_band": 0.9120370370370371,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08796296296296297
    },
    {
      "epoch": 0.6848404255319149,
      "grad_norm": 104.32115444110507,
      "learning_rate": 1.9024053180412592e-07,
      "loss": 0.5015,
      "step": 4120,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.4358974358974359,
      "success_rate.epoch.env.math": 0.8927765237020316,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.744351669941061,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4850115003688646,
      "success_rate.epoch.global": 0.6861997776719072,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9893364928909952,
      "tokens_p.mean_in_band": 0.7386067708333334,
      "tokens_rate.above_band": 0.8978723404255319,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10212765957446808
    },
    {
      "epoch": 0.6856715425531915,
      "grad_norm": 226.9499489073709,
      "learning_rate": 1.9021763634779897e-07,
      "loss": 0.5772,
      "step": 4125,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.4358974358974359,
      "success_rate.epoch.env.math": 0.8927765237020316,
      "success_rate.epoch.env.sat": 0.10566037735849057,
      "success_rate.epoch.env.science": 0.7445398773006136,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48499222570135886,
      "success_rate.epoch.global": 0.6862402793207427,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9940599173553719,
      "tokens_p.mean_in_band": 0.7047697368421053,
      "tokens_rate.above_band": 0.9502617801047121,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049738219895287955
    },
    {
      "epoch": 0.6865026595744681,
      "grad_norm": 100.18664374400898,
      "learning_rate": 1.9019472275767072e-07,
      "loss": 0.4131,
      "step": 4130,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4697986577181208,
      "success_rate.epoch.env.logic": 0.4358974358974359,
      "success_rate.epoch.env.math": 0.8927765237020316,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7447903898014219,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48497888870472744,
      "success_rate.epoch.global": 0.6863304789089756,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9918846899224806,
      "tokens_p.mean_in_band": 0.5349702380952381,
      "tokens_rate.above_band": 0.9247311827956989,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07526881720430108
    },
    {
      "epoch": 0.6873337765957447,
      "grad_norm": 40.22069364599915,
      "learning_rate": 1.9017179107440719e-07,
      "loss": 0.4693,
      "step": 4135,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.4366998577524893,
      "success_rate.epoch.env.math": 0.8928974069898534,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7451028403525954,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4854125642782966,
      "success_rate.epoch.global": 0.6867279062401014,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9955968688845401,
      "tokens_p.mean_in_band": 0.7885044642857143,
      "tokens_rate.above_band": 0.9864864864864865,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013513513513513514
    },
    {
      "epoch": 0.6881648936170213,
      "grad_norm": 183.06213638135222,
      "learning_rate": 1.9014884133870642e-07,
      "loss": 0.4633,
      "step": 4140,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.4366998577524893,
      "success_rate.epoch.env.math": 0.8928974069898534,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.7452276064610867,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48542390665179586,
      "success_rate.epoch.global": 0.6868271057631412,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982069672131147,
      "tokens_p.mean_below_band": 1.0408340855860843e-15,
      "tokens_p.mean_in_band": 0.5863486842105263,
      "tokens_rate.above_band": 0.9682539682539683,
      "tokens_rate.below_band": 0.0015873015873015873,
      "tokens_rate.in_band": 0.03015873015873016
    },
    {
      "epoch": 0.6889960106382979,
      "grad_norm": 71.36165659838801,
      "learning_rate": 1.9012587359129867e-07,
      "loss": 0.4756,
      "step": 4145,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.4366998577524893,
      "success_rate.epoch.env.math": 0.8930180180180181,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.7455389880224884,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48542733833838736,
      "success_rate.epoch.global": 0.6870156571247825,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9894153225806451,
      "tokens_p.mean_in_band": 0.6549030172413793,
      "tokens_rate.above_band": 0.8953068592057761,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10469314079422383
    },
    {
      "epoch": 0.6898271276595744,
      "grad_norm": 83.56963839508559,
      "learning_rate": 1.9010288787294602e-07,
      "loss": 0.3838,
      "step": 4150,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.4366998577524893,
      "success_rate.epoch.env.math": 0.8931383577052868,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.745849609375,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.485466516614731,
      "success_rate.epoch.global": 0.6873123716226892,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9927884615384616,
      "tokens_p.mean_below_band": 1.3322676295501878e-15,
      "tokens_p.mean_in_band": 0.6129807692307693,
      "tokens_rate.above_band": 0.8851063829787233,
      "tokens_rate.below_band": 0.00425531914893617,
      "tokens_rate.in_band": 0.11063829787234042
    },
    {
      "epoch": 0.690658244680851,
      "grad_norm": 73.73365539366097,
      "learning_rate": 1.900798842244425e-07,
      "loss": 0.4778,
      "step": 4155,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.4366998577524893,
      "success_rate.epoch.env.math": 0.8933782267115601,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.7459775719161384,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48549995584631395,
      "success_rate.epoch.global": 0.6875493135553101,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9882478632478633,
      "tokens_p.mean_in_band": 0.6502403846153846,
      "tokens_rate.above_band": 0.9,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1
    },
    {
      "epoch": 0.6914893617021277,
      "grad_norm": 93.40037029657991,
      "learning_rate": 1.9005686268661393e-07,
      "loss": 0.417,
      "step": 4160,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.4366998577524893,
      "success_rate.epoch.env.math": 0.8934977578475336,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.7462250365319045,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48553331909647207,
      "success_rate.epoch.global": 0.6877956480605487,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9834710743801653,
      "tokens_p.mean_below_band": 8.003553375601768e-11,
      "tokens_p.mean_in_band": 0.7975260416666666,
      "tokens_rate.above_band": 0.9029850746268657,
      "tokens_rate.below_band": 0.007462686567164179,
      "tokens_rate.in_band": 0.08955223880597014
    },
    {
      "epoch": 0.6923204787234043,
      "grad_norm": 179.94449149617503,
      "learning_rate": 1.900338233003179e-07,
      "loss": 0.5748,
      "step": 4165,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47333333333333333,
      "success_rate.epoch.env.logic": 0.43607954545454547,
      "success_rate.epoch.env.math": 0.8934977578475336,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.7464103188123631,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48549377091306434,
      "success_rate.epoch.global": 0.6878348566025843,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.21428571428571427,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9920720443349754,
      "tokens_p.mean_in_band": 0.5764780405405405,
      "tokens_rate.above_band": 0.8144433299899699,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1855566700100301
    },
    {
      "epoch": 0.6931515957446809,
      "grad_norm": 84.06062585441798,
      "learning_rate": 1.9001076610644368e-07,
      "loss": 0.5008,
      "step": 4170,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43607954545454547,
      "success_rate.epoch.env.math": 0.8934977578475336,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.7466569414053003,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48583326921420833,
      "success_rate.epoch.global": 0.6880806172256337,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9976099426386233,
      "tokens_p.mean_in_band": 0.7514204545454546,
      "tokens_rate.above_band": 0.9794007490636704,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020599250936329586
    },
    {
      "epoch": 0.6939827127659575,
      "grad_norm": 76.2497679839275,
      "learning_rate": 1.8998769114591218e-07,
      "loss": 0.472,
      "step": 4175,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43607954545454547,
      "success_rate.epoch.env.math": 0.8936170212765957,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.7466601894583434,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48580883372009254,
      "success_rate.epoch.global": 0.6880604058518169,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9889914772727273,
      "tokens_p.mean_in_band": 0.6758643617021277,
      "tokens_rate.above_band": 0.7892376681614349,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.21076233183856502
    },
    {
      "epoch": 0.694813829787234,
      "grad_norm": 54.30070630849187,
      "learning_rate": 1.8996459845967575e-07,
      "loss": 0.501,
      "step": 4180,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.4376770538243626,
      "success_rate.epoch.env.math": 0.8936170212765957,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.7467248908296943,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48595994369656237,
      "success_rate.epoch.global": 0.6882463859208046,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7619047619047619,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9958202030812325,
      "tokens_p.mean_in_band": 0.5803571428571429,
      "tokens_rate.above_band": 0.9622641509433962,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03773584905660377
    },
    {
      "epoch": 0.6956449468085106,
      "grad_norm": 84.67462063163026,
      "learning_rate": 1.8994148808871827e-07,
      "loss": 0.6198,
      "step": 4185,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43847241867043846,
      "success_rate.epoch.env.math": 0.8936170212765957,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.747031742185607,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48602483675043007,
      "success_rate.epoch.global": 0.6884319573065453,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9934090909090909,
      "tokens_p.mean_in_band": 0.6356026785714286,
      "tokens_rate.above_band": 0.8870967741935484,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11290322580645161
    },
    {
      "epoch": 0.6964760638297872,
      "grad_norm": 92.51553447457067,
      "learning_rate": 1.89918360074055e-07,
      "loss": 0.4158,
      "step": 4190,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43723554301833567,
      "success_rate.epoch.env.math": 0.8936170212765957,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.7471542746427706,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4859235328236174,
      "success_rate.epoch.global": 0.6883137254901961,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.48888888888888893,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.998882393397524,
      "tokens_p.mean_below_band": 5.617039278149605e-09,
      "tokens_p.mean_in_band": 0.6546415441176471,
      "tokens_rate.above_band": 0.9540682414698163,
      "tokens_rate.below_band": 0.0013123359580052493,
      "tokens_rate.in_band": 0.04461942257217848
    },
    {
      "epoch": 0.6973071808510638,
      "grad_norm": 94.02753634138327,
      "learning_rate": 1.8989521445673248e-07,
      "loss": 0.4481,
      "step": 4195,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43723554301833567,
      "success_rate.epoch.env.math": 0.8936170212765957,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.7473989837890153,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48594577910963965,
      "success_rate.epoch.global": 0.6885091707164133,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9917613636363637,
      "tokens_p.mean_in_band": 0.6403245192307693,
      "tokens_rate.above_band": 0.8286252354048964,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1713747645951036
    },
    {
      "epoch": 0.6981382978723404,
      "grad_norm": 111.91926376542496,
      "learning_rate": 1.898720512778285e-07,
      "loss": 0.4445,
      "step": 4200,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43723554301833567,
      "success_rate.epoch.env.math": 0.8936170212765957,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.7477042049299178,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4859735264860853,
      "success_rate.epoch.global": 0.6887531328320802,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9969533426183844,
      "tokens_p.mean_in_band": 0.4327392578125,
      "tokens_rate.above_band": 0.9573333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.042666666666666665
    },
    {
      "epoch": 0.698969414893617,
      "grad_norm": 132.50047862122815,
      "learning_rate": 1.8984887057845206e-07,
      "loss": 0.4653,
      "step": 4205,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.436241610738255,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43723554301833567,
      "success_rate.epoch.env.math": 0.8937360178970917,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.7478260869565218,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48599542454491257,
      "success_rate.epoch.global": 0.6888993267574761,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_in_band": 0.7405598958333334,
      "tokens_rate.above_band": 0.9047619047619048,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09523809523809523
    },
    {
      "epoch": 0.6998005319148937,
      "grad_norm": 131.29949345986978,
      "learning_rate": 1.8982567239974322e-07,
      "loss": 0.4596,
      "step": 4210,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.4388185654008439,
      "success_rate.epoch.env.math": 0.8938547486033519,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.7480694980694981,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48590786879916925,
      "success_rate.epoch.global": 0.6891321344800625,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941546762589928,
      "tokens_p.mean_in_band": 0.5889756944444444,
      "tokens_rate.above_band": 0.9686411149825784,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0313588850174216
    },
    {
      "epoch": 0.7006316489361702,
      "grad_norm": 112.48530892295777,
      "learning_rate": 1.8980245678287304e-07,
      "loss": 0.6103,
      "step": 4215,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.4388185654008439,
      "success_rate.epoch.env.math": 0.8940914158305463,
      "success_rate.epoch.env.sat": 0.1037037037037037,
      "success_rate.epoch.env.science": 0.7483124397299904,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48591642273194524,
      "success_rate.epoch.global": 0.6893158388003748,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9905849358974359,
      "tokens_p.mean_in_band": 0.62984375,
      "tokens_rate.above_band": 0.861878453038674,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13812154696132597
    },
    {
      "epoch": 0.7014627659574468,
      "grad_norm": 136.60351204631363,
      "learning_rate": 1.8977922376904354e-07,
      "loss": 0.5868,
      "step": 4220,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43820224719101125,
      "success_rate.epoch.env.math": 0.8944444444444445,
      "success_rate.epoch.env.sat": 0.1037037037037037,
      "success_rate.epoch.env.science": 0.7484337349397591,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4859035141513848,
      "success_rate.epoch.global": 0.6894506866416978,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9943605834464043,
      "tokens_p.mean_in_band": 0.5211693548387096,
      "tokens_rate.above_band": 0.9596354166666666,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040364583333333336
    },
    {
      "epoch": 0.7022938829787234,
      "grad_norm": 113.51386691917365,
      "learning_rate": 1.897559733994877e-07,
      "loss": 0.7681,
      "step": 4225,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43820224719101125,
      "success_rate.epoch.env.math": 0.8945615982241953,
      "success_rate.epoch.env.sat": 0.1033210332103321,
      "success_rate.epoch.env.science": 0.7483156881616939,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48586864474304964,
      "success_rate.epoch.global": 0.6893703241895262,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.990530303030303,
      "tokens_p.mean_in_band": 0.6213942307692307,
      "tokens_rate.above_band": 0.8638743455497382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13612565445026178
    },
    {
      "epoch": 0.703125,
      "grad_norm": 74.17269979025768,
      "learning_rate": 1.8973270571546913e-07,
      "loss": 0.551,
      "step": 4230,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43899018232819076,
      "success_rate.epoch.env.math": 0.8947951273532669,
      "success_rate.epoch.env.sat": 0.1033210332103321,
      "success_rate.epoch.env.science": 0.748618120644076,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4859889989929254,
      "success_rate.epoch.global": 0.6897571606475716,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921183628318584,
      "tokens_p.mean_below_band": 8.149072527885437e-09,
      "tokens_p.mean_in_band": 0.7651909722222222,
      "tokens_rate.above_band": 0.9576271186440678,
      "tokens_rate.below_band": 0.00423728813559322,
      "tokens_rate.in_band": 0.038135593220338986
    },
    {
      "epoch": 0.7039561170212766,
      "grad_norm": 257.42223166839324,
      "learning_rate": 1.8970942075828233e-07,
      "loss": 0.432,
      "step": 4235,
      "success_rate.epoch.env.abd": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.438375350140056,
      "success_rate.epoch.env.math": 0.8950276243093923,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.7487388902233966,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4859306878663405,
      "success_rate.epoch.global": 0.6897356143079316,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9962412587412588,
      "tokens_p.mean_in_band": 0.6454454787234043,
      "tokens_rate.above_band": 0.9383202099737533,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06167979002624672
    },
    {
      "epoch": 0.7047872340425532,
      "grad_norm": 115.5946326771729,
      "learning_rate": 1.8968611856925244e-07,
      "loss": 0.5261,
      "step": 4240,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43916083916083914,
      "success_rate.epoch.env.math": 0.8951434878587197,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.7486194477791116,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4872098648364021,
      "success_rate.epoch.global": 0.6898212898212899,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960069444444445,
      "tokens_p.mean_in_band": 0.6231770833333333,
      "tokens_rate.above_band": 0.96,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04
    },
    {
      "epoch": 0.7056183510638298,
      "grad_norm": 106.75897843806494,
      "learning_rate": 1.89662799189735e-07,
      "loss": 0.4994,
      "step": 4245,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.43333333333333335,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43916083916083914,
      "success_rate.epoch.env.math": 0.8952590959206174,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.7489208633093525,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48724777607205105,
      "success_rate.epoch.global": 0.6901102313305387,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953435430463576,
      "tokens_p.mean_in_band": 0.7045200892857143,
      "tokens_rate.above_band": 0.9556962025316456,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04430379746835443
    },
    {
      "epoch": 0.7064494680851063,
      "grad_norm": 89.77211511640985,
      "learning_rate": 1.896394626611163e-07,
      "loss": 0.5757,
      "step": 4250,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4370860927152318,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43854748603351956,
      "success_rate.epoch.env.math": 0.8953744493392071,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.7491013659237958,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48756007264365214,
      "success_rate.epoch.global": 0.6902435241197457,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970170454545455,
      "tokens_p.mean_in_band": 0.5926339285714286,
      "tokens_rate.above_band": 0.9617486338797814,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03825136612021858
    },
    {
      "epoch": 0.707280585106383,
      "grad_norm": 104.68640032224654,
      "learning_rate": 1.89616109024813e-07,
      "loss": 0.5432,
      "step": 4255,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.43854748603351956,
      "success_rate.epoch.env.math": 0.8953744493392071,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.749341632750778,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4879185860796485,
      "success_rate.epoch.global": 0.6904835709857409,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949090121317158,
      "tokens_p.mean_below_band": 4.1443854570388794e-08,
      "tokens_p.mean_in_band": 0.8020833333333334,
      "tokens_rate.above_band": 0.9931153184165232,
      "tokens_rate.below_band": 0.0017211703958691911,
      "tokens_rate.in_band": 0.0051635111876075735
    },
    {
      "epoch": 0.7081117021276596,
      "grad_norm": 97.49138747304247,
      "learning_rate": 1.8959273832227197e-07,
      "loss": 0.4554,
      "step": 4260,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4768211920529801,
      "success_rate.epoch.env.logic": 0.4393305439330544,
      "success_rate.epoch.env.math": 0.8954895489548955,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.7495215311004785,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48801659115827795,
      "success_rate.epoch.global": 0.6907232460895153,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9922839506172839,
      "tokens_p.mean_in_band": 0.7349330357142857,
      "tokens_rate.above_band": 0.9455252918287937,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054474708171206226
    },
    {
      "epoch": 0.7089428191489362,
      "grad_norm": 67.56734200042959,
      "learning_rate": 1.8956935059497052e-07,
      "loss": 0.3633,
      "step": 4265,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48026315789473684,
      "success_rate.epoch.env.logic": 0.43949930458970793,
      "success_rate.epoch.env.math": 0.8956043956043956,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.7496413199426112,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4883661695210092,
      "success_rate.epoch.global": 0.6908556397957605,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992973372781065,
      "tokens_p.mean_in_band": 0.6189236111111112,
      "tokens_rate.above_band": 0.9690366972477065,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03096330275229358
    },
    {
      "epoch": 0.7097739361702128,
      "grad_norm": 64.03939956288343,
      "learning_rate": 1.8954594588441617e-07,
      "loss": 0.591,
      "step": 4270,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48026315789473684,
      "success_rate.epoch.env.logic": 0.43949930458970793,
      "success_rate.epoch.env.math": 0.8956043956043956,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.75,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48836449735290943,
      "success_rate.epoch.global": 0.6910355486862442,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965277777777778,
      "tokens_p.mean_in_band": 0.6300951086956522,
      "tokens_rate.above_band": 0.9361997226074896,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0638002773925104
    },
    {
      "epoch": 0.7106050531914894,
      "grad_norm": 148.01650939739176,
      "learning_rate": 1.8952252423214652e-07,
      "loss": 0.3919,
      "step": 4275,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48026315789473684,
      "success_rate.epoch.env.logic": 0.43949930458970793,
      "success_rate.epoch.env.math": 0.8957189901207464,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7501193317422434,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.488385763376418,
      "success_rate.epoch.global": 0.6911787424687162,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9889705882352942,
      "tokens_p.mean_in_band": 0.6166294642857143,
      "tokens_rate.above_band": 0.9132231404958677,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08677685950413223
    },
    {
      "epoch": 0.711436170212766,
      "grad_norm": 51.177074398787305,
      "learning_rate": 1.894990856797293e-07,
      "loss": 0.6083,
      "step": 4280,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.2857142857142857,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48026315789473684,
      "success_rate.epoch.env.logic": 0.43949930458970793,
      "success_rate.epoch.env.math": 0.895947426067908,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.750059623181493,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4884011022297281,
      "success_rate.epoch.global": 0.6912627354121642,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.8571428571428572,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.98828125,
      "tokens_p.mean_in_band": 0.5224609375,
      "tokens_rate.above_band": 0.8947368421052632,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10526315789473684
    },
    {
      "epoch": 0.7122672872340425,
      "grad_norm": 184.75490898945247,
      "learning_rate": 1.8947563026876213e-07,
      "loss": 0.5772,
      "step": 4285,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48026315789473684,
      "success_rate.epoch.env.logic": 0.4388888888888889,
      "success_rate.epoch.env.math": 0.895947426067908,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7502978317846081,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4866356634892442,
      "success_rate.epoch.global": 0.6912399753238742,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9946268459915611,
      "tokens_p.mean_in_band": 0.7361111111111112,
      "tokens_rate.above_band": 0.9546827794561934,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.045317220543806644
    },
    {
      "epoch": 0.7130984042553191,
      "grad_norm": 86.46547925366191,
      "learning_rate": 1.8945215804087266e-07,
      "loss": 0.6543,
      "step": 4290,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.477124183006536,
      "success_rate.epoch.env.logic": 0.43966712898751736,
      "success_rate.epoch.env.math": 0.895947426067908,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.7503569728700619,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48642642769796063,
      "success_rate.epoch.global": 0.6912648282236944,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9849943374858438,
      "tokens_p.mean_in_band": 0.5704105062724014,
      "tokens_rate.above_band": 0.7598967297762479,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.24010327022375216
    },
    {
      "epoch": 0.7139295212765957,
      "grad_norm": 94.08215311191753,
      "learning_rate": 1.8942866903771834e-07,
      "loss": 0.5902,
      "step": 4295,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.477124183006536,
      "success_rate.epoch.env.logic": 0.43966712898751736,
      "success_rate.epoch.env.math": 0.895947426067908,
      "success_rate.epoch.env.sat": 0.10181818181818182,
      "success_rate.epoch.env.science": 0.7504757373929591,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48636941349586765,
      "success_rate.epoch.global": 0.6911470361816782,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.35714285714285715,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9934413580246914,
      "tokens_p.mean_below_band": 5.502442945726216e-11,
      "tokens_p.mean_in_band": 0.6466619318181818,
      "tokens_rate.above_band": 0.8127090301003345,
      "tokens_rate.below_band": 0.0033444816053511705,
      "tokens_rate.in_band": 0.18394648829431437
    },
    {
      "epoch": 0.7147606382978723,
      "grad_norm": 159.40994791261662,
      "learning_rate": 1.894051633009864e-07,
      "loss": 0.4786,
      "step": 4300,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.477124183006536,
      "success_rate.epoch.env.logic": 0.43966712898751736,
      "success_rate.epoch.env.math": 0.8960612691466083,
      "success_rate.epoch.env.sat": 0.10181818181818182,
      "success_rate.epoch.env.science": 0.7505938242280285,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48639049803348305,
      "success_rate.epoch.global": 0.6913257459243309,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.990234375,
      "tokens_p.mean_below_band": 2.514570951461792e-08,
      "tokens_p.mean_in_band": 0.6315104166666666,
      "tokens_rate.above_band": 0.927536231884058,
      "tokens_rate.below_band": 0.007246376811594203,
      "tokens_rate.in_band": 0.06521739130434782
    },
    {
      "epoch": 0.715591755319149,
      "grad_norm": 84.0879312020626,
      "learning_rate": 1.893816408723938e-07,
      "loss": 0.553,
      "step": 4305,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.477124183006536,
      "success_rate.epoch.env.logic": 0.43966712898751736,
      "success_rate.epoch.env.math": 0.8960612691466083,
      "success_rate.epoch.env.sat": 0.10144927536231885,
      "success_rate.epoch.env.science": 0.7507714217896986,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4863731063158292,
      "success_rate.epoch.global": 0.691361819858592,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.3666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9970407196969697,
      "tokens_p.mean_in_band": 0.6302734375,
      "tokens_rate.above_band": 0.9406175771971497,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05938242280285035
    },
    {
      "epoch": 0.7164228723404256,
      "grad_norm": 73.02164494461557,
      "learning_rate": 1.8935810179368701e-07,
      "loss": 0.4041,
      "step": 4310,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4805194805194805,
      "success_rate.epoch.env.logic": 0.43966712898751736,
      "success_rate.epoch.env.math": 0.8960612691466083,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.7511258592083432,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4866806965031241,
      "success_rate.epoch.global": 0.6915873503223826,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9951517706576728,
      "tokens_p.mean_in_band": 0.7201334635416666,
      "tokens_rate.above_band": 0.9251170046801872,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0748829953198128
    },
    {
      "epoch": 0.7172539893617021,
      "grad_norm": 78.4239188360767,
      "learning_rate": 1.8933454610664218e-07,
      "loss": 0.4876,
      "step": 4315,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4805194805194805,
      "success_rate.epoch.env.logic": 0.4404432132963989,
      "success_rate.epoch.env.math": 0.8961748633879781,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.7514204545454546,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48678835776561163,
      "success_rate.epoch.global": 0.691918417420641,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9916460396039604,
      "tokens_p.mean_in_band": 0.630859375,
      "tokens_rate.above_band": 0.9181818181818182,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08181818181818182
    },
    {
      "epoch": 0.7180851063829787,
      "grad_norm": 98.40533914804605,
      "learning_rate": 1.8931097385306486e-07,
      "loss": 0.8607,
      "step": 4320,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4805194805194805,
      "success_rate.epoch.env.logic": 0.43983402489626555,
      "success_rate.epoch.env.math": 0.8961748633879781,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.7514191106906338,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4867328548333431,
      "success_rate.epoch.global": 0.6918479926448053,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9944371727748691,
      "tokens_p.mean_in_band": 0.6472981770833334,
      "tokens_rate.above_band": 0.9408866995073891,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.059113300492610835
    },
    {
      "epoch": 0.7189162234042553,
      "grad_norm": 103.58482178009173,
      "learning_rate": 1.8928738507479003e-07,
      "loss": 0.4619,
      "step": 4325,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4805194805194805,
      "success_rate.epoch.env.logic": 0.43983402489626555,
      "success_rate.epoch.env.math": 0.8962882096069869,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.7515366430260048,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48675384379283226,
      "success_rate.epoch.global": 0.6919895849287793,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9976796998420221,
      "tokens_p.mean_in_band": 0.5546875,
      "tokens_rate.above_band": 0.960546282245827,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03945371775417299
    },
    {
      "epoch": 0.7197473404255319,
      "grad_norm": 76.54371369058103,
      "learning_rate": 1.8926377981368202e-07,
      "loss": 0.5284,
      "step": 4330,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4805194805194805,
      "success_rate.epoch.env.logic": 0.4413793103448276,
      "success_rate.epoch.env.math": 0.8964013086150491,
      "success_rate.epoch.env.sat": 0.10071942446043165,
      "success_rate.epoch.env.science": 0.7514177693761814,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4868607440452193,
      "success_rate.epoch.global": 0.6919663351185922,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.4333333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.992442936458976,
      "tokens_p.mean_below_band": 4.4648186303675175e-07,
      "tokens_p.mean_in_band": 0.5511291348600509,
      "tokens_rate.above_band": 0.8040674603174603,
      "tokens_rate.below_band": 0.000992063492063492,
      "tokens_rate.in_band": 0.1949404761904762
    },
    {
      "epoch": 0.7205784574468085,
      "grad_norm": 84.83162136887483,
      "learning_rate": 1.8924015811163437e-07,
      "loss": 0.5044,
      "step": 4335,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4838709677419355,
      "success_rate.epoch.env.logic": 0.44214876033057854,
      "success_rate.epoch.env.math": 0.8964013086150491,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.751357733175915,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4871970985439989,
      "success_rate.epoch.global": 0.6919431279620853,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.76,
      "success_rate.window.global": 0.7777777777777778,
      "tokens_p.mean_above_band": 0.9891377005347594,
      "tokens_p.mean_in_band": 0.7549913194444444,
      "tokens_rate.above_band": 0.8862559241706162,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11374407582938388
    },
    {
      "epoch": 0.7214095744680851,
      "grad_norm": 73.98248086914344,
      "learning_rate": 1.8921652001056978e-07,
      "loss": 0.4356,
      "step": 4340,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4407894736842105,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4838709677419355,
      "success_rate.epoch.env.logic": 0.44214876033057854,
      "success_rate.epoch.env.math": 0.8965141612200436,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.7513564519933946,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48720724140058747,
      "success_rate.epoch.global": 0.692025664527956,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9955561926605505,
      "tokens_p.mean_in_band": 0.42373511904761907,
      "tokens_rate.above_band": 0.9688888888888889,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03111111111111111
    },
    {
      "epoch": 0.7222406914893617,
      "grad_norm": 67.93868482693091,
      "learning_rate": 1.8919286555244013e-07,
      "loss": 0.4441,
      "step": 4345,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4838709677419355,
      "success_rate.epoch.env.logic": 0.44214876033057854,
      "success_rate.epoch.env.math": 0.8965141612200436,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.7514150943396226,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.487544842592084,
      "success_rate.epoch.global": 0.6921197312156384,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9975308641975309,
      "tokens_p.mean_in_band": 0.8370535714285714,
      "tokens_rate.above_band": 0.9830097087378641,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01699029126213592
    },
    {
      "epoch": 0.7230718085106383,
      "grad_norm": 159.20782865461274,
      "learning_rate": 1.8916919477922627e-07,
      "loss": 0.5283,
      "step": 4350,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.44214876033057854,
      "success_rate.epoch.env.math": 0.8967391304347826,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.7515322960867515,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48787672353748585,
      "success_rate.epoch.global": 0.6923546467266901,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7083333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9940713431646074,
      "tokens_p.mean_below_band": 3.259629011154175e-07,
      "tokens_p.mean_in_band": 0.50625,
      "tokens_rate.above_band": 0.8928825622775801,
      "tokens_rate.below_band": 0.00035587188612099647,
      "tokens_rate.in_band": 0.10676156583629894
    },
    {
      "epoch": 0.7239029255319149,
      "grad_norm": 267.6183368942195,
      "learning_rate": 1.8914550773293804e-07,
      "loss": 0.4552,
      "step": 4355,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.44214876033057854,
      "success_rate.epoch.env.math": 0.8970747562296858,
      "success_rate.epoch.env.sat": 0.099644128113879,
      "success_rate.epoch.env.science": 0.7513551732264907,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48815415187539096,
      "success_rate.epoch.global": 0.6922256097560976,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9950810185185185,
      "tokens_p.mean_in_band": 0.5784801136363636,
      "tokens_rate.above_band": 0.907563025210084,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09243697478991597
    },
    {
      "epoch": 0.7247340425531915,
      "grad_norm": 76.93213741137572,
      "learning_rate": 1.8912180445561412e-07,
      "loss": 0.5652,
      "step": 4360,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.44214876033057854,
      "success_rate.epoch.env.math": 0.8971861471861472,
      "success_rate.epoch.env.sat": 0.099644128113879,
      "success_rate.epoch.env.science": 0.7512941176470588,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48815872781875724,
      "success_rate.epoch.global": 0.6922959805115713,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9865384615384616,
      "tokens_p.mean_in_band": 0.6928453947368421,
      "tokens_rate.above_band": 0.87248322147651,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12751677852348994
    },
    {
      "epoch": 0.7255651595744681,
      "grad_norm": 81.75392936680419,
      "learning_rate": 1.8909808498932205e-07,
      "loss": 0.6424,
      "step": 4365,
      "success_rate.epoch.env.abd": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4840764331210191,
      "success_rate.epoch.env.logic": 0.44154057771664373,
      "success_rate.epoch.env.math": 0.8971861471861472,
      "success_rate.epoch.env.sat": 0.099644128113879,
      "success_rate.epoch.env.science": 0.7513513513513513,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48782654573074724,
      "success_rate.epoch.global": 0.6921673003802281,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.625,
      "success_rate.window.env_macro_mean": 0.20833333333333334,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9932397959183673,
      "tokens_p.mean_in_band": 0.6305118865030674,
      "tokens_rate.above_band": 0.8825648414985591,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11743515850144093
    },
    {
      "epoch": 0.7263962765957447,
      "grad_norm": 667.9185564578713,
      "learning_rate": 1.8907434937615803e-07,
      "loss": 0.4817,
      "step": 4370,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.44154057771664373,
      "success_rate.epoch.env.math": 0.8974082073434125,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7514681700728212,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48899661998298405,
      "success_rate.epoch.global": 0.6922375816497038,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9915844298245614,
      "tokens_p.mean_in_band": 0.5990010245901639,
      "tokens_rate.above_band": 0.8236994219653179,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17630057803468208
    },
    {
      "epoch": 0.7272273936170213,
      "grad_norm": 106.54796761053292,
      "learning_rate": 1.89050597658247e-07,
      "loss": 0.3869,
      "step": 4375,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.44154057771664373,
      "success_rate.epoch.env.math": 0.8974082073434125,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7513500821789152,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4889858847199017,
      "success_rate.epoch.global": 0.6921791951404708,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9954941860465116,
      "tokens_p.mean_in_band": 0.6475929054054054,
      "tokens_rate.above_band": 0.9457478005865103,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054252199413489736
    },
    {
      "epoch": 0.7280585106382979,
      "grad_norm": 100.99380518293161,
      "learning_rate": 1.8902682987774242e-07,
      "loss": 0.3401,
      "step": 4380,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.44154057771664373,
      "success_rate.epoch.env.math": 0.8975188781014024,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7513488153882243,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48899583053511064,
      "success_rate.epoch.global": 0.6922610015174507,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9900442477876106,
      "tokens_p.mean_in_band": 0.730078125,
      "tokens_rate.above_band": 0.9576271186440678,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0423728813559322
    },
    {
      "epoch": 0.7288896276595744,
      "grad_norm": 79.44632920665005,
      "learning_rate": 1.8900304607682626e-07,
      "loss": 0.5829,
      "step": 4385,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.4409340659340659,
      "success_rate.epoch.env.math": 0.8976293103448276,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7514071294559099,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48895603367406826,
      "success_rate.epoch.global": 0.6922493553769149,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4166666666666667,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9933271670190275,
      "tokens_p.mean_in_band": 0.6509507123161765,
      "tokens_rate.above_band": 0.912540192926045,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08745980707395498
    },
    {
      "epoch": 0.729720744680851,
      "grad_norm": 62.61111910390177,
      "learning_rate": 1.8897924629770898e-07,
      "loss": 0.3829,
      "step": 4390,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.44170096021947874,
      "success_rate.epoch.env.math": 0.8976293103448276,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7515236755743084,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4890363464380511,
      "success_rate.epoch.global": 0.6923893268647665,
      "success_rate.window.env.logic": 0.8333333333333334,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995286673553719,
      "tokens_p.mean_in_band": 0.6028262867647058,
      "tokens_rate.above_band": 0.9660678642714571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033932135728542916
    },
    {
      "epoch": 0.7305518617021277,
      "grad_norm": 86.15968875375953,
      "learning_rate": 1.8895543058262932e-07,
      "loss": 0.5256,
      "step": 4395,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.44805194805194803,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.44170096021947874,
      "success_rate.epoch.env.math": 0.8966630785791173,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.751580426129712,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48895366632802323,
      "success_rate.epoch.global": 0.6923659497122084,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9928678678678678,
      "tokens_p.mean_in_band": 0.6512784090909091,
      "tokens_rate.above_band": 0.9380281690140845,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061971830985915494
    },
    {
      "epoch": 0.7313829787234043,
      "grad_norm": 186.37100709797232,
      "learning_rate": 1.8893159897385438e-07,
      "loss": 0.6695,
      "step": 4400,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48427672955974843,
      "success_rate.epoch.env.logic": 0.4410958904109589,
      "success_rate.epoch.env.math": 0.896774193548387,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7514626725953663,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4892217796735016,
      "success_rate.epoch.global": 0.6922960496443167,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9965999388753056,
      "tokens_p.mean_below_band": 1.8533319234848022e-07,
      "tokens_p.mean_in_band": 0.509521484375,
      "tokens_rate.above_band": 0.9522700814901047,
      "tokens_rate.below_band": 0.0011641443538998836,
      "tokens_rate.in_band": 0.046565774155995346
    },
    {
      "epoch": 0.7322140957446809,
      "grad_norm": 101.93626897576901,
      "learning_rate": 1.8890775151367938e-07,
      "loss": 0.6065,
      "step": 4405,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48125,
      "success_rate.epoch.env.logic": 0.4410958904109589,
      "success_rate.epoch.env.math": 0.896774193548387,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.751578947368421,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48895719287471134,
      "success_rate.epoch.global": 0.6922844175491679,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.21428571428571427,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9967196132596685,
      "tokens_p.mean_in_band": 0.6408808679039302,
      "tokens_rate.above_band": 0.92672,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07328
    },
    {
      "epoch": 0.7330452127659575,
      "grad_norm": 117.9752160742047,
      "learning_rate": 1.8888388824442777e-07,
      "loss": 0.4082,
      "step": 4410,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48125,
      "success_rate.epoch.env.logic": 0.4410958904109589,
      "success_rate.epoch.env.math": 0.896774193548387,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.751927119831815,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48898884491683803,
      "success_rate.epoch.global": 0.6925634824667473,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9879807692307693,
      "tokens_p.mean_in_band": 0.7007211538461539,
      "tokens_rate.above_band": 0.9,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1
    },
    {
      "epoch": 0.733876329787234,
      "grad_norm": 130.0204194839608,
      "learning_rate": 1.88860009208451e-07,
      "loss": 0.343,
      "step": 4415,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48125,
      "success_rate.epoch.env.logic": 0.4410958904109589,
      "success_rate.epoch.env.math": 0.8968850698174007,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7522165188987401,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4890252335837415,
      "success_rate.epoch.global": 0.692842041679251,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974424552429667,
      "tokens_p.mean_in_band": 0.5304418103448276,
      "tokens_rate.above_band": 0.9642416769420469,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.035758323057953144
    },
    {
      "epoch": 0.7347074468085106,
      "grad_norm": 240.71635052843217,
      "learning_rate": 1.8883611444812845e-07,
      "loss": 0.5749,
      "step": 4420,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48125,
      "success_rate.epoch.env.logic": 0.4418604651162791,
      "success_rate.epoch.env.math": 0.8968850698174007,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7524475524475525,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48911574342502634,
      "success_rate.epoch.global": 0.6930737890448166,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9913194444444444,
      "tokens_p.mean_in_band": 0.7491319444444444,
      "tokens_rate.above_band": 0.9523809523809523,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047619047619047616
    },
    {
      "epoch": 0.7355385638297872,
      "grad_norm": 94.6305726076469,
      "learning_rate": 1.888122040058675e-07,
      "loss": 0.4512,
      "step": 4425,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.4426229508196721,
      "success_rate.epoch.env.math": 0.8971061093247589,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7526205450733753,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4895137950183004,
      "success_rate.epoch.global": 0.6933976484775399,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9855401529636711,
      "tokens_p.mean_in_band": 0.854375,
      "tokens_rate.above_band": 0.9543795620437956,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04562043795620438
    },
    {
      "epoch": 0.7363696808510638,
      "grad_norm": 109.1126549076257,
      "learning_rate": 1.8878827792410335e-07,
      "loss": 0.4643,
      "step": 4430,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.444141689373297,
      "success_rate.epoch.env.math": 0.8971061093247589,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7529658060013956,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48968324951663184,
      "success_rate.epoch.global": 0.6937669376693767,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9936740890688259,
      "tokens_p.mean_in_band": 0.825390625,
      "tokens_rate.above_band": 0.9610894941634242,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038910505836575876
    },
    {
      "epoch": 0.7372007978723404,
      "grad_norm": 137.67767526394704,
      "learning_rate": 1.887643362452989e-07,
      "loss": 0.7313,
      "step": 4435,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.444141689373297,
      "success_rate.epoch.env.math": 0.8971061093247589,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.7532527881040892,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4897093387986949,
      "success_rate.epoch.global": 0.6939972920114337,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9976587947882736,
      "tokens_p.mean_in_band": 0.5655184659090909,
      "tokens_rate.above_band": 0.9702031602708804,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029796839729119638
    },
    {
      "epoch": 0.738031914893617,
      "grad_norm": 75.32472949630618,
      "learning_rate": 1.8874037901194479e-07,
      "loss": 0.4643,
      "step": 4440,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.444141689373297,
      "success_rate.epoch.env.math": 0.8972162740899358,
      "success_rate.epoch.env.sat": 0.0989399293286219,
      "success_rate.epoch.env.science": 0.7534818941504178,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4897082860712661,
      "success_rate.epoch.global": 0.694122952051706,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9994261268781303,
      "tokens_p.mean_in_band": 0.5360169491525424,
      "tokens_rate.above_band": 0.9530628480509149,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.046937151949085126
    },
    {
      "epoch": 0.7388630319148937,
      "grad_norm": 132.7806959351578,
      "learning_rate": 1.8871640626655923e-07,
      "loss": 0.3691,
      "step": 4445,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.4448979591836735,
      "success_rate.epoch.env.math": 0.8975453575240128,
      "success_rate.epoch.env.sat": 0.0989399293286219,
      "success_rate.epoch.env.science": 0.7534214799350498,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4898014623466374,
      "success_rate.epoch.global": 0.6942942942942943,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9925411522633745,
      "tokens_p.mean_in_band": 0.7430555555555556,
      "tokens_rate.above_band": 0.9310344827586207,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06896551724137931
    },
    {
      "epoch": 0.7396941489361702,
      "grad_norm": 64.22165100729973,
      "learning_rate": 1.8869241805168795e-07,
      "loss": 0.5711,
      "step": 4450,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.44429347826086957,
      "success_rate.epoch.env.math": 0.8976545842217484,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.753592953175707,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.489740356799614,
      "success_rate.epoch.global": 0.6942694269426942,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9988425925925926,
      "tokens_p.mean_in_band": 0.625,
      "tokens_rate.above_band": 0.9253365973072215,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07466340269277846
    },
    {
      "epoch": 0.7405252659574468,
      "grad_norm": 114.42536682688672,
      "learning_rate": 1.886684144099042e-07,
      "loss": 0.6166,
      "step": 4455,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.484472049689441,
      "success_rate.epoch.env.logic": 0.44369063772048845,
      "success_rate.epoch.env.math": 0.8976545842217484,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.7537071362372567,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4896959333924475,
      "success_rate.epoch.global": 0.6942570100464838,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.3333333333333333,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.999859865470852,
      "tokens_p.mean_in_band": 0.5884989754098361,
      "tokens_rate.above_band": 0.9164383561643835,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08356164383561644
    },
    {
      "epoch": 0.7413563829787234,
      "grad_norm": 130.77393913351526,
      "learning_rate": 1.8864439538380853e-07,
      "loss": 0.4507,
      "step": 4460,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48466257668711654,
      "success_rate.epoch.env.logic": 0.4444444444444444,
      "success_rate.epoch.env.math": 0.8976545842217484,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.7539351851851852,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4898025136351347,
      "success_rate.epoch.global": 0.6944278010784901,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.993574236468098,
      "tokens_p.mean_in_band": 0.7829953457446809,
      "tokens_rate.above_band": 0.9859868813357185,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014013118664281454
    },
    {
      "epoch": 0.7421875,
      "grad_norm": 66.2519139594964,
      "learning_rate": 1.8862036101602884e-07,
      "loss": 0.4097,
      "step": 4465,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48466257668711654,
      "success_rate.epoch.env.logic": 0.4438430311231394,
      "success_rate.epoch.env.math": 0.8976545842217484,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.7541059449456397,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48976336331142106,
      "success_rate.epoch.global": 0.6944610778443113,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45999999999999996,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9944545454545455,
      "tokens_p.mean_in_band": 0.6390143060064936,
      "tokens_rate.above_band": 0.8992805755395683,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10071942446043165
    },
    {
      "epoch": 0.7430186170212766,
      "grad_norm": 70.04259190456737,
      "learning_rate": 1.8859631134922022e-07,
      "loss": 0.4983,
      "step": 4470,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48466257668711654,
      "success_rate.epoch.env.logic": 0.4438430311231394,
      "success_rate.epoch.env.math": 0.8976545842217484,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.7544467544467545,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.48979434599334054,
      "success_rate.epoch.global": 0.6947352677236015,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9975476457399103,
      "tokens_p.mean_in_band": 0.6392299107142857,
      "tokens_rate.above_band": 0.9695652173913043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030434782608695653
    },
    {
      "epoch": 0.7438497340425532,
      "grad_norm": 84.71976278032501,
      "learning_rate": 1.8857224642606498e-07,
      "loss": 0.4106,
      "step": 4475,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.4445945945945946,
      "success_rate.epoch.env.math": 0.8977635782747604,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.7545034642032332,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4901633976881233,
      "success_rate.epoch.global": 0.6949177877428998,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9871244635193133,
      "tokens_p.mean_in_band": 0.784912109375,
      "tokens_rate.above_band": 0.966804979253112,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03319502074688797
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 101.78363343055061,
      "learning_rate": 1.8854816628927244e-07,
      "loss": 0.6266,
      "step": 4480,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4551282051282051,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.44534412955465585,
      "success_rate.epoch.env.math": 0.8977635782747604,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.7546125461254612,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49056102666854956,
      "success_rate.epoch.global": 0.6951328754852195,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958448753462604,
      "tokens_p.mean_in_band": 0.6267027243589743,
      "tokens_rate.above_band": 0.9025,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0975
    },
    {
      "epoch": 0.7455119680851063,
      "grad_norm": 270.3873463813209,
      "learning_rate": 1.885240709815789e-07,
      "loss": 0.4389,
      "step": 4485,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.44609164420485176,
      "success_rate.epoch.env.math": 0.8978723404255319,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.7547256800368833,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4908709683060782,
      "success_rate.epoch.global": 0.6950492096629883,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958530805687204,
      "tokens_p.mean_in_band": 0.5828208111702128,
      "tokens_rate.above_band": 0.8997867803837953,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10021321961620469
    },
    {
      "epoch": 0.746343085106383,
      "grad_norm": 92.75956210863058,
      "learning_rate": 1.8849996054574774e-07,
      "loss": 0.5714,
      "step": 4490,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.44609164420485176,
      "success_rate.epoch.env.math": 0.89798087141339,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.7549516351911562,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4911835773063001,
      "success_rate.epoch.global": 0.695321811680572,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9908333333333333,
      "tokens_p.mean_in_band": 0.6580584490740741,
      "tokens_rate.above_band": 0.9615384615384616,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038461538461538464
    },
    {
      "epoch": 0.7471742021276596,
      "grad_norm": 87.23461190489874,
      "learning_rate": 1.8847583502456897e-07,
      "loss": 0.443,
      "step": 4495,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.44609164420485176,
      "success_rate.epoch.env.math": 0.8980891719745223,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.7552334943639292,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4912190463730188,
      "success_rate.epoch.global": 0.6955939267639178,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957496136012365,
      "tokens_p.mean_in_band": 0.71484375,
      "tokens_rate.above_band": 0.9528718703976435,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047128129602356406
    },
    {
      "epoch": 0.7480053191489362,
      "grad_norm": 95.23486458877622,
      "learning_rate": 1.884516944608595e-07,
      "loss": 0.4724,
      "step": 4500,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.44609164420485176,
      "success_rate.epoch.env.math": 0.8980891719745223,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.7555147058823529,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49124461105651185,
      "success_rate.epoch.global": 0.6958203183102781,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9838963963963964,
      "tokens_p.mean_below_band": 6.07222318649292e-07,
      "tokens_p.mean_in_band": 0.7063238188976378,
      "tokens_rate.above_band": 0.8125915080527086,
      "tokens_rate.below_band": 0.0014641288433382138,
      "tokens_rate.in_band": 0.18594436310395315
    },
    {
      "epoch": 0.7488364361702128,
      "grad_norm": 87.79097437163627,
      "learning_rate": 1.8842753889746295e-07,
      "loss": 0.3709,
      "step": 4505,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4468371467025572,
      "success_rate.epoch.env.math": 0.8980891719745223,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.7556270096463023,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.491322593443935,
      "success_rate.epoch.global": 0.6959559916741005,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9909336419753086,
      "tokens_p.mean_in_band": 0.7455610795454546,
      "tokens_rate.above_band": 0.8804347826086957,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11956521739130435
    },
    {
      "epoch": 0.7496675531914894,
      "grad_norm": 60.275132336223486,
      "learning_rate": 1.884033683772495e-07,
      "loss": 0.4219,
      "step": 4510,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4468371467025572,
      "success_rate.epoch.env.math": 0.8981972428419936,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.7558513079394218,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49192055907343835,
      "success_rate.epoch.global": 0.6962720926778554,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9873481781376519,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.759046052631579,
      "tokens_rate.above_band": 0.9250936329588015,
      "tokens_rate.below_band": 0.003745318352059925,
      "tokens_rate.in_band": 0.07116104868913857
    },
    {
      "epoch": 0.750498670212766,
      "grad_norm": 129.80182577304845,
      "learning_rate": 1.883791829431159e-07,
      "loss": 0.4917,
      "step": 4515,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4469798657718121,
      "success_rate.epoch.env.math": 0.8981972428419936,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.756131102452441,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4919589693990996,
      "success_rate.epoch.global": 0.6964391691394659,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963735673352435,
      "tokens_p.mean_in_band": 0.5546875,
      "tokens_rate.above_band": 0.9432432432432433,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05675675675675676
    },
    {
      "epoch": 0.7513297872340425,
      "grad_norm": 115.17396105034123,
      "learning_rate": 1.8835498263798544e-07,
      "loss": 0.3525,
      "step": 4520,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.44638069705093836,
      "success_rate.epoch.env.math": 0.8981972428419936,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.7561813186813187,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4919090646271,
      "success_rate.epoch.global": 0.6964126890008894,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9970112517580872,
      "tokens_p.mean_below_band": 1.2014061212539673e-07,
      "tokens_p.mean_in_band": 0.5718961148648649,
      "tokens_rate.above_band": 0.9492656875834445,
      "tokens_rate.below_band": 0.0013351134846461949,
      "tokens_rate.in_band": 0.049399198931909215
    },
    {
      "epoch": 0.7521609042553191,
      "grad_norm": 97.3441646839279,
      "learning_rate": 1.8833076750480762e-07,
      "loss": 0.5321,
      "step": 4525,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4457831325301205,
      "success_rate.epoch.env.math": 0.8983050847457628,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.7564043915827996,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4918848237438666,
      "success_rate.epoch.global": 0.6965343601895735,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.992814465408805,
      "tokens_p.mean_in_band": 0.5687087414821125,
      "tokens_rate.above_band": 0.8713283647523016,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12867163524769837
    },
    {
      "epoch": 0.7529920212765957,
      "grad_norm": 82.49339131704869,
      "learning_rate": 1.8830653758655847e-07,
      "loss": 0.3581,
      "step": 4530,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4457831325301205,
      "success_rate.epoch.env.math": 0.8984126984126984,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.7565157750342936,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4919047325728147,
      "success_rate.epoch.global": 0.6966691339748334,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9987344236760125,
      "tokens_p.mean_in_band": 0.7041377314814815,
      "tokens_rate.above_band": 0.9596412556053812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04035874439461883
    },
    {
      "epoch": 0.7538231382978723,
      "grad_norm": 81.1211690797154,
      "learning_rate": 1.882822929262401e-07,
      "loss": 0.3259,
      "step": 4535,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4585987261146497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4457831325301205,
      "success_rate.epoch.env.math": 0.8986272439281943,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.7566826593557231,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4919394080125352,
      "success_rate.epoch.global": 0.6968934911242604,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9855769230769231,
      "tokens_p.mean_in_band": 0.8697916666666666,
      "tokens_rate.above_band": 0.9774436090225563,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022556390977443608
    },
    {
      "epoch": 0.754654255319149,
      "grad_norm": 98.63975221861453,
      "learning_rate": 1.8825803356688083e-07,
      "loss": 0.3687,
      "step": 4540,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4620253164556962,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.4457831325301205,
      "success_rate.epoch.env.math": 0.8987341772151899,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.7569048162519972,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49224829237732454,
      "success_rate.epoch.global": 0.6970592581646224,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944571865443425,
      "tokens_p.mean_in_band": 0.6529017857142857,
      "tokens_rate.above_band": 0.9211267605633803,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07887323943661972
    },
    {
      "epoch": 0.7554853723404256,
      "grad_norm": 93.80341475181635,
      "learning_rate": 1.8823375955153514e-07,
      "loss": 0.3712,
      "step": 4545,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4620253164556962,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.446524064171123,
      "success_rate.epoch.env.math": 0.8987341772151899,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.7569048162519972,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4923156497992339,
      "success_rate.epoch.global": 0.6971040189125296,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930240471869328,
      "tokens_p.mean_in_band": 0.7568873355263158,
      "tokens_rate.above_band": 0.9354838709677419,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06451612903225806
    },
    {
      "epoch": 0.7563164893617021,
      "grad_norm": 1080.2769110308175,
      "learning_rate": 1.8820947092328338e-07,
      "loss": 0.5171,
      "step": 4550,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4620253164556962,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.446524064171123,
      "success_rate.epoch.env.math": 0.8989473684210526,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.757015742642026,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49234511503522405,
      "success_rate.epoch.global": 0.6972829297105729,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9962899543378996,
      "tokens_p.mean_in_band": 0.7503004807692307,
      "tokens_rate.above_band": 0.9805970149253731,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019402985074626865
    },
    {
      "epoch": 0.7571476063829787,
      "grad_norm": 77.03679756876943,
      "learning_rate": 1.88185167725232e-07,
      "loss": 0.7005,
      "step": 4555,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4620253164556962,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.448,
      "success_rate.epoch.env.math": 0.8991596638655462,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.7570711678832117,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49250362926382,
      "success_rate.epoch.global": 0.6975062712114505,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9941722972972973,
      "tokens_p.mean_in_band": 0.7371651785714286,
      "tokens_rate.above_band": 0.9296482412060302,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07035175879396985
    },
    {
      "epoch": 0.7579787234042553,
      "grad_norm": 87.16888046312441,
      "learning_rate": 1.8816085000051317e-07,
      "loss": 0.3796,
      "step": 4560,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4620253164556962,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.448,
      "success_rate.epoch.env.math": 0.8991596638655462,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.7573479152426521,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4925287881146783,
      "success_rate.epoch.global": 0.697729283397228,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9963983050847458,
      "tokens_p.mean_in_band": 0.7682291666666666,
      "tokens_rate.above_band": 0.9800664451827242,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019933554817275746
    },
    {
      "epoch": 0.7588098404255319,
      "grad_norm": 95.60483840089177,
      "learning_rate": 1.881365177922849e-07,
      "loss": 0.4044,
      "step": 4565,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.46540880503144655,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4909090909090909,
      "success_rate.epoch.env.logic": 0.448,
      "success_rate.epoch.env.math": 0.8991596638655462,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.757568859549283,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4928564638312584,
      "success_rate.epoch.global": 0.6979519669957271,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950342465753425,
      "tokens_p.mean_in_band": 0.7084517045454546,
      "tokens_rate.above_band": 0.9707446808510638,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02925531914893617
    },
    {
      "epoch": 0.7596409574468085,
      "grad_norm": 136.58477556778897,
      "learning_rate": 1.8811217114373093e-07,
      "loss": 0.4351,
      "step": 4570,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.46540880503144655,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4879518072289157,
      "success_rate.epoch.env.logic": 0.4474034620505992,
      "success_rate.epoch.env.math": 0.8991596638655462,
      "success_rate.epoch.env.sat": 0.10309278350515463,
      "success_rate.epoch.env.science": 0.7575068243858053,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4924954320903522,
      "success_rate.epoch.global": 0.6976299131458855,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.35,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9937592749629002,
      "tokens_p.mean_below_band": 4.274625098332763e-11,
      "tokens_p.mean_in_band": 0.5373263888888888,
      "tokens_rate.above_band": 0.9159223300970873,
      "tokens_rate.below_band": 0.0001941747572815534,
      "tokens_rate.in_band": 0.08388349514563107
    },
    {
      "epoch": 0.7604720744680851,
      "grad_norm": 69.68600503184477,
      "learning_rate": 1.8808781009806054e-07,
      "loss": 0.4638,
      "step": 4575,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4879518072289157,
      "success_rate.epoch.env.logic": 0.44680851063829785,
      "success_rate.epoch.env.math": 0.89937106918239,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.7575619740732318,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49213716786795775,
      "success_rate.epoch.global": 0.6973529411764706,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9909735654416505,
      "tokens_p.mean_in_band": 0.5750465645695364,
      "tokens_rate.above_band": 0.8370210469508904,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16297895304910956
    },
    {
      "epoch": 0.7613031914893617,
      "grad_norm": 154.82241261414472,
      "learning_rate": 1.8806343469850865e-07,
      "loss": 0.4098,
      "step": 4580,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4879518072289157,
      "success_rate.epoch.env.logic": 0.44680851063829785,
      "success_rate.epoch.env.math": 0.8994764397905759,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.7578373466606089,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49217178088573627,
      "success_rate.epoch.global": 0.6976197472818102,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9900210084033614,
      "tokens_p.mean_in_band": 0.7777777777777778,
      "tokens_rate.above_band": 0.9296875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0703125
    },
    {
      "epoch": 0.7621343085106383,
      "grad_norm": 59.196976003857145,
      "learning_rate": 1.8803904498833565e-07,
      "loss": 0.6436,
      "step": 4585,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4879518072289157,
      "success_rate.epoch.env.logic": 0.44754316069057104,
      "success_rate.epoch.env.math": 0.8994764397905759,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.758057194734453,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49225855344265596,
      "success_rate.epoch.global": 0.697841726618705,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994951923076923,
      "tokens_p.mean_in_band": 0.6676136363636364,
      "tokens_rate.above_band": 0.9219858156028369,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07801418439716312
    },
    {
      "epoch": 0.7629654255319149,
      "grad_norm": 183.89250930950763,
      "learning_rate": 1.8801464101082725e-07,
      "loss": 0.4558,
      "step": 4590,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4879518072289157,
      "success_rate.epoch.env.logic": 0.44754316069057104,
      "success_rate.epoch.env.math": 0.8987473903966597,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.758057194734453,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4921922762250272,
      "success_rate.epoch.global": 0.6978280011740534,
      "success_rate.window.env.math": 0.8,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5166666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9882352941176471,
      "tokens_p.mean_in_band": 0.579358552631579,
      "tokens_rate.above_band": 0.8173076923076923,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18269230769230768
    },
    {
      "epoch": 0.7637965425531915,
      "grad_norm": 90.28466282422191,
      "learning_rate": 1.8799022280929457e-07,
      "loss": 0.5128,
      "step": 4595,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4879518072289157,
      "success_rate.epoch.env.logic": 0.4482758620689655,
      "success_rate.epoch.env.math": 0.8989583333333333,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.7582766439909298,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4922980120042586,
      "success_rate.epoch.global": 0.6981381029174608,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.988031914893617,
      "tokens_p.mean_in_band": 0.8483072916666666,
      "tokens_rate.above_band": 0.9690721649484536,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030927835051546393
    },
    {
      "epoch": 0.7646276595744681,
      "grad_norm": 57.17971859733982,
      "learning_rate": 1.879657904270739e-07,
      "loss": 0.4732,
      "step": 4600,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48502994011976047,
      "success_rate.epoch.env.logic": 0.44900662251655626,
      "success_rate.epoch.env.math": 0.899063475546306,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.758440969861772,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49240087198559546,
      "success_rate.epoch.global": 0.6983011130638547,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9913245178258329,
      "tokens_p.mean_below_band": 5.885958671569824e-07,
      "tokens_p.mean_in_band": 0.5678986025528169,
      "tokens_rate.above_band": 0.8572144288577155,
      "tokens_rate.below_band": 0.000501002004008016,
      "tokens_rate.in_band": 0.14228456913827656
    },
    {
      "epoch": 0.7654587765957447,
      "grad_norm": 61.728200587299696,
      "learning_rate": 1.8794134390752677e-07,
      "loss": 0.2586,
      "step": 4605,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48502994011976047,
      "success_rate.epoch.env.logic": 0.44900662251655626,
      "success_rate.epoch.env.math": 0.899063475546306,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7586050724637681,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4924157904039587,
      "success_rate.epoch.global": 0.6984336114770897,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9893973214285714,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 0.7662898936170213,
      "grad_norm": 126.1425396514624,
      "learning_rate": 1.8791688329403973e-07,
      "loss": 0.405,
      "step": 4610,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48502994011976047,
      "success_rate.epoch.env.logic": 0.44900662251655626,
      "success_rate.epoch.env.math": 0.899063475546306,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7586518887129609,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49242004642661263,
      "success_rate.epoch.global": 0.6985078993563487,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.16666666666666669,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9936143761301989,
      "tokens_p.mean_in_band": 0.65159375,
      "tokens_rate.above_band": 0.8984565393988627,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10154346060113728
    },
    {
      "epoch": 0.7671210106382979,
      "grad_norm": 103.05027562454406,
      "learning_rate": 1.8789240863002443e-07,
      "loss": 0.394,
      "step": 4615,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.44900662251655626,
      "success_rate.epoch.env.math": 0.8991683991683992,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7585895117540687,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4927025777574016,
      "success_rate.epoch.global": 0.6985820786434732,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.989029255319149,
      "tokens_p.mean_in_band": 0.7979403409090909,
      "tokens_rate.above_band": 0.962457337883959,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03754266211604096
    },
    {
      "epoch": 0.7679521276595744,
      "grad_norm": 235.67823000533363,
      "learning_rate": 1.8786791995891731e-07,
      "loss": 0.5307,
      "step": 4620,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.44900662251655626,
      "success_rate.epoch.env.math": 0.8992731048805815,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7585817524841915,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49271139107033846,
      "success_rate.epoch.global": 0.698656149576395,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9877717391304348,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_p.mean_in_band": 0.8000710227272727,
      "tokens_rate.above_band": 0.9387755102040817,
      "tokens_rate.below_band": 0.00510204081632653,
      "tokens_rate.in_band": 0.05612244897959184
    },
    {
      "epoch": 0.768783244680851,
      "grad_norm": 119.01019874978113,
      "learning_rate": 1.8784341732417986e-07,
      "loss": 0.2938,
      "step": 4625,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4497354497354497,
      "success_rate.epoch.env.math": 0.8995859213250518,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7587996389891697,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4928258938129149,
      "success_rate.epoch.global": 0.6990078786110301,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9949596774193549,
      "tokens_p.mean_in_band": 0.80078125,
      "tokens_rate.above_band": 0.9959839357429718,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004016064257028112
    },
    {
      "epoch": 0.7696143617021277,
      "grad_norm": 63.59816524060304,
      "learning_rate": 1.8781890076929817e-07,
      "loss": 0.4444,
      "step": 4630,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4497354497354497,
      "success_rate.epoch.env.math": 0.8995859213250518,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7589004055881028,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49283505441281794,
      "success_rate.epoch.global": 0.6991253644314869,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970734126984127,
      "tokens_p.mean_in_band": 0.7033854166666667,
      "tokens_rate.above_band": 0.9545454545454546,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.045454545454545456
    },
    {
      "epoch": 0.7704454787234043,
      "grad_norm": 87.13401439465125,
      "learning_rate": 1.877943703377832e-07,
      "loss": 0.3747,
      "step": 4635,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.449868073878628,
      "success_rate.epoch.env.math": 0.8996897621509824,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.759009009009009,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49286642426645566,
      "success_rate.epoch.global": 0.6991988346686089,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957425068119891,
      "tokens_p.mean_in_band": 0.6631804435483871,
      "tokens_rate.above_band": 0.9594771241830066,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040522875816993466
    },
    {
      "epoch": 0.7712765957446809,
      "grad_norm": 125.8055342406205,
      "learning_rate": 1.8776982607317038e-07,
      "loss": 0.4595,
      "step": 4640,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.449868073878628,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7590632740373789,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49289956089167275,
      "success_rate.epoch.global": 0.6993739991265104,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970238095238095,
      "tokens_p.mean_in_band": 0.4344429347826087,
      "tokens_rate.above_band": 0.9319526627218935,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06804733727810651
    },
    {
      "epoch": 0.7721077127659575,
      "grad_norm": 111.69254458982232,
      "learning_rate": 1.8774526801901982e-07,
      "loss": 0.5783,
      "step": 4645,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4492753623188406,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7592800899887514,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49286538856363493,
      "success_rate.epoch.global": 0.6994471923188827,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982127383015598,
      "tokens_p.mean_in_band": 0.5079385080645161,
      "tokens_rate.above_band": 0.9490131578947368,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05098684210526316
    },
    {
      "epoch": 0.772938829787234,
      "grad_norm": 278.6715397925128,
      "learning_rate": 1.87720696218916e-07,
      "loss": 0.3832,
      "step": 4650,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4486842105263158,
      "success_rate.epoch.env.math": 0.8990731204943357,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7591093117408907,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.492711860423085,
      "success_rate.epoch.global": 0.6991420677621055,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9966346153846154,
      "tokens_p.mean_below_band": 6.007030606269836e-08,
      "tokens_p.mean_in_band": 0.5984375,
      "tokens_rate.above_band": 0.9544787077826725,
      "tokens_rate.below_band": 0.0014684287812041115,
      "tokens_rate.in_band": 0.04405286343612335
    },
    {
      "epoch": 0.7737699468085106,
      "grad_norm": 89.42207069568659,
      "learning_rate": 1.8769611071646794e-07,
      "loss": 0.4132,
      "step": 4655,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4486842105263158,
      "success_rate.epoch.env.math": 0.8991769547325102,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.7593799146259268,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4927459001615588,
      "success_rate.epoch.global": 0.6994043295074822,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9847383720930233,
      "tokens_p.mean_in_band": 0.853515625,
      "tokens_rate.above_band": 0.9699248120300752,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03007518796992481
    },
    {
      "epoch": 0.7746010638297872,
      "grad_norm": 98.70776367422869,
      "learning_rate": 1.8767151155530878e-07,
      "loss": 0.5693,
      "step": 4660,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4486842105263158,
      "success_rate.epoch.env.math": 0.8992805755395683,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.7593714927048261,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49272206086864245,
      "success_rate.epoch.global": 0.6993758165190884,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.3,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9972564017292983,
      "tokens_p.mean_in_band": 0.6680445995145631,
      "tokens_rate.above_band": 0.93588546529723,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06411453470277
    },
    {
      "epoch": 0.7754321808510638,
      "grad_norm": 158.28623187938004,
      "learning_rate": 1.8764689877909605e-07,
      "loss": 0.4424,
      "step": 4665,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.45013123359580054,
      "success_rate.epoch.env.math": 0.8993839835728953,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.7593630858936982,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4928622448951592,
      "success_rate.epoch.global": 0.6995359628770301,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9898255813953488,
      "tokens_p.mean_below_band": 1.8189894035458565e-09,
      "tokens_p.mean_in_band": 0.7298583984375,
      "tokens_rate.above_band": 0.9662921348314607,
      "tokens_rate.below_band": 0.003745318352059925,
      "tokens_rate.in_band": 0.0299625468164794
    },
    {
      "epoch": 0.7762632978723404,
      "grad_norm": 112.02966213611131,
      "learning_rate": 1.876222724315114e-07,
      "loss": 0.4689,
      "step": 4670,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4508519003931848,
      "success_rate.epoch.env.math": 0.8993839835728953,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.759300761990139,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4929220942491433,
      "success_rate.epoch.global": 0.6995652173913044,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7777777777777778,
      "tokens_p.mean_above_band": 0.994526836158192,
      "tokens_p.mean_in_band": 0.5738407258064516,
      "tokens_rate.above_band": 0.9580514208389715,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04194857916102842
    },
    {
      "epoch": 0.777094414893617,
      "grad_norm": 87.2594615700588,
      "learning_rate": 1.8759763255626054e-07,
      "loss": 0.4573,
      "step": 4675,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4508519003931848,
      "success_rate.epoch.env.math": 0.8997955010224948,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.7594624860022396,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4929742071092978,
      "success_rate.epoch.global": 0.6998696974084262,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.999664810231023,
      "tokens_p.mean_in_band": 0.5460611979166666,
      "tokens_rate.above_band": 0.9619047619047619,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0380952380952381
    },
    {
      "epoch": 0.7779255319148937,
      "grad_norm": 98.47884497130033,
      "learning_rate": 1.875729791970732e-07,
      "loss": 0.6578,
      "step": 4680,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.45157068062827227,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.7596239928379588,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49307282402278063,
      "success_rate.epoch.global": 0.7001301894980472,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9997102009273571,
      "tokens_p.mean_in_band": 0.5305266203703703,
      "tokens_rate.above_band": 0.9599406528189911,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040059347181008904
    },
    {
      "epoch": 0.7787566489361702,
      "grad_norm": 79.4876342910686,
      "learning_rate": 1.8754831239770312e-07,
      "loss": 0.4461,
      "step": 4685,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.45157068062827227,
      "success_rate.epoch.env.math": 0.9,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.7598926894701542,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4930649768045274,
      "success_rate.epoch.global": 0.7002457002457002,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4523809523809524,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9959072305593452,
      "tokens_p.mean_in_band": 0.640869140625,
      "tokens_rate.above_band": 0.93854033290653,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06145966709346991
    },
    {
      "epoch": 0.7795877659574468,
      "grad_norm": 73.45925761774734,
      "learning_rate": 1.875236322019278e-07,
      "loss": 0.5456,
      "step": 4690,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4516971279373368,
      "success_rate.epoch.env.math": 0.90020366598778,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.7598926894701542,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4930949871042405,
      "success_rate.epoch.global": 0.700274447493861,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9897186147186147,
      "tokens_p.mean_in_band": 0.4779641544117647,
      "tokens_rate.above_band": 0.7310126582278481,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2689873417721519
    },
    {
      "epoch": 0.7804188829787234,
      "grad_norm": 109.79854067353953,
      "learning_rate": 1.874989386535485e-07,
      "loss": 0.4015,
      "step": 4695,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4516971279373368,
      "success_rate.epoch.env.math": 0.900709219858156,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.760053619302949,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4931555765318015,
      "success_rate.epoch.global": 0.7006204010965229,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.988108407079646,
      "tokens_p.mean_below_band": 1.126900315284729e-07,
      "tokens_p.mean_in_band": 0.84140625,
      "tokens_rate.above_band": 0.9495798319327731,
      "tokens_rate.below_band": 0.008403361344537815,
      "tokens_rate.in_band": 0.04201680672268908
    },
    {
      "epoch": 0.78125,
      "grad_norm": 109.7366112421173,
      "learning_rate": 1.8747423179639027e-07,
      "loss": 0.3603,
      "step": 4700,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.4516971279373368,
      "success_rate.epoch.env.math": 0.9008097165991903,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.7603748326639893,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49319391381380834,
      "success_rate.epoch.global": 0.7009224560392043,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9846854304635762,
      "tokens_p.mean_in_band": 0.80625,
      "tokens_rate.above_band": 0.967948717948718,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03205128205128205
    },
    {
      "epoch": 0.7820811170212766,
      "grad_norm": 56.87436390428632,
      "learning_rate": 1.874495116743017e-07,
      "loss": 0.6172,
      "step": 4705,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4880952380952381,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.901010101010101,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7604282846308276,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49324992089314124,
      "success_rate.epoch.global": 0.700993806711796,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9935661764705882,
      "tokens_p.mean_below_band": 4.5821070671081543e-07,
      "tokens_p.mean_in_band": 0.16626420454545454,
      "tokens_rate.above_band": 0.38095238095238093,
      "tokens_rate.below_band": 0.0028011204481792717,
      "tokens_rate.in_band": 0.6162464985994398
    },
    {
      "epoch": 0.7829122340425532,
      "grad_norm": 64.95903033996777,
      "learning_rate": 1.8742477833115493e-07,
      "loss": 0.5067,
      "step": 4710,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4911242603550296,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.901010101010101,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7606418542455984,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49354470197264694,
      "success_rate.epoch.global": 0.7012089810017271,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.988080039964476,
      "tokens_p.mean_in_band": 0.5522765456989247,
      "tokens_rate.above_band": 0.8288553551711446,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17114464482885536
    },
    {
      "epoch": 0.7837433510638298,
      "grad_norm": 78.81993271704219,
      "learning_rate": 1.8740003181084564e-07,
      "loss": 0.2517,
      "step": 4715,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.901010101010101,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7608550434201736,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49383620887068047,
      "success_rate.epoch.global": 0.7014238458219474,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.995873786407767,
      "tokens_p.mean_in_band": 0.7572544642857143,
      "tokens_rate.above_band": 0.9735349716446124,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026465028355387523
    },
    {
      "epoch": 0.7845744680851063,
      "grad_norm": 94.4205246120049,
      "learning_rate": 1.873752721572928e-07,
      "loss": 0.4092,
      "step": 4720,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.9011099899091827,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7610146862483311,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4938598026640659,
      "success_rate.epoch.global": 0.7015955153083225,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.990296803652968,
      "tokens_p.mean_in_band": 0.720703125,
      "tokens_rate.above_band": 0.9647577092511013,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03524229074889868
    },
    {
      "epoch": 0.785405585106383,
      "grad_norm": 270.09233023408433,
      "learning_rate": 1.8735049941443872e-07,
      "loss": 0.5048,
      "step": 4725,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.9013091641490433,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7611209964412812,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4938875739761395,
      "success_rate.epoch.global": 0.7017669875017957,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9905555555555555,
      "tokens_p.mean_in_band": 0.6970052083333333,
      "tokens_rate.above_band": 0.8823529411764706,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11764705882352941
    },
    {
      "epoch": 0.7862367021276596,
      "grad_norm": 54.12579572871874,
      "learning_rate": 1.87325713626249e-07,
      "loss": 0.4699,
      "step": 4730,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49411764705882355,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.9015075376884422,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7613333333333333,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49392491128808963,
      "success_rate.epoch.global": 0.7020238266111669,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.8571428571428572,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9881993006993007,
      "tokens_p.mean_in_band": 0.66552734375,
      "tokens_rate.above_band": 0.9470198675496688,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.052980132450331126
    },
    {
      "epoch": 0.7870678191489362,
      "grad_norm": 65.33434926989125,
      "learning_rate": 1.873009148367123e-07,
      "loss": 0.3686,
      "step": 4735,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49707602339181284,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.9015075376884422,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.7615452930728241,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4939519717667284,
      "success_rate.epoch.global": 0.7021368134232038,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9968112244897959,
      "tokens_p.mean_in_band": 0.7623697916666666,
      "tokens_rate.above_band": 0.9961880559085133,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0038119440914866584
    },
    {
      "epoch": 0.7878989361702128,
      "grad_norm": 127.47005455921338,
      "learning_rate": 1.8727610308984044e-07,
      "loss": 0.502,
      "step": 4740,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.9017051153460381,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7614821388950521,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4941981664347731,
      "success_rate.epoch.global": 0.7021489971346705,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9927998812351544,
      "tokens_p.mean_in_band": 0.611686862244898,
      "tokens_rate.above_band": 0.8957446808510638,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10425531914893617
    },
    {
      "epoch": 0.7887300531914894,
      "grad_norm": 76.46894568721432,
      "learning_rate": 1.8725127842966812e-07,
      "loss": 0.3691,
      "step": 4745,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45241199478487615,
      "success_rate.epoch.env.math": 0.9018036072144289,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7616936377743294,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49422634741183374,
      "success_rate.epoch.global": 0.7023622047244095,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9893830128205128,
      "tokens_p.mean_in_band": 0.5825639204545454,
      "tokens_rate.above_band": 0.8764044943820225,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12359550561797752
    },
    {
      "epoch": 0.789561170212766,
      "grad_norm": 46.0606289653229,
      "learning_rate": 1.8722644090025308e-07,
      "loss": 0.4443,
      "step": 4750,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.453125,
      "success_rate.epoch.env.math": 0.9018036072144289,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7616832779623477,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4942902242666649,
      "success_rate.epoch.global": 0.7024320457796852,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9892293689320388,
      "tokens_p.mean_below_band": 1.6555645743210334e-12,
      "tokens_p.mean_in_band": 0.7705965909090909,
      "tokens_rate.above_band": 0.8995633187772926,
      "tokens_rate.below_band": 0.004366812227074236,
      "tokens_rate.in_band": 0.09606986899563319
    },
    {
      "epoch": 0.7903922872340425,
      "grad_norm": 44.382224407806696,
      "learning_rate": 1.8720159054567584e-07,
      "loss": 0.3246,
      "step": 4755,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4538361508452536,
      "success_rate.epoch.env.math": 0.9019019019019019,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7617887978746956,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49437340294348986,
      "success_rate.epoch.global": 0.7026022304832714,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9885737885462555,
      "tokens_p.mean_in_band": 0.7067792338709677,
      "tokens_rate.above_band": 0.8798449612403101,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12015503875968993
    },
    {
      "epoch": 0.7912234042553191,
      "grad_norm": 481.43337915230035,
      "learning_rate": 1.871767274100397e-07,
      "loss": 0.5468,
      "step": 4760,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45454545454545453,
      "success_rate.epoch.env.math": 0.9019019019019019,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7617783676177837,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4944369368928798,
      "success_rate.epoch.global": 0.7026718102586084,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995365466101695,
      "tokens_p.mean_in_band": 0.653671875,
      "tokens_rate.above_band": 0.9496981891348089,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05030181086519115
    },
    {
      "epoch": 0.7920545212765957,
      "grad_norm": 448.1947975683327,
      "learning_rate": 1.8715185153747062e-07,
      "loss": 0.4941,
      "step": 4765,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45454545454545453,
      "success_rate.epoch.env.math": 0.902,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7618732052131655,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49445447650137786,
      "success_rate.epoch.global": 0.7028261490151299,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994050875273523,
      "tokens_p.mean_in_band": 0.658203125,
      "tokens_rate.above_band": 0.9744136460554371,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0255863539445629
    },
    {
      "epoch": 0.7928856382978723,
      "grad_norm": 80.66313638530086,
      "learning_rate": 1.871269629721172e-07,
      "loss": 0.5221,
      "step": 4770,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45454545454545453,
      "success_rate.epoch.env.math": 0.902,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7620309050772627,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49446881285265953,
      "success_rate.epoch.global": 0.7029533456983877,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9901620370370371,
      "tokens_p.mean_in_band": 0.65625,
      "tokens_rate.above_band": 0.9432314410480349,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056768558951965066
    },
    {
      "epoch": 0.793716755319149,
      "grad_norm": 123.52223254235444,
      "learning_rate": 1.8710206175815048e-07,
      "loss": 0.501,
      "step": 4775,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45395590142671854,
      "success_rate.epoch.env.math": 0.9020979020979021,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7622932745314223,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49444796907387095,
      "success_rate.epoch.global": 0.7031071835803877,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9928192800788954,
      "tokens_p.mean_in_band": 0.6898777173913043,
      "tokens_rate.above_band": 0.9168173598553345,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08318264014466546
    },
    {
      "epoch": 0.7945478723404256,
      "grad_norm": 98.88084300513229,
      "learning_rate": 1.870771479397641e-07,
      "loss": 0.4787,
      "step": 4780,
      "success_rate.epoch.env.abd": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4533678756476684,
      "success_rate.epoch.env.math": 0.9022931206380858,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7622824410663142,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4944112744644186,
      "success_rate.epoch.global": 0.7031183255019222,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988938053097345,
      "tokens_p.mean_in_band": 0.6005208333333333,
      "tokens_rate.above_band": 0.9576271186440678,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0423728813559322
    },
    {
      "epoch": 0.7953789893617021,
      "grad_norm": 137.35959469548166,
      "learning_rate": 1.8705222156117395e-07,
      "loss": 0.4876,
      "step": 4785,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4533678756476684,
      "success_rate.epoch.env.math": 0.9025844930417495,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7624394539850287,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49353376312090674,
      "success_rate.epoch.global": 0.7032716927453769,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9884956173780488,
      "tokens_p.mean_below_band": 1.7229467630386353e-08,
      "tokens_p.mean_in_band": 0.17882948833459789,
      "tokens_rate.above_band": 0.33223600911623197,
      "tokens_rate.below_band": 0.0002532286654849329,
      "tokens_rate.in_band": 0.6675107622182831
    },
    {
      "epoch": 0.7962101063829787,
      "grad_norm": 55.68244950472272,
      "learning_rate": 1.8702728266661825e-07,
      "loss": 0.4169,
      "step": 4790,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45348837209302323,
      "success_rate.epoch.env.math": 0.9026812313803376,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.762544014084507,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4935630172012177,
      "success_rate.epoch.global": 0.7033404406538735,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978911042944786,
      "tokens_p.mean_in_band": 0.5463709677419355,
      "tokens_rate.above_band": 0.9633569739952719,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03664302600472813
    },
    {
      "epoch": 0.7970412234042553,
      "grad_norm": 107.77214994914767,
      "learning_rate": 1.8700233130035744e-07,
      "loss": 0.4674,
      "step": 4795,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45348837209302323,
      "success_rate.epoch.env.math": 0.9028741328047571,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7627006817681988,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49333686841688634,
      "success_rate.epoch.global": 0.7034512143161483,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.993421052631579,
      "tokens_p.mean_in_band": 0.794677734375,
      "tokens_rate.above_band": 0.9726962457337884,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027303754266211604
    },
    {
      "epoch": 0.7978723404255319,
      "grad_norm": 106.40908438699832,
      "learning_rate": 1.8697736750667404e-07,
      "loss": 0.5547,
      "step": 4800,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45348837209302323,
      "success_rate.epoch.env.math": 0.902970297029703,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7626373626373626,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49333985433453265,
      "success_rate.epoch.global": 0.7034776437189496,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9938345546786922,
      "tokens_p.mean_below_band": 5.995204332975845e-15,
      "tokens_p.mean_in_band": 0.543395011655746,
      "tokens_rate.above_band": 0.877132262051916,
      "tokens_rate.below_band": 0.00024721878862793575,
      "tokens_rate.in_band": 0.12262051915945611
    },
    {
      "epoch": 0.7987034574468085,
      "grad_norm": 94.4949934902306,
      "learning_rate": 1.8695239132987267e-07,
      "loss": 0.3545,
      "step": 4805,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.26666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45348837209302323,
      "success_rate.epoch.env.math": 0.9030662710187932,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7627937623544916,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4933627973987344,
      "success_rate.epoch.global": 0.7036459072208824,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9889937106918238,
      "tokens_p.mean_in_band": 0.6333333333333333,
      "tokens_rate.above_band": 0.9137931034482759,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08620689655172414
    },
    {
      "epoch": 0.7995345744680851,
      "grad_norm": 103.10973473342527,
      "learning_rate": 1.8692740281427998e-07,
      "loss": 0.4871,
      "step": 4810,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4529032258064516,
      "success_rate.epoch.env.math": 0.9031620553359684,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7629499561018437,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4974991760452152,
      "success_rate.epoch.global": 0.703756201275691,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9942062248096731,
      "tokens_p.mean_below_band": 2.1736923372372985e-10,
      "tokens_p.mean_in_band": 0.5403772249190939,
      "tokens_rate.above_band": 0.8780967361384192,
      "tokens_rate.below_band": 0.00039323633503735744,
      "tokens_rate.in_band": 0.12151002752654345
    },
    {
      "epoch": 0.8003656914893617,
      "grad_norm": 79.63995874347275,
      "learning_rate": 1.8690240200424442e-07,
      "loss": 0.5516,
      "step": 4815,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.4529032258064516,
      "success_rate.epoch.env.math": 0.903448275862069,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7629385964912281,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49753214340252877,
      "success_rate.epoch.global": 0.703850509626274,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942651098901099,
      "tokens_p.mean_in_band": 0.5072115384615384,
      "tokens_rate.above_band": 0.9859154929577465,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014084507042253521
    },
    {
      "epoch": 0.8011968085106383,
      "grad_norm": 74.04759828394826,
      "learning_rate": 1.8687738894413635e-07,
      "loss": 0.5614,
      "step": 4820,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.4529032258064516,
      "success_rate.epoch.env.math": 0.9036381514257621,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7629791894852136,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4975530950895905,
      "success_rate.epoch.global": 0.7040022627633998,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9886363636363636,
      "tokens_p.mean_in_band": 0.5535386029411765,
      "tokens_rate.above_band": 0.8859060402684564,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11409395973154363
    },
    {
      "epoch": 0.8020279255319149,
      "grad_norm": 343.6331133242387,
      "learning_rate": 1.8685236367834774e-07,
      "loss": 0.4205,
      "step": 4825,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.45314505776636715,
      "success_rate.epoch.env.math": 0.9037328094302554,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7630310994305738,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4975884041722967,
      "success_rate.epoch.global": 0.7039706090151194,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9956226745458525,
      "tokens_p.mean_in_band": 0.5469341856060606,
      "tokens_rate.above_band": 0.8964096527369041,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10359034726309593
    },
    {
      "epoch": 0.8028590425531915,
      "grad_norm": 69.80312069617709,
      "learning_rate": 1.868273262512924e-07,
      "loss": 0.3274,
      "step": 4830,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.454661558109834,
      "success_rate.epoch.env.math": 0.9037328094302554,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7631348511383538,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4977356998133192,
      "success_rate.epoch.global": 0.7040801920090357,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940548780487805,
      "tokens_p.mean_in_band": 0.7297952586206896,
      "tokens_rate.above_band": 0.9339407744874715,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06605922551252848
    },
    {
      "epoch": 0.8036901595744681,
      "grad_norm": 137.664539334712,
      "learning_rate": 1.8680227670740552e-07,
      "loss": 0.5603,
      "step": 4835,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.454661558109834,
      "success_rate.epoch.env.math": 0.9038272816486752,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7632385120350109,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4975020557450327,
      "success_rate.epoch.global": 0.7041061097784677,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9936926605504587,
      "tokens_p.mean_in_band": 0.6197916666666666,
      "tokens_rate.above_band": 0.923728813559322,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07627118644067797
    },
    {
      "epoch": 0.8045212765957447,
      "grad_norm": 68.32100318860228,
      "learning_rate": 1.8677721509114402e-07,
      "loss": 0.5593,
      "step": 4840,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.454661558109834,
      "success_rate.epoch.env.math": 0.903921568627451,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.7633938333697792,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49752474740990044,
      "success_rate.epoch.global": 0.7042730221407418,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9912790697674418,
      "tokens_p.mean_in_band": 0.6490162037037037,
      "tokens_rate.above_band": 0.864321608040201,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.135678391959799
    },
    {
      "epoch": 0.8053523936170213,
      "grad_norm": 82.43262796546212,
      "learning_rate": 1.8675214144698605e-07,
      "loss": 0.487,
      "step": 4845,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.454661558109834,
      "success_rate.epoch.env.math": 0.9040156709108716,
      "success_rate.epoch.env.sat": 0.10367892976588629,
      "success_rate.epoch.env.science": 0.7637038654728107,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.497529858183969,
      "success_rate.epoch.global": 0.7044654176644598,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9903273809523809,
      "tokens_p.mean_in_band": 0.6241957720588235,
      "tokens_rate.above_band": 0.860655737704918,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13934426229508196
    },
    {
      "epoch": 0.8061835106382979,
      "grad_norm": 73.98335530994913,
      "learning_rate": 1.8672705581943123e-07,
      "loss": 0.4966,
      "step": 4850,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.454661558109834,
      "success_rate.epoch.env.math": 0.9042033235581622,
      "success_rate.epoch.env.sat": 0.10367892976588629,
      "success_rate.epoch.env.science": 0.7638585770405937,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4975609822035212,
      "success_rate.epoch.global": 0.7046734234234234,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9939786038728186,
      "tokens_p.mean_below_band": 2.1047890186309814e-07,
      "tokens_p.mean_in_band": 0.4960646299254526,
      "tokens_rate.above_band": 0.8165137614678899,
      "tokens_rate.below_band": 0.00019519812609798947,
      "tokens_rate.in_band": 0.1832910404060121
    },
    {
      "epoch": 0.8070146276595744,
      "grad_norm": 165.12937411134914,
      "learning_rate": 1.8670195825300036e-07,
      "loss": 0.5245,
      "step": 4855,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028901734104047,
      "success_rate.epoch.env.logic": 0.454661558109834,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7637949836423119,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4978438061895916,
      "success_rate.epoch.global": 0.7047819971870605,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9910493827160494,
      "tokens_p.mean_in_band": 0.7693014705882353,
      "tokens_rate.above_band": 0.9225512528473804,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0774487471526196
    },
    {
      "epoch": 0.807845744680851,
      "grad_norm": 77.03434377430698,
      "learning_rate": 1.8667684879223553e-07,
      "loss": 0.3306,
      "step": 4860,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.45535714285714285,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7638464893153074,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.49764898046321887,
      "success_rate.epoch.global": 0.7047659215520877,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9882422654690619,
      "tokens_p.mean_in_band": 0.5029169386422977,
      "tokens_rate.above_band": 0.7234657039711191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.27653429602888085
    },
    {
      "epoch": 0.8086768617021277,
      "grad_norm": 104.41531889994998,
      "learning_rate": 1.8665172748169981e-07,
      "loss": 0.5173,
      "step": 4865,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3125,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4547770700636943,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7636799651188141,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.4975811080095878,
      "success_rate.epoch.global": 0.7045678144764582,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.27777777777777773,
      "success_rate.window.global": 0.4,
      "tokens_p.mean_above_band": 0.9997700515084621,
      "tokens_p.mean_below_band": 5.343463271856308e-08,
      "tokens_p.mean_in_band": 0.6004569575471698,
      "tokens_rate.above_band": 0.9611032531824611,
      "tokens_rate.below_band": 0.0014144271570014145,
      "tokens_rate.in_band": 0.03748231966053748
    },
    {
      "epoch": 0.8095079787234043,
      "grad_norm": 69.62539356359133,
      "learning_rate": 1.8662659436597742e-07,
      "loss": 0.4742,
      "step": 4870,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4547770700636943,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7638858636462644,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5012762966457731,
      "success_rate.epoch.global": 0.7047752808988764,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.995343137254902,
      "tokens_p.mean_in_band": 0.755078125,
      "tokens_rate.above_band": 0.9622641509433962,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03773584905660377
    },
    {
      "epoch": 0.8103390957446809,
      "grad_norm": 85.62866956559783,
      "learning_rate": 1.8660144948967348e-07,
      "loss": 0.4147,
      "step": 4875,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4547770700636943,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7641940395910376,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5013043126407525,
      "success_rate.epoch.global": 0.70502385630087,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9945032573289903,
      "tokens_p.mean_in_band": 0.778125,
      "tokens_rate.above_band": 0.953416149068323,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.046583850931677016
    },
    {
      "epoch": 0.8111702127659575,
      "grad_norm": 63.483552341582175,
      "learning_rate": 1.8657629289741398e-07,
      "loss": 0.4129,
      "step": 4880,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4547770700636943,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7644502390265102,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5013276034985228,
      "success_rate.epoch.global": 0.7052306829336699,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9889846743295019,
      "tokens_p.mean_in_band": 0.7462890625,
      "tokens_rate.above_band": 0.9288256227758007,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0711743772241993
    },
    {
      "epoch": 0.812001329787234,
      "grad_norm": 101.85302100317311,
      "learning_rate": 1.8655112463384573e-07,
      "loss": 0.4437,
      "step": 4885,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4547770700636943,
      "success_rate.epoch.env.math": 0.904390243902439,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7646547980894486,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5013461997769717,
      "success_rate.epoch.global": 0.705395935529082,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9921573359073359,
      "tokens_p.mean_in_band": 0.6309742647058824,
      "tokens_rate.above_band": 0.9384057971014492,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06159420289855073
    },
    {
      "epoch": 0.8128324468085106,
      "grad_norm": 81.62243492391613,
      "learning_rate": 1.8652594474363616e-07,
      "loss": 0.4112,
      "step": 4890,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4541984732824427,
      "success_rate.epoch.env.math": 0.9044834307992202,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.7649609713790113,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5013299055410709,
      "success_rate.epoch.global": 0.7055858882822343,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9976607270773639,
      "tokens_p.mean_in_band": 0.6684283088235294,
      "tokens_rate.above_band": 0.9480475382003396,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05195246179966044
    },
    {
      "epoch": 0.8136635638297872,
      "grad_norm": 79.96352676025562,
      "learning_rate": 1.865007532714735e-07,
      "loss": 0.5706,
      "step": 4895,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.4541984732824427,
      "success_rate.epoch.env.math": 0.9044834307992202,
      "success_rate.epoch.env.sat": 0.10631229235880399,
      "success_rate.epoch.env.science": 0.764948006932409,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5015562513685872,
      "success_rate.epoch.global": 0.7055532242271646,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.994770749665328,
      "tokens_p.mean_in_band": 0.6636458333333334,
      "tokens_rate.above_band": 0.9521988527724665,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04780114722753346
    },
    {
      "epoch": 0.8144946808510638,
      "grad_norm": 57.590716677674045,
      "learning_rate": 1.8647555026206637e-07,
      "loss": 0.3592,
      "step": 4900,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.4541984732824427,
      "success_rate.epoch.env.math": 0.9045764362220059,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.7652023371564597,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5018568483201181,
      "success_rate.epoch.global": 0.7058412520961431,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9909695817490495,
      "tokens_p.mean_in_band": 0.8050130208333334,
      "tokens_rate.above_band": 0.9163763066202091,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08362369337979095
    },
    {
      "epoch": 0.8153257978723404,
      "grad_norm": 71.91926404585581,
      "learning_rate": 1.8645033576014394e-07,
      "loss": 0.4018,
      "step": 4905,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.4548919949174079,
      "success_rate.epoch.env.math": 0.9045764362220059,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.7653039152065758,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.501929130109671,
      "success_rate.epoch.global": 0.7059645201843833,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937782805429864,
      "tokens_p.mean_below_band": 2.7830537874251604e-10,
      "tokens_p.mean_in_band": 0.8141741071428571,
      "tokens_rate.above_band": 0.9650655021834061,
      "tokens_rate.below_band": 0.004366812227074236,
      "tokens_rate.in_band": 0.03056768558951965
    },
    {
      "epoch": 0.816156914893617,
      "grad_norm": 274.7525688377167,
      "learning_rate": 1.8642510981045584e-07,
      "loss": 0.3523,
      "step": 4910,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4457831325301205,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45558375634517767,
      "success_rate.epoch.env.math": 0.9046692607003891,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.7654054054054054,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5015154661496692,
      "success_rate.epoch.global": 0.7059316120027913,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947382869692533,
      "tokens_p.mean_in_band": 0.7389705882352942,
      "tokens_rate.above_band": 0.9757142857142858,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024285714285714285
    },
    {
      "epoch": 0.8169880319148937,
      "grad_norm": 52.93996123958456,
      "learning_rate": 1.863998724577719e-07,
      "loss": 0.4959,
      "step": 4915,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4491017964071856,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.4550063371356147,
      "success_rate.epoch.env.math": 0.9048543689320389,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.765290685109142,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5017710691135683,
      "success_rate.epoch.global": 0.7058987588899736,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.8125,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0,
      "tokens_p.mean_below_band": 1.7229467630386353e-08,
      "tokens_p.mean_in_band": 0.44343171296296297,
      "tokens_rate.above_band": 0.9700214132762313,
      "tokens_rate.below_band": 0.0010706638115631692,
      "tokens_rate.in_band": 0.028907922912205567
    },
    {
      "epoch": 0.8178191489361702,
      "grad_norm": 470.3258572603504,
      "learning_rate": 1.8637462374688222e-07,
      "loss": 0.3963,
      "step": 4920,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4491017964071856,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45569620253164556,
      "success_rate.epoch.env.math": 0.9049466537342385,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.7652774778665515,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5018409730186264,
      "success_rate.epoch.global": 0.7060052946913752,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.990625,
      "tokens_p.mean_in_band": 0.7449776785714286,
      "tokens_rate.above_band": 0.9554140127388535,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044585987261146494
    },
    {
      "epoch": 0.8186502659574468,
      "grad_norm": 222.2564187965822,
      "learning_rate": 1.863493637225971e-07,
      "loss": 0.5047,
      "step": 4925,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4491017964071856,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.35294117647058826,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45512010113780027,
      "success_rate.epoch.env.math": 0.9049466537342385,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7654294346137246,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5017696296789563,
      "success_rate.epoch.global": 0.7059314954051796,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9998148148148148,
      "tokens_p.mean_in_band": 0.6492686170212766,
      "tokens_rate.above_band": 0.9349030470914127,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06509695290858726
    },
    {
      "epoch": 0.8194813829787234,
      "grad_norm": 146.8123613003801,
      "learning_rate": 1.8632409242974694e-07,
      "loss": 0.5037,
      "step": 4930,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45512010113780027,
      "success_rate.epoch.env.math": 0.9050387596899225,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7654666954084932,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5002969641868622,
      "success_rate.epoch.global": 0.705980528511822,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9928764559068219,
      "tokens_p.mean_in_band": 0.7292317708333333,
      "tokens_rate.above_band": 0.9524564183835182,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04754358161648178
    },
    {
      "epoch": 0.8203125,
      "grad_norm": 97.59546532651102,
      "learning_rate": 1.86298809913182e-07,
      "loss": 0.3214,
      "step": 4935,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.4552332912988651,
      "success_rate.epoch.env.math": 0.9051306873184899,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7654028436018957,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5003098065489562,
      "success_rate.epoch.global": 0.7059477487493052,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.7000000000000001,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.995628612716763,
      "tokens_p.mean_in_band": 0.6509650735294118,
      "tokens_rate.above_band": 0.9621802002224694,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03781979977753059
    },
    {
      "epoch": 0.8211436170212766,
      "grad_norm": 82.8880972909026,
      "learning_rate": 1.8627351621777263e-07,
      "loss": 0.4876,
      "step": 4940,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45591939546599497,
      "success_rate.epoch.env.math": 0.9052224371373307,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7655038759689923,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5003897053083259,
      "success_rate.epoch.global": 0.7061111111111111,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959016393442623,
      "tokens_p.mean_in_band": 0.6470170454545454,
      "tokens_rate.above_band": 0.9682539682539683,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.031746031746031744
    },
    {
      "epoch": 0.8219747340425532,
      "grad_norm": 103.36121219849849,
      "learning_rate": 1.862482113884089e-07,
      "loss": 0.3889,
      "step": 4945,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45591939546599497,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7654400688616312,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5003922294371572,
      "success_rate.epoch.global": 0.7061354802887285,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9903694968553459,
      "tokens_p.mean_below_band": 1.1641532182693481e-10,
      "tokens_p.mean_in_band": 0.7599113805970149,
      "tokens_rate.above_band": 0.9034090909090909,
      "tokens_rate.below_band": 0.0014204545454545455,
      "tokens_rate.in_band": 0.09517045454545454
    },
    {
      "epoch": 0.8228058510638298,
      "grad_norm": 78.78916167231668,
      "learning_rate": 1.8622289547000072e-07,
      "loss": 0.4149,
      "step": 4950,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45534591194968554,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7656417974629112,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5003584335357909,
      "success_rate.epoch.global": 0.706200582605077,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.0005203996669443,
      "tokens_p.mean_in_band": 0.6318359375,
      "tokens_rate.above_band": 0.9615692554043235,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03843074459567654
    },
    {
      "epoch": 0.8236369680851063,
      "grad_norm": 164.92010111231042,
      "learning_rate": 1.8619756850747761e-07,
      "loss": 0.5795,
      "step": 4955,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45603015075376885,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.765843179377014,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5004389445101715,
      "success_rate.epoch.global": 0.7064042140282784,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9924679487179487,
      "tokens_p.mean_in_band": 0.5889559659090909,
      "tokens_rate.above_band": 0.8986175115207373,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10138248847926268
    },
    {
      "epoch": 0.824468085106383,
      "grad_norm": 227.3258338514629,
      "learning_rate": 1.8617223054578872e-07,
      "loss": 0.4598,
      "step": 4960,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45603015075376885,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.76594374060554,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5004480864400375,
      "success_rate.epoch.global": 0.7064855875831486,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9930638647921028,
      "tokens_p.mean_in_band": 0.5413041893468118,
      "tokens_rate.above_band": 0.8386853988961365,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16131460110386353
    },
    {
      "epoch": 0.8252992021276596,
      "grad_norm": 118.00463653645956,
      "learning_rate": 1.8614688162990275e-07,
      "loss": 0.5387,
      "step": 4965,
      "success_rate.epoch.env.abd": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45671267252195735,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.7660442154968877,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5005192679545408,
      "success_rate.epoch.global": 0.7066075633744285,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9955357142857143,
      "tokens_p.mean_in_band": 0.626953125,
      "tokens_rate.above_band": 0.9752808988764045,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024719101123595506
    },
    {
      "epoch": 0.8261303191489362,
      "grad_norm": 223.9414092082225,
      "learning_rate": 1.861215218048078e-07,
      "loss": 0.5116,
      "step": 4970,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45671267252195735,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.766144604162197,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5016263300773862,
      "success_rate.epoch.global": 0.7067294378288562,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971168154761905,
      "tokens_p.mean_in_band": 0.5672743055555556,
      "tokens_rate.above_band": 0.9613733905579399,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03862660944206009
    },
    {
      "epoch": 0.8269614361702128,
      "grad_norm": 101.33458403531469,
      "learning_rate": 1.8609615111551138e-07,
      "loss": 0.3921,
      "step": 4975,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45807259073842305,
      "success_rate.epoch.env.math": 0.9053140096618357,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.766295025728988,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.501763633694046,
      "success_rate.epoch.global": 0.7069323370693233,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9973370927318296,
      "tokens_p.mean_in_band": 0.5277901785714286,
      "tokens_rate.above_band": 0.957983193277311,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04201680672268908
    },
    {
      "epoch": 0.8277925531914894,
      "grad_norm": 41.12422575372285,
      "learning_rate": 1.8607076960704017e-07,
      "loss": 0.4036,
      "step": 4980,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45807259073842305,
      "success_rate.epoch.env.math": 0.9054054054054054,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.7663951993141878,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5017161245623311,
      "success_rate.epoch.global": 0.706858407079646,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942354368932039,
      "tokens_p.mean_in_band": 0.5442073170731707,
      "tokens_rate.above_band": 0.9094922737306843,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09050772626931568
    },
    {
      "epoch": 0.828623670212766,
      "grad_norm": 89.70388854311008,
      "learning_rate": 1.8604537732444023e-07,
      "loss": 0.369,
      "step": 4985,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5028571428571429,
      "success_rate.epoch.env.logic": 0.45807259073842305,
      "success_rate.epoch.env.math": 0.905587668593449,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.7664452539104349,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5017372443609028,
      "success_rate.epoch.global": 0.7069799585348998,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963533225283631,
      "tokens_p.mean_in_band": 0.6153273809523809,
      "tokens_rate.above_band": 0.9670846394984326,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.032915360501567396
    },
    {
      "epoch": 0.8294547872340425,
      "grad_norm": 128.28428517730092,
      "learning_rate": 1.8601997431277656e-07,
      "loss": 0.489,
      "step": 4990,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45807259073842305,
      "success_rate.epoch.env.math": 0.9056785370548605,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.7662170841361593,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5019815510892494,
      "success_rate.epoch.global": 0.7069465543433228,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941099476439791,
      "tokens_p.mean_in_band": 0.608203125,
      "tokens_rate.above_band": 0.9744897959183674,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025510204081632654
    },
    {
      "epoch": 0.8302859042553191,
      "grad_norm": 115.69334908785314,
      "learning_rate": 1.8599456061713331e-07,
      "loss": 0.3986,
      "step": 4995,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45807259073842305,
      "success_rate.epoch.env.math": 0.9056785370548605,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.766367137355584,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5019951922910152,
      "success_rate.epoch.global": 0.707067918277195,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9933850364963503,
      "tokens_p.mean_in_band": 0.6473958333333333,
      "tokens_rate.above_band": 0.9480968858131488,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05190311418685121
    },
    {
      "epoch": 0.8311170212765957,
      "grad_norm": 421.5381623064106,
      "learning_rate": 1.8596913628261358e-07,
      "loss": 0.4485,
      "step": 5000,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45692883895131087,
      "success_rate.epoch.env.math": 0.9058597502401537,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.766303185802865,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5019018750042391,
      "success_rate.epoch.global": 0.7069369742104538,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9964048672566371,
      "tokens_p.mean_in_band": 0.634265988372093,
      "tokens_rate.above_band": 0.9484412470023981,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05155875299760192
    },
    {
      "epoch": 0.8319481382978723,
      "grad_norm": 96.13394926760594,
      "learning_rate": 1.8594370135433933e-07,
      "loss": 0.4203,
      "step": 5005,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45692883895131087,
      "success_rate.epoch.env.math": 0.9059500959692899,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.7665028839991455,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5019282426338224,
      "success_rate.epoch.global": 0.7071389195148843,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_in_band": 0.7435546875,
      "tokens_rate.above_band": 0.8701298701298701,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12987012987012986
    },
    {
      "epoch": 0.832779255319149,
      "grad_norm": 69.38275752445975,
      "learning_rate": 1.8591825587745129e-07,
      "loss": 0.3719,
      "step": 5010,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45692883895131087,
      "success_rate.epoch.env.math": 0.9059500959692899,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.7667520273154076,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5019508920262099,
      "success_rate.epoch.global": 0.7073405866960474,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949919871794872,
      "tokens_p.mean_in_band": 0.79638671875,
      "tokens_rate.above_band": 0.975,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025
    },
    {
      "epoch": 0.8336103723404256,
      "grad_norm": 94.78114760423331,
      "learning_rate": 1.8589279989710897e-07,
      "loss": 0.4333,
      "step": 5015,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45692883895131087,
      "success_rate.epoch.env.math": 0.9060402684563759,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.7670006395224899,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5019816906347706,
      "success_rate.epoch.global": 0.7075822209990368,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9900568181818182,
      "tokens_p.mean_in_band": 0.54130859375,
      "tokens_rate.above_band": 0.8979591836734694,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10204081632653061
    },
    {
      "epoch": 0.8344414893617021,
      "grad_norm": 44.62805235217876,
      "learning_rate": 1.8586733345849054e-07,
      "loss": 0.3602,
      "step": 5020,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45692883895131087,
      "success_rate.epoch.env.math": 0.9060402684563759,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7672982754949969,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.50197660444531,
      "success_rate.epoch.global": 0.7077261479241133,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9946581196581197,
      "tokens_p.mean_in_band": 0.7126302083333333,
      "tokens_rate.above_band": 0.8863636363636364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11363636363636363
    },
    {
      "epoch": 0.8352726063829787,
      "grad_norm": 70.84938653094493,
      "learning_rate": 1.858418566067926e-07,
      "loss": 0.4653,
      "step": 5025,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45760598503740646,
      "success_rate.epoch.env.math": 0.9061302681992337,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7675951520306188,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5020733337511805,
      "success_rate.epoch.global": 0.7080472397692942,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9938568376068376,
      "tokens_p.mean_in_band": 0.551513671875,
      "tokens_rate.above_band": 0.936,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.064
    },
    {
      "epoch": 0.8361037234042553,
      "grad_norm": 66.59565573097711,
      "learning_rate": 1.8581636938723042e-07,
      "loss": 0.3828,
      "step": 5030,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.45828144458281445,
      "success_rate.epoch.env.math": 0.9061302681992337,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7677433064173396,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5021482077450105,
      "success_rate.epoch.global": 0.7082075212736756,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9945600381194409,
      "tokens_p.mean_in_band": 0.6614583333333334,
      "tokens_rate.above_band": 0.9493365500603136,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05066344993968637
    },
    {
      "epoch": 0.8369348404255319,
      "grad_norm": 92.17755944276485,
      "learning_rate": 1.8579087184503753e-07,
      "loss": 0.2834,
      "step": 5035,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5056818181818182,
      "success_rate.epoch.env.logic": 0.458955223880597,
      "success_rate.epoch.env.math": 0.9063097514340345,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7677433064173396,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5022257770661542,
      "success_rate.epoch.global": 0.7083276169570586,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973148994515539,
      "tokens_p.mean_in_band": 0.7312677556818182,
      "tokens_rate.above_band": 0.961335676625659,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03866432337434095
    },
    {
      "epoch": 0.8377659574468085,
      "grad_norm": 63.12521647716537,
      "learning_rate": 1.8576536402546577e-07,
      "loss": 0.3666,
      "step": 5040,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.458955223880597,
      "success_rate.epoch.env.math": 0.9063097514340345,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7677282377919321,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5024782942901508,
      "success_rate.epoch.global": 0.7083904579106115,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9900045955882353,
      "tokens_p.mean_in_band": 0.8170955882352942,
      "tokens_rate.above_band": 0.9411764705882353,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.058823529411764705
    },
    {
      "epoch": 0.8385970744680851,
      "grad_norm": 132.14260333855555,
      "learning_rate": 1.8573984597378533e-07,
      "loss": 0.5016,
      "step": 5045,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.458955223880597,
      "success_rate.epoch.env.math": 0.9063097514340345,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.7680237489397794,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5025051589399551,
      "success_rate.epoch.global": 0.7086301369863014,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.991234756097561,
      "tokens_p.mean_below_band": 6.927791673660977e-13,
      "tokens_p.mean_in_band": 0.5634014423076923,
      "tokens_rate.above_band": 0.9213483146067416,
      "tokens_rate.below_band": 0.0056179775280898875,
      "tokens_rate.in_band": 0.07303370786516854
    },
    {
      "epoch": 0.8394281914893617,
      "grad_norm": 132.24654694480157,
      "learning_rate": 1.857143177352845e-07,
      "loss": 0.4856,
      "step": 5050,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.45962732919254656,
      "success_rate.epoch.env.math": 0.9063097514340345,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7683185091063108,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5025611212036917,
      "success_rate.epoch.global": 0.7088122605363985,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9965122767857143,
      "tokens_p.mean_in_band": 0.737890625,
      "tokens_rate.above_band": 0.9180327868852459,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08196721311475409
    },
    {
      "epoch": 0.8402593085106383,
      "grad_norm": 82.75381195497917,
      "learning_rate": 1.8568877935526963e-07,
      "loss": 0.4736,
      "step": 5055,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.45962732919254656,
      "success_rate.epoch.env.math": 0.9063097514340345,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7685635709752485,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5025833995554133,
      "success_rate.epoch.global": 0.7090113496513059,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9811126373626373,
      "tokens_p.mean_in_band": 0.6964285714285714,
      "tokens_rate.above_band": 0.8666666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13333333333333333
    },
    {
      "epoch": 0.8410904255319149,
      "grad_norm": 110.18599328143114,
      "learning_rate": 1.8566323087906509e-07,
      "loss": 0.3668,
      "step": 5060,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4556213017751479,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.45962732919254656,
      "success_rate.epoch.env.math": 0.9063992359121299,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7682875264270613,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5028610167666954,
      "success_rate.epoch.global": 0.7089368679967204,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9963842975206612,
      "tokens_p.mean_below_band": 5.893525667488575e-10,
      "tokens_p.mean_in_band": 0.6242327008928571,
      "tokens_rate.above_band": 0.9615894039735099,
      "tokens_rate.below_band": 0.0013245033112582781,
      "tokens_rate.in_band": 0.03708609271523179
    },
    {
      "epoch": 0.8419215425531915,
      "grad_norm": 81.69390817781417,
      "learning_rate": 1.8563767235201317e-07,
      "loss": 0.4711,
      "step": 5065,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4556213017751479,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.45905707196029777,
      "success_rate.epoch.env.math": 0.9064885496183206,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7684343967885062,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5028306464790033,
      "success_rate.epoch.global": 0.7089990441076062,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9980127186009539,
      "tokens_p.mean_in_band": 0.5041852678571429,
      "tokens_rate.above_band": 0.9573820395738204,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0426179604261796
    },
    {
      "epoch": 0.8427526595744681,
      "grad_norm": 102.2999888297453,
      "learning_rate": 1.8561210381947397e-07,
      "loss": 0.527,
      "step": 5070,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4556213017751479,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.4591584158415842,
      "success_rate.epoch.env.math": 0.9064885496183206,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.768581081081081,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5028531944948088,
      "success_rate.epoch.global": 0.709061135371179,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4523809523809524,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9962698938992043,
      "tokens_p.mean_in_band": 0.6032072368421053,
      "tokens_rate.above_band": 0.952020202020202,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047979797979797977
    },
    {
      "epoch": 0.8435837765957447,
      "grad_norm": 134.25351070844295,
      "learning_rate": 1.8558652532682544e-07,
      "loss": 0.4385,
      "step": 5075,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.4591584158415842,
      "success_rate.epoch.env.math": 0.9065776930409915,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.768629934557737,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5031568512708039,
      "success_rate.epoch.global": 0.7091801936979948,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.999122920997921,
      "tokens_p.mean_in_band": 0.5834517045454546,
      "tokens_rate.above_band": 0.9776422764227642,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022357723577235773
    },
    {
      "epoch": 0.8444148936170213,
      "grad_norm": 102.71658622404625,
      "learning_rate": 1.8556093691946306e-07,
      "loss": 0.3784,
      "step": 5080,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5084745762711864,
      "success_rate.epoch.env.logic": 0.4591584158415842,
      "success_rate.epoch.env.math": 0.9065776930409915,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7687763713080169,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5031701637026474,
      "success_rate.epoch.global": 0.7092991546223071,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9897103658536586,
      "tokens_p.mean_below_band": 8.149072527885437e-09,
      "tokens_p.mean_in_band": 0.793212890625,
      "tokens_rate.above_band": 0.9060773480662984,
      "tokens_rate.below_band": 0.0055248618784530384,
      "tokens_rate.in_band": 0.08839779005524862
    },
    {
      "epoch": 0.8452460106382979,
      "grad_norm": 150.3481594804001,
      "learning_rate": 1.8553533864280002e-07,
      "loss": 0.4964,
      "step": 5085,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.45982694684796044,
      "success_rate.epoch.env.math": 0.9065776930409915,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7687117857895847,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5034761022729145,
      "success_rate.epoch.global": 0.7093609483580869,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9939478584729982,
      "tokens_p.mean_below_band": 2.9976945370435715e-09,
      "tokens_p.mean_in_band": 0.7272518382352942,
      "tokens_rate.above_band": 0.9675675675675676,
      "tokens_rate.below_band": 0.0018018018018018018,
      "tokens_rate.in_band": 0.03063063063063063
    },
    {
      "epoch": 0.8460771276595744,
      "grad_norm": 120.21214009748208,
      "learning_rate": 1.8550973054226697e-07,
      "loss": 0.3844,
      "step": 5090,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4599260172626387,
      "success_rate.epoch.env.math": 0.9065776930409915,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7688579856721449,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5034983995726635,
      "success_rate.epoch.global": 0.7094226579520697,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9953583645994262,
      "tokens_p.mean_in_band": 0.5595965038314177,
      "tokens_rate.above_band": 0.896695032653869,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10330496734613101
    },
    {
      "epoch": 0.846908244680851,
      "grad_norm": 58.516514937432355,
      "learning_rate": 1.8548411266331206e-07,
      "loss": 0.46,
      "step": 5095,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.45935960591133007,
      "success_rate.epoch.env.math": 0.9066666666666666,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.768955349620893,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5034638474111284,
      "success_rate.epoch.global": 0.7094447468698966,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9934966216216217,
      "tokens_p.mean_in_band": 0.5916108630952381,
      "tokens_rate.above_band": 0.9462915601023018,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05370843989769821
    },
    {
      "epoch": 0.8477393617021277,
      "grad_norm": 72.39119441768321,
      "learning_rate": 1.854584850514007e-07,
      "loss": 0.5245,
      "step": 5100,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.46002460024600245,
      "success_rate.epoch.env.math": 0.9066666666666666,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7690526315789473,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5035331452559219,
      "success_rate.epoch.global": 0.7095633247177254,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983231707317073,
      "tokens_p.mean_in_band": 0.5803865131578947,
      "tokens_rate.above_band": 0.9700315457413249,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02996845425867508
    },
    {
      "epoch": 0.8485704787234043,
      "grad_norm": 64.96241202138164,
      "learning_rate": 1.8543284775201564e-07,
      "loss": 0.5563,
      "step": 5105,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.4588235294117647,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.46002460024600245,
      "success_rate.epoch.env.math": 0.9067554709800191,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7692469499368952,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5035588836805854,
      "success_rate.epoch.global": 0.7097607395323545,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9969512195121951,
      "tokens_p.mean_in_band": 0.5854779411764706,
      "tokens_rate.above_band": 0.9786432160804021,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02135678391959799
    },
    {
      "epoch": 0.8494015957446809,
      "grad_norm": 113.45650888270792,
      "learning_rate": 1.8540720081065682e-07,
      "loss": 0.5288,
      "step": 5110,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4594594594594595,
      "success_rate.epoch.env.math": 0.9068441064638784,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7693439865433137,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5030393722246758,
      "success_rate.epoch.global": 0.7095897853844064,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982290436835891,
      "tokens_p.mean_in_band": 0.6148302801724138,
      "tokens_rate.above_band": 0.9668949771689498,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033105022831050226
    },
    {
      "epoch": 0.8502327127659575,
      "grad_norm": 81.0519607409086,
      "learning_rate": 1.8538154427284125e-07,
      "loss": 0.4576,
      "step": 5115,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4594594594594595,
      "success_rate.epoch.env.math": 0.9068441064638784,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.7694893885270014,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.503052590586829,
      "success_rate.epoch.global": 0.7097080787508486,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998593009478673,
      "tokens_p.mean_in_band": 0.5876116071428571,
      "tokens_rate.above_band": 0.9678899082568807,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03211009174311927
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 86.13391690307799,
      "learning_rate": 1.8535587818410302e-07,
      "loss": 0.4625,
      "step": 5120,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4588957055214724,
      "success_rate.epoch.env.math": 0.9069325735992403,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.7697313182199832,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.50299964907371,
      "success_rate.epoch.global": 0.709751797097518,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981720055710307,
      "tokens_p.mean_in_band": 0.6243106617647058,
      "tokens_rate.above_band": 0.9547872340425532,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04521276595744681
    },
    {
      "epoch": 0.8518949468085106,
      "grad_norm": 68.38127916349538,
      "learning_rate": 1.8533020258999317e-07,
      "loss": 0.5685,
      "step": 5125,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4588957055214724,
      "success_rate.epoch.env.math": 0.9069325735992403,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7697147651006712,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5029666223684995,
      "success_rate.epoch.global": 0.7096774193548387,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9974180911680912,
      "tokens_p.mean_below_band": 5.2386898864026366e-09,
      "tokens_p.mean_in_band": 0.5706129807692307,
      "tokens_rate.above_band": 0.9448183041722745,
      "tokens_rate.below_band": 0.0026917900403768506,
      "tokens_rate.in_band": 0.052489905787348586
    },
    {
      "epoch": 0.8527260638297872,
      "grad_norm": 129.56825701233763,
      "learning_rate": 1.8530451753607953e-07,
      "loss": 0.5243,
      "step": 5130,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.45955882352941174,
      "success_rate.epoch.env.math": 0.9070208728652751,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7696499685600503,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5030290424351681,
      "success_rate.epoch.global": 0.7097385886496005,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.65,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0005116959064329,
      "tokens_p.mean_below_band": 2.342858351767063e-09,
      "tokens_p.mean_in_band": 0.5967548076923077,
      "tokens_rate.above_band": 0.9416299559471366,
      "tokens_rate.below_band": 0.0011013215859030838,
      "tokens_rate.in_band": 0.05726872246696035
    },
    {
      "epoch": 0.8535571808510638,
      "grad_norm": 39.98947624230619,
      "learning_rate": 1.8527882306794683e-07,
      "loss": 0.3879,
      "step": 5135,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4589963280293758,
      "success_rate.epoch.env.math": 0.9072847682119205,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7697464906767232,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5030106717045574,
      "success_rate.epoch.global": 0.7098782138024358,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9973868843069874,
      "tokens_p.mean_in_band": 0.5791015625,
      "tokens_rate.above_band": 0.9646408839779006,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03535911602209945
    },
    {
      "epoch": 0.8543882978723404,
      "grad_norm": 51.62159186025119,
      "learning_rate": 1.8525311923119643e-07,
      "loss": 0.5168,
      "step": 5140,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4589963280293758,
      "success_rate.epoch.env.math": 0.9073724007561437,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7698429319371728,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5030274056868002,
      "success_rate.epoch.global": 0.7099959421073989,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942748091603053,
      "tokens_p.mean_in_band": 0.6163194444444444,
      "tokens_rate.above_band": 0.966789667896679,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033210332103321034
    },
    {
      "epoch": 0.855219414893617,
      "grad_norm": 42.92293315231294,
      "learning_rate": 1.8522740607144637e-07,
      "loss": 0.2993,
      "step": 5145,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.45965770171149145,
      "success_rate.epoch.env.math": 0.9074598677998111,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7700355722954593,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.503112994876261,
      "success_rate.epoch.global": 0.7102311123124747,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9954166666666666,
      "tokens_p.mean_in_band": 0.6368117559523809,
      "tokens_rate.above_band": 0.946969696969697,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05303030303030303
    },
    {
      "epoch": 0.8560505319148937,
      "grad_norm": 111.22718262520938,
      "learning_rate": 1.8520168363433115e-07,
      "loss": 0.5233,
      "step": 5150,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4603174603174603,
      "success_rate.epoch.env.math": 0.9074598677998111,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.7701798410706817,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5031860882745514,
      "success_rate.epoch.global": 0.7103876806699987,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9918067655867139,
      "tokens_p.mean_below_band": 5.885958671569824e-07,
      "tokens_p.mean_in_band": 0.529109733468286,
      "tokens_rate.above_band": 0.8317481884057971,
      "tokens_rate.below_band": 0.0004528985507246377,
      "tokens_rate.in_band": 0.16779891304347827
    },
    {
      "epoch": 0.8568816489361702,
      "grad_norm": 77.42124874726176,
      "learning_rate": 1.8517595196550186e-07,
      "loss": 0.3371,
      "step": 5155,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4609756097560976,
      "success_rate.epoch.env.math": 0.9075471698113208,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.7703719180944422,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5032399996265767,
      "success_rate.epoch.global": 0.7105263157894737,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937796208530806,
      "tokens_p.mean_in_band": 0.6525493421052632,
      "tokens_rate.above_band": 0.9173913043478261,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08260869565217391
    },
    {
      "epoch": 0.8577127659574468,
      "grad_norm": 75.49665057538526,
      "learning_rate": 1.8515021111062588e-07,
      "loss": 0.5233,
      "step": 5160,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.4609756097560976,
      "success_rate.epoch.env.math": 0.9077212806026366,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.7703719180944422,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5032558278803326,
      "success_rate.epoch.global": 0.710604425256341,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9991899727148704,
      "tokens_p.mean_below_band": 1.7848833522293717e-11,
      "tokens_p.mean_in_band": 0.5237723214285714,
      "tokens_rate.above_band": 0.953185955786736,
      "tokens_rate.below_band": 0.0013003901170351106,
      "tokens_rate.in_band": 0.045513654096228866
    },
    {
      "epoch": 0.8585438829787234,
      "grad_norm": 100.5683597417154,
      "learning_rate": 1.8512446111538692e-07,
      "loss": 0.4473,
      "step": 5165,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3333333333333333,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5112359550561798,
      "success_rate.epoch.env.logic": 0.46163215590742995,
      "success_rate.epoch.env.math": 0.9078947368421053,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.7705157652954688,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5033443596614079,
      "success_rate.epoch.global": 0.7108385009436505,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9922945205479452,
      "tokens_p.mean_in_band": 0.5183012937317785,
      "tokens_rate.above_band": 0.8469433288710397,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1530566711289603
    },
    {
      "epoch": 0.859375,
      "grad_norm": 59.43381072575893,
      "learning_rate": 1.8509870202548493e-07,
      "loss": 0.5055,
      "step": 5170,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5083798882681564,
      "success_rate.epoch.env.logic": 0.46163215590742995,
      "success_rate.epoch.env.math": 0.907981220657277,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.7706594323873122,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5062954326993385,
      "success_rate.epoch.global": 0.7109375,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.992715307364577,
      "tokens_p.mean_below_band": 2.426760537283761e-07,
      "tokens_p.mean_in_band": 0.43470652829935624,
      "tokens_rate.above_band": 0.7777514792899408,
      "tokens_rate.below_band": 0.0016568047337278107,
      "tokens_rate.in_band": 0.22059171597633137
    },
    {
      "epoch": 0.8602061170212766,
      "grad_norm": 110.38208457277385,
      "learning_rate": 1.8507293388663595e-07,
      "loss": 0.418,
      "step": 5175,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5055555555555555,
      "success_rate.epoch.env.logic": 0.46228710462287104,
      "success_rate.epoch.env.math": 0.9080675422138836,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7707072814521176,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5060792961975085,
      "success_rate.epoch.global": 0.7108628348364517,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9945952316810345,
      "tokens_p.mean_below_band": 1.862645149230957e-07,
      "tokens_p.mean_in_band": 0.528577302631579,
      "tokens_rate.above_band": 0.9066927210552027,
      "tokens_rate.below_band": 0.0004885197850512946,
      "tokens_rate.in_band": 0.09281875915974597
    },
    {
      "epoch": 0.8610372340425532,
      "grad_norm": 401.48654276649995,
      "learning_rate": 1.8504715674457215e-07,
      "loss": 0.4859,
      "step": 5180,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5055555555555555,
      "success_rate.epoch.env.logic": 0.4629404617253949,
      "success_rate.epoch.env.math": 0.9081537019681349,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7708507089241035,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5061595638637594,
      "success_rate.epoch.global": 0.7110573042776432,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9908588435374149,
      "tokens_p.mean_in_band": 0.75640625,
      "tokens_rate.above_band": 0.9216300940438872,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07836990595611286
    },
    {
      "epoch": 0.8618683510638298,
      "grad_norm": 69.59480462354695,
      "learning_rate": 1.850213706450416e-07,
      "loss": 0.5222,
      "step": 5185,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5055555555555555,
      "success_rate.epoch.env.logic": 0.4629404617253949,
      "success_rate.epoch.env.math": 0.9082397003745318,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7707378074197583,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5061571181275822,
      "success_rate.epoch.global": 0.7110393976065618,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9992788461538461,
      "tokens_p.mean_in_band": 0.5450846354166666,
      "tokens_rate.above_band": 0.9605911330049262,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03940886699507389
    },
    {
      "epoch": 0.8626994680851063,
      "grad_norm": 83.24604199451593,
      "learning_rate": 1.8499557563380836e-07,
      "loss": 0.3598,
      "step": 5190,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5055555555555555,
      "success_rate.epoch.env.logic": 0.4629404617253949,
      "success_rate.epoch.env.math": 0.9082397003745318,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7708810664444907,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5061701416752853,
      "success_rate.epoch.global": 0.7111559139784946,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964779896759393,
      "tokens_p.mean_below_band": 1.6977234433094661e-09,
      "tokens_p.mean_in_band": 0.754404920212766,
      "tokens_rate.above_band": 0.9858637263217416,
      "tokens_rate.below_band": 0.0008481764206955047,
      "tokens_rate.in_band": 0.013288097257562907
    },
    {
      "epoch": 0.863530585106383,
      "grad_norm": 66.86258879119843,
      "learning_rate": 1.8496977175665221e-07,
      "loss": 0.4882,
      "step": 5195,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5055555555555555,
      "success_rate.epoch.env.logic": 0.46237864077669905,
      "success_rate.epoch.env.math": 0.9083255378858747,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7711670480549199,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5061528687819286,
      "success_rate.epoch.global": 0.7113319011815252,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966517857142857,
      "tokens_p.mean_in_band": 0.6098845108695652,
      "tokens_rate.above_band": 0.9655172413793104,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034482758620689655
    },
    {
      "epoch": 0.8643617021276596,
      "grad_norm": 461.39987416908787,
      "learning_rate": 1.8494395905936875e-07,
      "loss": 0.4995,
      "step": 5200,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.46237864077669905,
      "success_rate.epoch.env.math": 0.9085820895522388,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7711018711018711,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5064186062342412,
      "success_rate.epoch.global": 0.7114688128772636,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.9333333333333332,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930555555555556,
      "tokens_p.mean_in_band": 0.6958705357142857,
      "tokens_rate.above_band": 0.954983922829582,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04501607717041801
    },
    {
      "epoch": 0.8651928191489362,
      "grad_norm": 62.920761833154074,
      "learning_rate": 1.8491813758776917e-07,
      "loss": 0.4371,
      "step": 5205,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463030303030303,
      "success_rate.epoch.env.math": 0.9086672879776329,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7711318795430945,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5064883216088067,
      "success_rate.epoch.global": 0.7116054677030287,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9938340807174888,
      "tokens_p.mean_in_band": 0.6256696428571429,
      "tokens_rate.above_band": 0.8643410852713178,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13565891472868216
    },
    {
      "epoch": 0.8660239361702128,
      "grad_norm": 112.23362344477916,
      "learning_rate": 1.8489230738768027e-07,
      "loss": 0.363,
      "step": 5210,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45348837209302323,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9087523277467412,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7712269047124767,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5065637897285694,
      "success_rate.epoch.global": 0.7117599785695151,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99481658692185,
      "tokens_p.mean_in_band": 0.5685177364864865,
      "tokens_rate.above_band": 0.9713400464756003,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02865995352439969
    },
    {
      "epoch": 0.8668550531914894,
      "grad_norm": 120.54854830860351,
      "learning_rate": 1.848664685049443e-07,
      "loss": 0.3702,
      "step": 5215,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45664739884393063,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9088372093023256,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7714641227706346,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5068802557617194,
      "success_rate.epoch.global": 0.7120299745751372,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99906600249066,
      "tokens_p.mean_in_band": 0.5454427083333333,
      "tokens_rate.above_band": 0.963985594237695,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03601440576230492
    },
    {
      "epoch": 0.867686170212766,
      "grad_norm": 93.79875126033119,
      "learning_rate": 1.8484062098541897e-07,
      "loss": 0.3146,
      "step": 5220,
      "success_rate.epoch.env.abd": 0.45652173913043476,
      "success_rate.epoch.env.agentgym:alfworld": 0.45664739884393063,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9089219330855018,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7717008493888544,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5069094785254826,
      "success_rate.epoch.global": 0.7122609974595534,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9837682038834952,
      "tokens_p.mean_in_band": 0.8057291666666667,
      "tokens_rate.above_band": 0.8728813559322034,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1271186440677966
    },
    {
      "epoch": 0.8685172872340425,
      "grad_norm": 96.17477032570376,
      "learning_rate": 1.848147648749773e-07,
      "loss": 0.4337,
      "step": 5225,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.45664739884393063,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9089219330855018,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7718898778720762,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5060436421610358,
      "success_rate.epoch.global": 0.7123196151790486,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9954633204633204,
      "tokens_p.mean_in_band": 0.10686657475490197,
      "tokens_rate.above_band": 0.28405352050888355,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.7159464794911164
    },
    {
      "epoch": 0.8693484042553191,
      "grad_norm": 150.19682517668573,
      "learning_rate": 1.8478890021950754e-07,
      "loss": 0.4695,
      "step": 5230,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.45664739884393063,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9089219330855018,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7720785935884178,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5060607981352487,
      "success_rate.epoch.global": 0.7124732905982906,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9823863636363637,
      "tokens_p.mean_in_band": 0.7083333333333334,
      "tokens_rate.above_band": 0.9016393442622951,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09836065573770492
    },
    {
      "epoch": 0.8701795212765957,
      "grad_norm": 174.023746545335,
      "learning_rate": 1.847630270649131e-07,
      "loss": 0.5299,
      "step": 5235,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.45664739884393063,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9091751621872104,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7721728344014885,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5060923863093195,
      "success_rate.epoch.global": 0.7126651541438677,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.8571428571428572,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9858156028368794,
      "tokens_p.mean_below_band": 9.049472282640636e-11,
      "tokens_p.mean_in_band": 0.7245279947916666,
      "tokens_rate.above_band": 0.8493975903614458,
      "tokens_rate.below_band": 0.006024096385542169,
      "tokens_rate.in_band": 0.14457831325301204
    },
    {
      "epoch": 0.8710106382978723,
      "grad_norm": 145.87926676819896,
      "learning_rate": 1.847371454571125e-07,
      "loss": 0.5801,
      "step": 5240,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.45664739884393063,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5082872928176796,
      "success_rate.epoch.env.logic": 0.463680387409201,
      "success_rate.epoch.env.math": 0.9092592592592592,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7719479446395373,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5060795869738738,
      "success_rate.epoch.global": 0.7125900240064017,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9879658385093167,
      "tokens_p.mean_in_band": 0.65234375,
      "tokens_rate.above_band": 0.9044943820224719,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09550561797752809
    },
    {
      "epoch": 0.871841755319149,
      "grad_norm": 95.14551052244866,
      "learning_rate": 1.847112554420393e-07,
      "loss": 0.4015,
      "step": 5245,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.45977011494252873,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.463768115942029,
      "success_rate.epoch.env.math": 0.9092592592592592,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7720891824938068,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5066298961245127,
      "success_rate.epoch.global": 0.7127248500999334,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998802570093458,
      "tokens_p.mean_in_band": 0.5251885775862069,
      "tokens_rate.above_band": 0.9736123748862603,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026387625113739762
    },
    {
      "epoch": 0.8726728723404256,
      "grad_norm": 96.40747778330923,
      "learning_rate": 1.8468535706564186e-07,
      "loss": 0.4411,
      "step": 5250,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.46285714285714286,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.463855421686747,
      "success_rate.epoch.env.math": 0.9093432007400555,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.7721362229102167,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5069303793569252,
      "success_rate.epoch.global": 0.7127829560585885,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9964145106861643,
      "tokens_p.mean_in_band": 0.546875,
      "tokens_rate.above_band": 0.961081081081081,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03891891891891892
    },
    {
      "epoch": 0.8735039893617021,
      "grad_norm": 145.66526206987086,
      "learning_rate": 1.846594503738835e-07,
      "loss": 0.335,
      "step": 5255,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.46285714285714286,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.463855421686747,
      "success_rate.epoch.env.math": 0.9093432007400555,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7722772277227723,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5069122803408292,
      "success_rate.epoch.global": 0.71280276816609,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937796208530806,
      "tokens_p.mean_in_band": 0.6166666666666667,
      "tokens_rate.above_band": 0.9336283185840708,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06637168141592921
    },
    {
      "epoch": 0.8743351063829787,
      "grad_norm": 99.61723336966499,
      "learning_rate": 1.8463353541274226e-07,
      "loss": 0.4987,
      "step": 5260,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.46285714285714286,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.463855421686747,
      "success_rate.epoch.env.math": 0.9094269870609981,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7724649629018961,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5069369641135626,
      "success_rate.epoch.global": 0.7129937491687725,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947277607361963,
      "tokens_p.mean_in_band": 0.5895724826388888,
      "tokens_rate.above_band": 0.9476744186046512,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05232558139534884
    },
    {
      "epoch": 0.8751662234042553,
      "grad_norm": 77.30451222916581,
      "learning_rate": 1.846076122282108e-07,
      "loss": 0.4781,
      "step": 5265,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.463855421686747,
      "success_rate.epoch.env.math": 0.9095940959409594,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7725587144622992,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072381285219546,
      "success_rate.epoch.global": 0.713184476342371,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9925814075630253,
      "tokens_p.mean_in_band": 0.7912946428571429,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05555555555555555
    },
    {
      "epoch": 0.8759973404255319,
      "grad_norm": 95.91580395374355,
      "learning_rate": 1.8458168086629647e-07,
      "loss": 0.3916,
      "step": 5270,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.463855421686747,
      "success_rate.epoch.env.math": 0.9095940959409594,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7727459860024701,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072551532074246,
      "success_rate.epoch.global": 0.713336875664187,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99375,
      "tokens_p.mean_in_band": 0.5911931818181818,
      "tokens_rate.above_band": 0.9508928571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049107142857142856
    },
    {
      "epoch": 0.8768284574468085,
      "grad_norm": 98.98842252879716,
      "learning_rate": 1.8455574137302107e-07,
      "loss": 0.4192,
      "step": 5275,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46329723225030084,
      "success_rate.epoch.env.math": 0.9097605893186004,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7728395061728395,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.507228046308476,
      "success_rate.epoch.global": 0.7133943979822116,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9981737012987013,
      "tokens_p.mean_in_band": 0.6482638888888889,
      "tokens_rate.above_band": 0.9319213313161876,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0680786686838124
    },
    {
      "epoch": 0.8776595744680851,
      "grad_norm": 146.98766796897505,
      "learning_rate": 1.845297937944208e-07,
      "loss": 0.5282,
      "step": 5280,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46274038461538464,
      "success_rate.epoch.env.math": 0.9098436062557498,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7729329494035376,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5071934656296515,
      "success_rate.epoch.global": 0.7134138251293618,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.996259842519685,
      "tokens_p.mean_in_band": 0.4921875,
      "tokens_rate.above_band": 0.9491778774289985,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05082212257100149
    },
    {
      "epoch": 0.8784906914893617,
      "grad_norm": 68.15240195818971,
      "learning_rate": 1.845038381765463e-07,
      "loss": 0.5068,
      "step": 5285,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46274038461538464,
      "success_rate.epoch.env.math": 0.9098436062557498,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.7731662214916787,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072146721831189,
      "success_rate.epoch.global": 0.7136038186157518,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9921482412060302,
      "tokens_p.mean_in_band": 0.6516927083333334,
      "tokens_rate.above_band": 0.8805309734513275,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11946902654867257
    },
    {
      "epoch": 0.8793218085106383,
      "grad_norm": 72.33138589840588,
      "learning_rate": 1.8447787456546248e-07,
      "loss": 0.3813,
      "step": 5290,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.4628297362110312,
      "success_rate.epoch.env.math": 0.9099264705882353,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7732593961799138,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072080785241453,
      "success_rate.epoch.global": 0.7135665076841547,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9920176630434783,
      "tokens_p.mean_below_band": 1.8189894035458565e-09,
      "tokens_p.mean_in_band": 0.6848958333333334,
      "tokens_rate.above_band": 0.9363867684478372,
      "tokens_rate.below_band": 0.002544529262086514,
      "tokens_rate.in_band": 0.061068702290076333
    },
    {
      "epoch": 0.8801529255319149,
      "grad_norm": 153.70816550968183,
      "learning_rate": 1.8445190300724828e-07,
      "loss": 0.6103,
      "step": 5295,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46347305389221555,
      "success_rate.epoch.env.math": 0.9100917431192661,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7733990147783252,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072942793251113,
      "success_rate.epoch.global": 0.7137940164151443,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9928909952606635,
      "tokens_p.mean_in_band": 0.83984375,
      "tokens_rate.above_band": 0.985981308411215,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014018691588785047
    },
    {
      "epoch": 0.8809840425531915,
      "grad_norm": 179.64357932032007,
      "learning_rate": 1.8442592354799694e-07,
      "loss": 0.5463,
      "step": 5300,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46347305389221555,
      "success_rate.epoch.env.math": 0.9100917431192661,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7733990147783252,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072942793251113,
      "success_rate.epoch.global": 0.7137940164151443,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.998100630733945,
      "tokens_p.mean_in_band": 0.556796875,
      "tokens_rate.above_band": 0.9721293199554069,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027870680044593088
    },
    {
      "epoch": 0.8818151595744681,
      "grad_norm": 330.46042255671426,
      "learning_rate": 1.8439993623381557e-07,
      "loss": 0.3594,
      "step": 5305,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46347305389221555,
      "success_rate.epoch.env.math": 0.9103385178408051,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7732868280672959,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5073065145987941,
      "success_rate.epoch.global": 0.7138510384971557,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9927130044843049,
      "tokens_p.mean_below_band": 1.1641532182693481e-10,
      "tokens_p.mean_in_band": 0.8079427083333334,
      "tokens_rate.above_band": 0.9591397849462365,
      "tokens_rate.below_band": 0.002150537634408602,
      "tokens_rate.in_band": 0.03870967741935484
    },
    {
      "epoch": 0.8826462765957447,
      "grad_norm": 103.69438618589606,
      "learning_rate": 1.8437394111082537e-07,
      "loss": 0.4821,
      "step": 5310,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46347305389221555,
      "success_rate.epoch.env.math": 0.9104204753199269,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7733798195242002,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5073224190475236,
      "success_rate.epoch.global": 0.7139645596403068,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9989837398373984,
      "tokens_p.mean_in_band": 0.6741477272727273,
      "tokens_rate.above_band": 0.9306431273644389,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06935687263556116
    },
    {
      "epoch": 0.8834773936170213,
      "grad_norm": 120.24352776037023,
      "learning_rate": 1.8434793822516123e-07,
      "loss": 0.4081,
      "step": 5315,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.46411483253588515,
      "success_rate.epoch.env.math": 0.9104204753199269,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7734727347273472,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5073892093972342,
      "success_rate.epoch.global": 0.7140779907468605,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9958105335157319,
      "tokens_p.mean_in_band": 0.5834375,
      "tokens_rate.above_band": 0.966931216931217,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03306878306878307
    },
    {
      "epoch": 0.8843085106382979,
      "grad_norm": 88.61726468216064,
      "learning_rate": 1.8432192762297193e-07,
      "loss": 0.4345,
      "step": 5320,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.4647550776583035,
      "success_rate.epoch.env.math": 0.9104204753199269,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7734070887113297,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5074414456796343,
      "success_rate.epoch.global": 0.7140969745012551,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9933274021352313,
      "tokens_p.mean_in_band": 0.7868923611111112,
      "tokens_rate.above_band": 0.9689655172413794,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03103448275862069
    },
    {
      "epoch": 0.8851396276595744,
      "grad_norm": 229.29870823855558,
      "learning_rate": 1.8429590935041995e-07,
      "loss": 0.5412,
      "step": 5325,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.464839094159714,
      "success_rate.epoch.env.math": 0.9104204753199269,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.77329510546795,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5074389032485462,
      "success_rate.epoch.global": 0.7139838901360095,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.4047619047619048,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.994473102431835,
      "tokens_p.mean_in_band": 0.5250673491379311,
      "tokens_rate.above_band": 0.903462050599201,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09653794940079893
    },
    {
      "epoch": 0.885970744680851,
      "grad_norm": 254.57616947749648,
      "learning_rate": 1.8426988345368132e-07,
      "loss": 0.4033,
      "step": 5330,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.464839094159714,
      "success_rate.epoch.env.math": 0.9104204753199269,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7735270049099836,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5074599850160039,
      "success_rate.epoch.global": 0.714172604908947,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957757296466974,
      "tokens_p.mean_in_band": 0.660888671875,
      "tokens_rate.above_band": 0.9760119940029985,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0239880059970015
    },
    {
      "epoch": 0.8868018617021277,
      "grad_norm": 408.7961185472496,
      "learning_rate": 1.8424384997894562e-07,
      "loss": 0.4684,
      "step": 5335,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.464922711058264,
      "success_rate.epoch.env.math": 0.9104204753199269,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7735733278789119,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5074717977312291,
      "success_rate.epoch.global": 0.714153805566548,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9999066467513069,
      "tokens_p.mean_in_band": 0.5439236111111111,
      "tokens_rate.above_band": 0.9674855491329479,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03251445086705202
    },
    {
      "epoch": 0.8876329787234043,
      "grad_norm": 58.46042877756656,
      "learning_rate": 1.8421780897241593e-07,
      "loss": 0.4678,
      "step": 5340,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.510989010989011,
      "success_rate.epoch.env.logic": 0.464922711058264,
      "success_rate.epoch.env.math": 0.9105022831050228,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.773758430410791,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5074960623054996,
      "success_rate.epoch.global": 0.7143422093329818,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9911723163841808,
      "tokens_p.mean_in_band": 0.8697916666666666,
      "tokens_rate.above_band": 0.9833333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016666666666666666
    },
    {
      "epoch": 0.8884640957446809,
      "grad_norm": 22.362169171649757,
      "learning_rate": 1.841917604803086e-07,
      "loss": 0.4257,
      "step": 5345,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.9105839416058394,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7738970588235294,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072120470778674,
      "success_rate.epoch.global": 0.714304531085353,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9982525629077353,
      "tokens_p.mean_in_band": 0.6082763671875,
      "tokens_rate.above_band": 0.9710407239819004,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02895927601809955
    },
    {
      "epoch": 0.8892952127659575,
      "grad_norm": 53.66031052460184,
      "learning_rate": 1.8416570454885336e-07,
      "loss": 0.4381,
      "step": 5350,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.9105839416058394,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7739893834218048,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.507220440223165,
      "success_rate.epoch.global": 0.714379773505399,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9983974358974359,
      "tokens_p.mean_in_band": 0.3391170058139535,
      "tokens_rate.above_band": 0.8391019644527596,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16089803554724041
    },
    {
      "epoch": 0.890126329787234,
      "grad_norm": 57.13801330016607,
      "learning_rate": 1.8413964122429308e-07,
      "loss": 0.283,
      "step": 5355,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.9107468123861566,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7741277290348908,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072478235316562,
      "success_rate.epoch.global": 0.7145677062771417,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9890939597315436,
      "tokens_p.mean_in_band": 0.8190104166666666,
      "tokens_rate.above_band": 0.9802631578947368,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019736842105263157
    },
    {
      "epoch": 0.8909574468085106,
      "grad_norm": 59.69692465871971,
      "learning_rate": 1.8411357055288385e-07,
      "loss": 0.474,
      "step": 5360,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.9107468123861566,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7742198653885376,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.507256199563806,
      "success_rate.epoch.global": 0.7146428101565584,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5416666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9994868035190616,
      "tokens_p.mean_in_band": 0.5507089120370371,
      "tokens_rate.above_band": 0.969300739056282,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030699260943718023
    },
    {
      "epoch": 0.8917885638297872,
      "grad_norm": 120.55733575071133,
      "learning_rate": 1.8408749258089462e-07,
      "loss": 0.3917,
      "step": 5365,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4659090909090909,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.910828025477707,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7743119266055046,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5072719517736712,
      "success_rate.epoch.global": 0.7147553918990005,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9948770491803278,
      "tokens_p.mean_in_band": 0.72421875,
      "tokens_rate.above_band": 0.9838709677419355,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016129032258064516
    },
    {
      "epoch": 0.8926196808510638,
      "grad_norm": 56.88185408967301,
      "learning_rate": 1.8406140735460745e-07,
      "loss": 0.4158,
      "step": 5370,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4632768361581921,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.910828025477707,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7744039127776645,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5067899329298968,
      "success_rate.epoch.global": 0.7146424815983176,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9927288475565281,
      "tokens_p.mean_in_band": 0.6876346982758621,
      "tokens_rate.above_band": 0.9219905850706119,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07800941492938802
    },
    {
      "epoch": 0.8934507978723404,
      "grad_norm": 126.20126337988553,
      "learning_rate": 1.8403531492031723e-07,
      "loss": 0.415,
      "step": 5375,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4632768361581921,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.4643705463182898,
      "success_rate.epoch.env.math": 0.9109900090826522,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.7744958239967407,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5068130142775351,
      "success_rate.epoch.global": 0.7147924330005255,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9947996183206107,
      "tokens_p.mean_in_band": 0.6330180921052632,
      "tokens_rate.above_band": 0.9718100890207715,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028189910979228485
    },
    {
      "epoch": 0.894281914893617,
      "grad_norm": 54.55800904396644,
      "learning_rate": 1.8400921532433164e-07,
      "loss": 0.3074,
      "step": 5380,
      "success_rate.epoch.env.abd": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:alfworld": 0.4632768361581921,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.4638196915776987,
      "success_rate.epoch.env.math": 0.9111514052583862,
      "success_rate.epoch.env.sat": 0.10793650793650794,
      "success_rate.epoch.env.science": 0.7744758803175249,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5070035411673789,
      "success_rate.epoch.global": 0.7147355990027555,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9920454545454546,
      "tokens_p.mean_in_band": 0.7213541666666666,
      "tokens_rate.above_band": 0.8870967741935484,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11290322580645161
    },
    {
      "epoch": 0.8951130319148937,
      "grad_norm": 67.10472061459373,
      "learning_rate": 1.8398310861297107e-07,
      "loss": 0.3511,
      "step": 5385,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4632768361581921,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.46445497630331756,
      "success_rate.epoch.env.math": 0.9112318840579711,
      "success_rate.epoch.env.sat": 0.10793650793650794,
      "success_rate.epoch.env.science": 0.7745676500508647,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5081246644358861,
      "success_rate.epoch.global": 0.7149226330972988,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.996155753968254,
      "tokens_p.mean_in_band": 0.8640625,
      "tokens_rate.above_band": 0.9901768172888016,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009823182711198428
    },
    {
      "epoch": 0.8959441489361702,
      "grad_norm": 200.31084704830042,
      "learning_rate": 1.8395699483256853e-07,
      "loss": 0.4486,
      "step": 5390,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.4645390070921986,
      "success_rate.epoch.env.math": 0.9112318840579711,
      "success_rate.epoch.env.sat": 0.10793650793650794,
      "success_rate.epoch.env.science": 0.7746593451291438,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.508414757575925,
      "success_rate.epoch.global": 0.7149783776700301,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975945857795173,
      "tokens_p.mean_in_band": 0.6343245967741935,
      "tokens_rate.above_band": 0.961128526645768,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038871473354231974
    },
    {
      "epoch": 0.8967752659574468,
      "grad_norm": 69.37958639655824,
      "learning_rate": 1.8393087402946957e-07,
      "loss": 0.3711,
      "step": 5395,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.4645390070921986,
      "success_rate.epoch.env.math": 0.9112318840579711,
      "success_rate.epoch.env.sat": 0.11075949367088607,
      "success_rate.epoch.env.science": 0.7748425116846169,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5086880441477297,
      "success_rate.epoch.global": 0.715165007857517,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9898389570552147,
      "tokens_p.mean_in_band": 0.8142755681818182,
      "tokens_rate.above_band": 0.9367816091954023,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06321839080459771
    },
    {
      "epoch": 0.8976063829787234,
      "grad_norm": 203.84137353491911,
      "learning_rate": 1.8390474625003222e-07,
      "loss": 0.3331,
      "step": 5400,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5054347826086957,
      "success_rate.epoch.env.logic": 0.4645390070921986,
      "success_rate.epoch.env.math": 0.9112318840579711,
      "success_rate.epoch.env.sat": 0.11041009463722397,
      "success_rate.epoch.env.science": 0.7750253807106599,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.508672905056128,
      "success_rate.epoch.global": 0.7152205208742312,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.987145390070922,
      "tokens_p.mean_in_band": 0.7509068080357143,
      "tokens_rate.above_band": 0.834319526627219,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16568047337278108
    },
    {
      "epoch": 0.8984375,
      "grad_norm": 41.302546137968896,
      "learning_rate": 1.8387861154062692e-07,
      "loss": 0.4441,
      "step": 5405,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5027027027027027,
      "success_rate.epoch.env.logic": 0.4645390070921986,
      "success_rate.epoch.env.math": 0.9113924050632911,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7750710515631344,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5084117150921587,
      "success_rate.epoch.global": 0.7151451739471619,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9844774590163935,
      "tokens_p.mean_in_band": 0.7504300458715596,
      "tokens_rate.above_band": 0.8484005563282336,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15159944367176634
    },
    {
      "epoch": 0.8992686170212766,
      "grad_norm": 198.3513399811832,
      "learning_rate": 1.8385246994763633e-07,
      "loss": 0.4245,
      "step": 5410,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5027027027027027,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9113924050632911,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7752991279659298,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5084899207062057,
      "success_rate.epoch.global": 0.7153685311029796,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99231843575419,
      "tokens_p.mean_in_band": 0.5631793478260869,
      "tokens_rate.above_band": 0.8861386138613861,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11386138613861387
    },
    {
      "epoch": 0.9000997340425532,
      "grad_norm": 98.05155018026738,
      "learning_rate": 1.838263215174554e-07,
      "loss": 0.3299,
      "step": 5415,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5027027027027027,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9114724480578139,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7754357519254155,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5085096177020246,
      "success_rate.epoch.global": 0.7155172413793104,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.99140625,
      "tokens_p.mean_in_band": 0.8125,
      "tokens_rate.above_band": 0.96,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04
    },
    {
      "epoch": 0.9009308510638298,
      "grad_norm": 67.32561951735258,
      "learning_rate": 1.838001662964912e-07,
      "loss": 0.2388,
      "step": 5420,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5027027027027027,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9116321009918846,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7756630896942701,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5085447986750178,
      "success_rate.epoch.global": 0.7157771107921179,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9918355855855856,
      "tokens_p.mean_in_band": 0.7578125,
      "tokens_rate.above_band": 0.9823008849557522,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017699115044247787
    },
    {
      "epoch": 0.9017619680851063,
      "grad_norm": 115.12481471270185,
      "learning_rate": 1.837740043311628e-07,
      "loss": 0.4129,
      "step": 5425,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5027027027027027,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9108108108108108,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7759805903760615,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5084989996296285,
      "success_rate.epoch.global": 0.715943162560292,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950657894736842,
      "tokens_p.mean_in_band": 0.6008112980769231,
      "tokens_rate.above_band": 0.868020304568528,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1319796954314721
    },
    {
      "epoch": 0.902593085106383,
      "grad_norm": 91.58198245798793,
      "learning_rate": 1.837478356679013e-07,
      "loss": 0.4245,
      "step": 5430,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46629213483146065,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9108108108108108,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7761616161616162,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5082697562735242,
      "success_rate.epoch.global": 0.7159979155810318,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9962605384824585,
      "tokens_p.mean_below_band": 3.9301812648773193e-07,
      "tokens_p.mean_in_band": 0.5061860068259386,
      "tokens_rate.above_band": 0.9259632334424578,
      "tokens_rate.below_band": 0.0002518257365902795,
      "tokens_rate.in_band": 0.0737849408209519
    },
    {
      "epoch": 0.9034242021276596,
      "grad_norm": 79.6995287275183,
      "learning_rate": 1.8372166035314968e-07,
      "loss": 0.2948,
      "step": 5435,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4692737430167598,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9109712230215827,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7762068269036558,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.508559504558807,
      "success_rate.epoch.global": 0.7161458333333334,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974391805377721,
      "tokens_p.mean_below_band": 3.1650415621697903e-10,
      "tokens_p.mean_in_band": 0.6010044642857143,
      "tokens_rate.above_band": 0.9726027397260274,
      "tokens_rate.below_band": 0.0012453300124533001,
      "tokens_rate.in_band": 0.026151930261519303
    },
    {
      "epoch": 0.9042553191489362,
      "grad_norm": 162.34376600416132,
      "learning_rate": 1.8369547843336272e-07,
      "loss": 0.4836,
      "step": 5440,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4692737430167598,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4651711924439197,
      "success_rate.epoch.env.math": 0.9111310592459605,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7760290556900726,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5085578741052429,
      "success_rate.epoch.global": 0.7161441394562248,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973880597014926,
      "tokens_p.mean_below_band": 1.3597309589385986e-07,
      "tokens_p.mean_in_band": 0.5050403225806451,
      "tokens_rate.above_band": 0.9544159544159544,
      "tokens_rate.below_band": 0.0014245014245014246,
      "tokens_rate.in_band": 0.04415954415954416
    },
    {
      "epoch": 0.9050864361702128,
      "grad_norm": 58.87048100575551,
      "learning_rate": 1.8366928995500685e-07,
      "loss": 0.3133,
      "step": 5445,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4692737430167598,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4658018867924528,
      "success_rate.epoch.env.math": 0.9112107623318386,
      "success_rate.epoch.env.sat": 0.11006289308176101,
      "success_rate.epoch.env.science": 0.7761645493042952,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5086347732914823,
      "success_rate.epoch.global": 0.7163286531461258,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9942908653846154,
      "tokens_p.mean_in_band": 0.8380859375,
      "tokens_rate.above_band": 0.9765258215962441,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023474178403755867
    },
    {
      "epoch": 0.9059175531914894,
      "grad_norm": 76.48996585799078,
      "learning_rate": 1.8364309496456027e-07,
      "loss": 0.3129,
      "step": 5450,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4692737430167598,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4658018867924528,
      "success_rate.epoch.env.math": 0.9112903225806451,
      "success_rate.epoch.env.sat": 0.109717868338558,
      "success_rate.epoch.env.science": 0.7762547873412619,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.508618843613534,
      "success_rate.epoch.global": 0.7163461538461539,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9962628589798542,
      "tokens_p.mean_in_band": 0.671926738410596,
      "tokens_rate.above_band": 0.9392109500805152,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0607890499194847
    },
    {
      "epoch": 0.906748670212766,
      "grad_norm": 72.81418129946775,
      "learning_rate": 1.8361689350851266e-07,
      "loss": 0.2836,
      "step": 5455,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.4658018867924528,
      "success_rate.epoch.env.math": 0.9113697403760072,
      "success_rate.epoch.env.sat": 0.109717868338558,
      "success_rate.epoch.env.science": 0.7762998790810157,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.508898206226314,
      "success_rate.epoch.global": 0.7164566826860631,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9940124671916011,
      "tokens_p.mean_in_band": 0.8459821428571429,
      "tokens_rate.above_band": 0.9819587628865979,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01804123711340206
    },
    {
      "epoch": 0.9075797872340425,
      "grad_norm": 88.36304180432292,
      "learning_rate": 1.8359068563336514e-07,
      "loss": 0.5004,
      "step": 5460,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.4658018867924528,
      "success_rate.epoch.env.math": 0.9115281501340483,
      "success_rate.epoch.env.sat": 0.109717868338558,
      "success_rate.epoch.env.science": 0.7764350453172205,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5091679673886493,
      "success_rate.epoch.global": 0.7166774821544452,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.998471685971686,
      "tokens_p.mean_in_band": 0.7217881944444444,
      "tokens_rate.above_band": 0.9885496183206107,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011450381679389313
    },
    {
      "epoch": 0.9084109042553191,
      "grad_norm": 53.24133699265181,
      "learning_rate": 1.835644713856303e-07,
      "loss": 0.4388,
      "step": 5465,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.4658018867924528,
      "success_rate.epoch.env.math": 0.911685994647636,
      "success_rate.epoch.env.sat": 0.109717868338558,
      "success_rate.epoch.env.science": 0.7766599597585513,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5092027636572783,
      "success_rate.epoch.global": 0.7169346473029046,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9878571428571429,
      "tokens_p.mean_in_band": 0.833984375,
      "tokens_rate.above_band": 0.9562841530054644,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04371584699453552
    },
    {
      "epoch": 0.9092420212765957,
      "grad_norm": 71.85357657503724,
      "learning_rate": 1.8353825081183202e-07,
      "loss": 0.4464,
      "step": 5470,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.46588235294117647,
      "success_rate.epoch.env.math": 0.9117647058823529,
      "success_rate.epoch.env.sat": 0.109717868338558,
      "success_rate.epoch.env.science": 0.7767497988736927,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5092254015207858,
      "success_rate.epoch.global": 0.716988467020863,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9962121212121212,
      "tokens_p.mean_in_band": 0.6067708333333334,
      "tokens_rate.above_band": 0.9635036496350365,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0364963503649635
    },
    {
      "epoch": 0.9100731382978723,
      "grad_norm": 126.49033226744454,
      "learning_rate": 1.8351202395850538e-07,
      "loss": 0.4302,
      "step": 5475,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.46650998824911866,
      "success_rate.epoch.env.math": 0.9118432769367765,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7768395657418576,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5092665928746015,
      "success_rate.epoch.global": 0.717042217042217,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9956290192926045,
      "tokens_p.mean_in_band": 0.6981026785714286,
      "tokens_rate.above_band": 0.9174041297935103,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08259587020648967
    },
    {
      "epoch": 0.910904255319149,
      "grad_norm": 135.66130541386818,
      "learning_rate": 1.8348579087219661e-07,
      "loss": 0.346,
      "step": 5480,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.46650998824911866,
      "success_rate.epoch.env.math": 0.9119217081850534,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7769292604501608,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5092818770524724,
      "success_rate.epoch.global": 0.7171521035598706,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9857772435897436,
      "tokens_p.mean_in_band": 0.65703125,
      "tokens_rate.above_band": 0.9397590361445783,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.060240963855421686
    },
    {
      "epoch": 0.9117353723404256,
      "grad_norm": 219.08448873485182,
      "learning_rate": 1.8345955159946305e-07,
      "loss": 0.4447,
      "step": 5485,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.4671361502347418,
      "success_rate.epoch.env.math": 0.912,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7771084337349398,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5093622067875041,
      "success_rate.epoch.global": 0.7173716207476394,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937193627450981,
      "tokens_p.mean_in_band": 0.5677734375,
      "tokens_rate.above_band": 0.9107142857142857,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08928571428571429
    },
    {
      "epoch": 0.9125664893617021,
      "grad_norm": 265.95525225476683,
      "learning_rate": 1.8343330618687294e-07,
      "loss": 0.5568,
      "step": 5490,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026737967914439,
      "success_rate.epoch.env.logic": 0.4671361502347418,
      "success_rate.epoch.env.math": 0.9120781527531083,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7772873194221509,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5093855739184423,
      "success_rate.epoch.global": 0.7175542916235781,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9904891304347826,
      "tokens_p.mean_in_band": 0.6,
      "tokens_rate.above_band": 0.9484536082474226,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05154639175257732
    },
    {
      "epoch": 0.9133976063829787,
      "grad_norm": 113.36668262783957,
      "learning_rate": 1.8340705468100547e-07,
      "loss": 0.3579,
      "step": 5495,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4722222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053191489361702,
      "success_rate.epoch.env.logic": 0.4671361502347418,
      "success_rate.epoch.env.math": 0.9120781527531083,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7773547094188377,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5096321868403889,
      "success_rate.epoch.global": 0.7176804855998967,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963834269662921,
      "tokens_p.mean_in_band": 0.613037109375,
      "tokens_rate.above_band": 0.9910913140311804,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008908685968819599
    },
    {
      "epoch": 0.9142287234042553,
      "grad_norm": 91.15157953329543,
      "learning_rate": 1.833807971284506e-07,
      "loss": 0.3707,
      "step": 5500,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4696132596685083,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053191489361702,
      "success_rate.epoch.env.logic": 0.4671361502347418,
      "success_rate.epoch.env.math": 0.9122340425531915,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7774439102564102,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094172893934745,
      "success_rate.epoch.global": 0.717733608673206,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9973529411764706,
      "tokens_p.mean_in_band": 0.6429036458333334,
      "tokens_rate.above_band": 0.9860788863109049,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013921113689095127
    },
    {
      "epoch": 0.9150598404255319,
      "grad_norm": 85.7865363983733,
      "learning_rate": 1.8335453357580912e-07,
      "loss": 0.3479,
      "step": 5505,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4696132596685083,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053191489361702,
      "success_rate.epoch.env.logic": 0.46776084407971863,
      "success_rate.epoch.env.math": 0.9122340425531915,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7775330396475771,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094821824149421,
      "success_rate.epoch.global": 0.7178428589859372,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9897260273972602,
      "tokens_p.mean_in_band": 0.7274305555555556,
      "tokens_rate.above_band": 0.9240506329113924,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0759493670886076
    },
    {
      "epoch": 0.9158909574468085,
      "grad_norm": 123.57800215684804,
      "learning_rate": 1.8332826406969235e-07,
      "loss": 0.301,
      "step": 5510,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.4696132596685083,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.4672131147540984,
      "success_rate.epoch.env.math": 0.912311780336581,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7777555511102221,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5096976259531923,
      "success_rate.epoch.global": 0.7180048975383426,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9980396065922382,
      "tokens_p.mean_in_band": 0.6572779605263158,
      "tokens_rate.above_band": 0.99,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01
    },
    {
      "epoch": 0.9167220744680851,
      "grad_norm": 90.49517374831306,
      "learning_rate": 1.8330198865672226e-07,
      "loss": 0.418,
      "step": 5515,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.4672131147540984,
      "success_rate.epoch.env.math": 0.912311780336581,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7779776179056754,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094832417859115,
      "success_rate.epoch.global": 0.71809401159047,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965277777777778,
      "tokens_p.mean_in_band": 0.6599392361111112,
      "tokens_rate.above_band": 0.9896907216494846,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010309278350515464
    },
    {
      "epoch": 0.9175531914893617,
      "grad_norm": 67.32676576008845,
      "learning_rate": 1.8327570738353125e-07,
      "loss": 0.5005,
      "step": 5520,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.4666666666666667,
      "success_rate.epoch.env.math": 0.9124668435013262,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7778665601278466,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094375651767739,
      "success_rate.epoch.global": 0.718018018018018,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9976081530782029,
      "tokens_p.mean_in_band": 0.5864415322580645,
      "tokens_rate.above_band": 0.9509493670886076,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0490506329113924
    },
    {
      "epoch": 0.9183843085106383,
      "grad_norm": 149.87406036329205,
      "learning_rate": 1.8324942029676214e-07,
      "loss": 0.4205,
      "step": 5525,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.4666666666666667,
      "success_rate.epoch.env.math": 0.9125441696113075,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7780439121756487,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094607177365723,
      "success_rate.epoch.global": 0.7181993569131833,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9855769230769231,
      "tokens_p.mean_in_band": 0.8412642045454546,
      "tokens_rate.above_band": 0.9285714285714286,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07142857142857142
    },
    {
      "epoch": 0.9192154255319149,
      "grad_norm": 67.83569970990335,
      "learning_rate": 1.8322312744306807e-07,
      "loss": 0.7035,
      "step": 5530,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.4672897196261682,
      "success_rate.epoch.env.math": 0.912621359223301,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7780215396888711,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5095223422897285,
      "success_rate.epoch.global": 0.7182881377714947,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.986,
      "tokens_p.mean_below_band": 2.88089116414388e-07,
      "tokens_p.mean_in_band": 0.10345790952890792,
      "tokens_rate.above_band": 0.13791835233541744,
      "tokens_rate.below_band": 0.0033100404560500183,
      "tokens_rate.in_band": 0.8587716072085325
    },
    {
      "epoch": 0.9200465425531915,
      "grad_norm": 149.39185118653322,
      "learning_rate": 1.8319682886911243e-07,
      "loss": 0.4134,
      "step": 5535,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.4679113185530922,
      "success_rate.epoch.env.math": 0.9126984126984127,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7780215396888711,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5093428243224798,
      "success_rate.epoch.global": 0.718268242548818,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.4,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9940915300546448,
      "tokens_p.mean_in_band": 0.6588635341726619,
      "tokens_rate.above_band": 0.9294057897409853,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07059421025901473
    },
    {
      "epoch": 0.9208776595744681,
      "grad_norm": 122.91575502138198,
      "learning_rate": 1.8317052462156875e-07,
      "loss": 0.5052,
      "step": 5540,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.4679113185530922,
      "success_rate.epoch.env.math": 0.9127753303964757,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7779549531592586,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5093437635196116,
      "success_rate.epoch.global": 0.7182845403184386,
      "success_rate.window.env.abd": 0.5,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.998284869083585,
      "tokens_p.mean_below_band": 7.188646122813225e-09,
      "tokens_p.mean_in_band": 0.15450613839285715,
      "tokens_rate.above_band": 0.8870031263957123,
      "tokens_rate.below_band": 0.00044662795891022776,
      "tokens_rate.in_band": 0.1125502456453774
    },
    {
      "epoch": 0.9217087765957447,
      "grad_norm": 45.88892155646569,
      "learning_rate": 1.8314421474712056e-07,
      "loss": 0.3265,
      "step": 5545,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.4679113185530922,
      "success_rate.epoch.env.math": 0.9128521126760564,
      "success_rate.epoch.env.sat": 0.109375,
      "success_rate.epoch.env.science": 0.7779326827325234,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5093487191425976,
      "success_rate.epoch.global": 0.7183369690748107,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9885519801980198,
      "tokens_p.mean_in_band": 0.576171875,
      "tokens_rate.above_band": 0.8416666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15833333333333333
    },
    {
      "epoch": 0.9225398936170213,
      "grad_norm": 67.16419115377029,
      "learning_rate": 1.8311789929246154e-07,
      "loss": 0.3728,
      "step": 5550,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46703296703296704,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.46853146853146854,
      "success_rate.epoch.env.math": 0.9120492524186455,
      "success_rate.epoch.env.sat": 0.10903426791277258,
      "success_rate.epoch.env.science": 0.7780211029265379,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5093091716723933,
      "success_rate.epoch.global": 0.718261092587843,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952098540145985,
      "tokens_p.mean_in_band": 0.6761067708333334,
      "tokens_rate.above_band": 0.9448275862068966,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05517241379310345
    },
    {
      "epoch": 0.9233710106382979,
      "grad_norm": 52.69756643980287,
      "learning_rate": 1.8309157830429512e-07,
      "loss": 0.3466,
      "step": 5555,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.46853146853146854,
      "success_rate.epoch.env.math": 0.9121265377855887,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.7781536012733784,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5095622222299582,
      "success_rate.epoch.global": 0.7183495643259866,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9976954277286135,
      "tokens_p.mean_in_band": 0.6669921875,
      "tokens_rate.above_band": 0.904,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.096
    },
    {
      "epoch": 0.9242021276595744,
      "grad_norm": 68.73886400895024,
      "learning_rate": 1.8306525182933458e-07,
      "loss": 0.4179,
      "step": 5560,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.4691501746216531,
      "success_rate.epoch.env.math": 0.9121265377855887,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.7782859415390734,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5096304991714017,
      "success_rate.epoch.global": 0.7184938524590164,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9933873720136519,
      "tokens_p.mean_in_band": 0.81640625,
      "tokens_rate.above_band": 0.9543973941368078,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04560260586319218
    },
    {
      "epoch": 0.925033244680851,
      "grad_norm": 94.56886753915559,
      "learning_rate": 1.8303891991430303e-07,
      "loss": 0.2386,
      "step": 5565,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052631578947369,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9121265377855887,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.778594122319301,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5097146308094963,
      "success_rate.epoch.global": 0.7187819856704196,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954111600587372,
      "tokens_p.mean_in_band": 0.65625,
      "tokens_rate.above_band": 0.9742489270386266,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02575107296137339
    },
    {
      "epoch": 0.9258643617021277,
      "grad_norm": 86.2283807168584,
      "learning_rate": 1.830125826059331e-07,
      "loss": 0.4311,
      "step": 5570,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026178010471204,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9121265377855887,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.7787259376860488,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094861270385083,
      "success_rate.epoch.global": 0.7187979539641943,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9932541824069078,
      "tokens_p.mean_below_band": 3.2782554626464844e-07,
      "tokens_p.mean_in_band": 0.4228376400203666,
      "tokens_rate.above_band": 0.7900234491579621,
      "tokens_rate.below_band": 0.0006395224898742272,
      "tokens_rate.in_band": 0.20933702835216372
    },
    {
      "epoch": 0.9266954787234043,
      "grad_norm": 60.439870970998264,
      "learning_rate": 1.8298623995096713e-07,
      "loss": 0.3498,
      "step": 5575,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026178010471204,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9121265377855887,
      "success_rate.epoch.env.sat": 0.10835913312693499,
      "success_rate.epoch.env.science": 0.7789452815226011,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094754747466513,
      "success_rate.epoch.global": 0.7188857653973934,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9926394628099173,
      "tokens_p.mean_in_band": 0.6589133522727273,
      "tokens_rate.above_band": 0.8461538461538461,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15384615384615385
    },
    {
      "epoch": 0.9275265957446809,
      "grad_norm": 118.51258004537772,
      "learning_rate": 1.8295989199615682e-07,
      "loss": 0.4497,
      "step": 5580,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5026178010471204,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9122036874451273,
      "success_rate.epoch.env.sat": 0.10835913312693499,
      "success_rate.epoch.env.science": 0.7790766792153755,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5094944335968616,
      "success_rate.epoch.global": 0.719029374201788,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9930921052631579,
      "tokens_p.mean_in_band": 0.8177083333333334,
      "tokens_rate.above_band": 0.9693877551020408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030612244897959183
    },
    {
      "epoch": 0.9283577127659575,
      "grad_norm": 82.31978805853106,
      "learning_rate": 1.8293353878826337e-07,
      "loss": 0.344,
      "step": 5585,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052083333333334,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9122036874451273,
      "success_rate.epoch.env.sat": 0.10835913312693499,
      "success_rate.epoch.env.science": 0.7792079207920792,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5097418675843994,
      "success_rate.epoch.global": 0.7191728363543528,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949596774193549,
      "tokens_p.mean_in_band": 0.6793094758064516,
      "tokens_rate.above_band": 0.9583333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041666666666666664
    },
    {
      "epoch": 0.929188829787234,
      "grad_norm": 112.32913906802416,
      "learning_rate": 1.8290718037405727e-07,
      "loss": 0.376,
      "step": 5590,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052083333333334,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9122036874451273,
      "success_rate.epoch.env.sat": 0.10835913312693499,
      "success_rate.epoch.env.science": 0.7790973871733967,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5097318190736102,
      "success_rate.epoch.global": 0.7191168963757019,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9989247311827957,
      "tokens_p.mean_in_band": 0.5826171875,
      "tokens_rate.above_band": 0.9587628865979382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041237113402061855
    },
    {
      "epoch": 0.9300199468085106,
      "grad_norm": 210.56060122057153,
      "learning_rate": 1.8288081680031818e-07,
      "loss": 0.5236,
      "step": 5595,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052083333333334,
      "success_rate.epoch.env.logic": 0.4697674418604651,
      "success_rate.epoch.env.math": 0.9122807017543859,
      "success_rate.epoch.env.sat": 0.10835913312693499,
      "success_rate.epoch.env.science": 0.7792721518987342,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5097547080767553,
      "success_rate.epoch.global": 0.7192960081622242,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9927685950413223,
      "tokens_p.mean_in_band": 0.6494391025641025,
      "tokens_rate.above_band": 0.8612099644128114,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1387900355871886
    },
    {
      "epoch": 0.9308510638297872,
      "grad_norm": 123.92616469593366,
      "learning_rate": 1.8285444811383508e-07,
      "loss": 0.3939,
      "step": 5600,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052083333333334,
      "success_rate.epoch.env.logic": 0.4692218350754936,
      "success_rate.epoch.env.math": 0.9122807017543859,
      "success_rate.epoch.env.sat": 0.10802469135802469,
      "success_rate.epoch.env.science": 0.7794030440798577,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.509686602951959,
      "success_rate.epoch.global": 0.7192199847055825,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986538461538461,
      "tokens_p.mean_in_band": 0.4475911458333333,
      "tokens_rate.above_band": 0.9312320916905444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06876790830945559
    },
    {
      "epoch": 0.9316821808510638,
      "grad_norm": 192.43246560782973,
      "learning_rate": 1.8282807436140588e-07,
      "loss": 0.5641,
      "step": 5605,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052083333333334,
      "success_rate.epoch.env.logic": 0.4692218350754936,
      "success_rate.epoch.env.math": 0.9115586690017513,
      "success_rate.epoch.env.sat": 0.10802469135802469,
      "success_rate.epoch.env.science": 0.7794466403162056,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5096249269050239,
      "success_rate.epoch.global": 0.719199898076188,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983501552795031,
      "tokens_p.mean_in_band": 0.4619732481060606,
      "tokens_rate.above_band": 0.9512555391432792,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04874446085672083
    },
    {
      "epoch": 0.9325132978723404,
      "grad_norm": 66.30292936547168,
      "learning_rate": 1.8280169558983754e-07,
      "loss": 0.4176,
      "step": 5610,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5052083333333334,
      "success_rate.epoch.env.logic": 0.4692218350754936,
      "success_rate.epoch.env.math": 0.9115586690017513,
      "success_rate.epoch.env.sat": 0.10802469135802469,
      "success_rate.epoch.env.science": 0.7796208530805687,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5096407644290569,
      "success_rate.epoch.global": 0.7193429262702152,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9873511904761905,
      "tokens_p.mean_in_band": 0.8818359375,
      "tokens_rate.above_band": 0.9692307692307692,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03076923076923077
    },
    {
      "epoch": 0.933344414893617,
      "grad_norm": 64.2818990011968,
      "learning_rate": 1.827753118459459e-07,
      "loss": 0.3374,
      "step": 5615,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5077720207253886,
      "success_rate.epoch.env.logic": 0.4692218350754936,
      "success_rate.epoch.env.math": 0.9115586690017513,
      "success_rate.epoch.env.sat": 0.10802469135802469,
      "success_rate.epoch.env.science": 0.7798382323929769,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5098935886749172,
      "success_rate.epoch.global": 0.7195571955719557,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930555555555556,
      "tokens_p.mean_in_band": 0.5616319444444444,
      "tokens_rate.above_band": 0.9591836734693877,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04081632653061224
    },
    {
      "epoch": 0.9341755319148937,
      "grad_norm": 97.80506391486851,
      "learning_rate": 1.8274892317655566e-07,
      "loss": 0.5687,
      "step": 5620,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5077720207253886,
      "success_rate.epoch.env.logic": 0.4692218350754936,
      "success_rate.epoch.env.math": 0.9116360454943132,
      "success_rate.epoch.env.sat": 0.10802469135802469,
      "success_rate.epoch.env.science": 0.7800118273211117,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.509916404258617,
      "success_rate.epoch.global": 0.719735503560529,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9954681588902901,
      "tokens_p.mean_in_band": 0.6418779481132075,
      "tokens_rate.above_band": 0.9373522458628841,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06264775413711583
    },
    {
      "epoch": 0.9350066489361702,
      "grad_norm": 295.8926035675023,
      "learning_rate": 1.8272252962850022e-07,
      "loss": 0.419,
      "step": 5625,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5077720207253886,
      "success_rate.epoch.env.logic": 0.46983758700696054,
      "success_rate.epoch.env.math": 0.9117132867132867,
      "success_rate.epoch.env.sat": 0.1076923076923077,
      "success_rate.epoch.env.science": 0.7800551832873472,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5099531283905223,
      "success_rate.epoch.global": 0.7197508896797153,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9952713815789473,
      "tokens_p.mean_in_band": 0.6477430555555556,
      "tokens_rate.above_band": 0.8710601719197708,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12893982808022922
    },
    {
      "epoch": 0.9358377659574468,
      "grad_norm": 69.1298632991204,
      "learning_rate": 1.826961312486217e-07,
      "loss": 0.2545,
      "step": 5630,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5077720207253886,
      "success_rate.epoch.env.logic": 0.4704519119351101,
      "success_rate.epoch.env.math": 0.9117903930131004,
      "success_rate.epoch.env.sat": 0.1076923076923077,
      "success_rate.epoch.env.science": 0.780185148709868,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5100278008132936,
      "success_rate.epoch.global": 0.7199288708243363,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.992688679245283,
      "tokens_p.mean_in_band": 0.697265625,
      "tokens_rate.above_band": 0.9430604982206405,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05693950177935943
    },
    {
      "epoch": 0.9366688829787234,
      "grad_norm": 134.50068873257337,
      "learning_rate": 1.8266972808377074e-07,
      "loss": 0.407,
      "step": 5635,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5077720207253886,
      "success_rate.epoch.env.logic": 0.4710648148148148,
      "success_rate.epoch.env.math": 0.9117903930131004,
      "success_rate.epoch.env.sat": 0.10736196319018405,
      "success_rate.epoch.env.science": 0.7803149606299212,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5100652890221694,
      "success_rate.epoch.global": 0.7199796902767199,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9956234643734644,
      "tokens_p.mean_in_band": 0.5833834134615384,
      "tokens_rate.above_band": 0.9399538106235565,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06004618937644342
    },
    {
      "epoch": 0.9375,
      "grad_norm": 89.89322297515757,
      "learning_rate": 1.826433201808065e-07,
      "loss": 0.4559,
      "step": 5640,
      "success_rate.epoch.env.abd": 0.4583333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5077720207253886,
      "success_rate.epoch.env.logic": 0.4710648148148148,
      "success_rate.epoch.env.math": 0.9117903930131004,
      "success_rate.epoch.env.sat": 0.10736196319018405,
      "success_rate.epoch.env.science": 0.7804878048780488,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5100810021356356,
      "success_rate.epoch.global": 0.7201217964983506,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9922480620155039,
      "tokens_p.mean_in_band": 0.544140625,
      "tokens_rate.above_band": 0.8657718120805369,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1342281879194631
    },
    {
      "epoch": 0.9383311170212766,
      "grad_norm": 140.61777539299692,
      "learning_rate": 1.826169075865965e-07,
      "loss": 0.471,
      "step": 5645,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.47167630057803467,
      "success_rate.epoch.env.math": 0.9117903930131004,
      "success_rate.epoch.env.sat": 0.10703363914373089,
      "success_rate.epoch.env.science": 0.7804638364779874,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5108715688206612,
      "success_rate.epoch.global": 0.7200253485424588,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9881500987491771,
      "tokens_p.mean_in_band": 0.6969708136792453,
      "tokens_rate.above_band": 0.877527440785673,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12247255921432698
    },
    {
      "epoch": 0.9391622340425532,
      "grad_norm": 155.31347010657367,
      "learning_rate": 1.8259049034801664e-07,
      "loss": 0.4401,
      "step": 5650,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.47167630057803467,
      "success_rate.epoch.env.math": 0.9117903930131004,
      "success_rate.epoch.env.sat": 0.10703363914373089,
      "success_rate.epoch.env.science": 0.7807224185316058,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.510895076280081,
      "success_rate.epoch.global": 0.7202380952380952,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937043795620438,
      "tokens_p.mean_below_band": 2.2351741790771484e-07,
      "tokens_p.mean_in_band": 0.5067377253320683,
      "tokens_rate.above_band": 0.8664305590690615,
      "tokens_rate.below_band": 0.00025297242600556537,
      "tokens_rate.in_band": 0.13331646850493295
    },
    {
      "epoch": 0.9399933510638298,
      "grad_norm": 153.811615759648,
      "learning_rate": 1.8256406851195106e-07,
      "loss": 0.3535,
      "step": 5655,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.47167630057803467,
      "success_rate.epoch.env.math": 0.9117903930131004,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7808084772370487,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5108732341559795,
      "success_rate.epoch.global": 0.7202177490821623,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9875553097345132,
      "tokens_p.mean_in_band": 0.7020596590909091,
      "tokens_rate.above_band": 0.9112903225806451,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08870967741935484
    },
    {
      "epoch": 0.9408244680851063,
      "grad_norm": 33.00768094321201,
      "learning_rate": 1.8253764212529204e-07,
      "loss": 0.5389,
      "step": 5660,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.47167630057803467,
      "success_rate.epoch.env.math": 0.9118673647469459,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7808944684189878,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5108880489665054,
      "success_rate.epoch.global": 0.7203239686155404,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9971804511278195,
      "tokens_p.mean_in_band": 0.6077127659574468,
      "tokens_rate.above_band": 0.9396274887604368,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06037251123956326
    },
    {
      "epoch": 0.941655585106383,
      "grad_norm": 72.33420528706179,
      "learning_rate": 1.8251121123493992e-07,
      "loss": 0.3276,
      "step": 5665,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.47167630057803467,
      "success_rate.epoch.env.math": 0.9118673647469459,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7809803921568628,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5108958602154031,
      "success_rate.epoch.global": 0.7203947368421053,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.989939024390244,
      "tokens_p.mean_in_band": 0.8671875,
      "tokens_rate.above_band": 0.9951456310679612,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0048543689320388345
    },
    {
      "epoch": 0.9424867021276596,
      "grad_norm": 78.54609457190823,
      "learning_rate": 1.8248477588780312e-07,
      "loss": 0.3592,
      "step": 5670,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4722863741339492,
      "success_rate.epoch.env.math": 0.912020905923345,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7811091514795219,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5109769851294915,
      "success_rate.epoch.global": 0.7206068268015171,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921116504854369,
      "tokens_p.mean_below_band": 9.255018085241318e-09,
      "tokens_p.mean_in_band": 0.871875,
      "tokens_rate.above_band": 0.9716981132075472,
      "tokens_rate.below_band": 0.0047169811320754715,
      "tokens_rate.in_band": 0.02358490566037736
    },
    {
      "epoch": 0.9433178191489362,
      "grad_norm": 91.49992006573414,
      "learning_rate": 1.8245833613079783e-07,
      "loss": 0.3057,
      "step": 5675,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4722863741339492,
      "success_rate.epoch.env.math": 0.9113043478260869,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7810419114766941,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5109057307567565,
      "success_rate.epoch.global": 0.7205306380290587,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9941432968536251,
      "tokens_p.mean_below_band": 4.3655745685100555e-09,
      "tokens_p.mean_in_band": 0.6121002906976745,
      "tokens_rate.above_band": 0.9432258064516129,
      "tokens_rate.below_band": 0.0012903225806451613,
      "tokens_rate.in_band": 0.05548387096774193
    },
    {
      "epoch": 0.9441489361702128,
      "grad_norm": 114.36942567723449,
      "learning_rate": 1.824318920108482e-07,
      "loss": 0.3578,
      "step": 5680,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4722863741339492,
      "success_rate.epoch.env.math": 0.9113814074717637,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7812133072407045,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5109283176121826,
      "success_rate.epoch.global": 0.7207070707070707,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9996666666666667,
      "tokens_p.mean_in_band": 0.5948840725806451,
      "tokens_rate.above_band": 0.9603072983354674,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03969270166453265
    },
    {
      "epoch": 0.9449800531914894,
      "grad_norm": 112.42782695550275,
      "learning_rate": 1.8240544357488602e-07,
      "loss": 0.4535,
      "step": 5685,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9113814074717637,
      "success_rate.epoch.env.sat": 0.10670731707317073,
      "success_rate.epoch.env.science": 0.7812989045383412,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5109914324787986,
      "success_rate.epoch.global": 0.7208128234254702,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970472440944882,
      "tokens_p.mean_in_band": 0.6451981707317073,
      "tokens_rate.above_band": 0.9559139784946237,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04408602150537634
    },
    {
      "epoch": 0.945811170212766,
      "grad_norm": 86.37560047605557,
      "learning_rate": 1.8237899086985078e-07,
      "loss": 0.433,
      "step": 5690,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.46994535519125685,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9113814074717637,
      "success_rate.epoch.env.sat": 0.10638297872340426,
      "success_rate.epoch.env.science": 0.7815126050420168,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5109813744927902,
      "success_rate.epoch.global": 0.7208979694791272,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9961890243902439,
      "tokens_p.mean_in_band": 0.6688988095238095,
      "tokens_rate.above_band": 0.9398280802292264,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06017191977077364
    },
    {
      "epoch": 0.9466422872340425,
      "grad_norm": 166.9032547031139,
      "learning_rate": 1.8235253394268961e-07,
      "loss": 0.3494,
      "step": 5695,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9114583333333334,
      "success_rate.epoch.env.sat": 0.10638297872340426,
      "success_rate.epoch.env.science": 0.781597968353194,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5112580127598823,
      "success_rate.epoch.global": 0.7210386991050044,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9946369636963697,
      "tokens_p.mean_in_band": 0.6320082720588235,
      "tokens_rate.above_band": 0.946875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053125
    },
    {
      "epoch": 0.9474734042553191,
      "grad_norm": 53.286843872894984,
      "learning_rate": 1.8232607284035701e-07,
      "loss": 0.4844,
      "step": 5700,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.3684210526315789,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5051546391752577,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9114583333333334,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.7816832649873071,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5112364603936381,
      "success_rate.epoch.global": 0.7210181451612904,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9894340974212035,
      "tokens_p.mean_in_band": 0.7130408653846154,
      "tokens_rate.above_band": 0.9306666666666666,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06933333333333333
    },
    {
      "epoch": 0.9483045212765957,
      "grad_norm": 55.37192669990385,
      "learning_rate": 1.82299607609815e-07,
      "loss": 0.3795,
      "step": 5705,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9114583333333334,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.7818536585365854,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5143534612513426,
      "success_rate.epoch.global": 0.7212289095945605,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9642857142857143,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949742759146342,
      "tokens_p.mean_in_band": 0.7826286764705882,
      "tokens_rate.above_band": 0.9872084273890143,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012791572610985704
    },
    {
      "epoch": 0.9491356382978723,
      "grad_norm": 61.4604155222677,
      "learning_rate": 1.8227313829803286e-07,
      "loss": 0.2709,
      "step": 5710,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9116117850953206,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.7821087507308517,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.514390601611002,
      "success_rate.epoch.global": 0.7215094339622642,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9898148148148148,
      "tokens_p.mean_in_band": 0.87890625,
      "tokens_rate.above_band": 0.9926470588235294,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007352941176470588
    },
    {
      "epoch": 0.949966755319149,
      "grad_norm": 56.37754010095084,
      "learning_rate": 1.822466649519871e-07,
      "loss": 0.4267,
      "step": 5715,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9116117850953206,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.7820837390457643,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5145875413804143,
      "success_rate.epoch.global": 0.7214680744092509,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9949751148545176,
      "tokens_p.mean_in_band": 0.6371626420454546,
      "tokens_rate.above_band": 0.9674074074074074,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03259259259259259
    },
    {
      "epoch": 0.9507978723404256,
      "grad_norm": 69.17142813485735,
      "learning_rate": 1.822201876186615e-07,
      "loss": 0.3764,
      "step": 5720,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9116117850953206,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.782295719844358,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146068123621046,
      "success_rate.epoch.global": 0.7216430096721518,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9993594436310396,
      "tokens_p.mean_in_band": 0.5391049592391305,
      "tokens_rate.above_band": 0.9368998628257887,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06310013717421124
    },
    {
      "epoch": 0.9516289893617021,
      "grad_norm": 148.37458987188273,
      "learning_rate": 1.8219370634504677e-07,
      "loss": 0.4433,
      "step": 5725,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.4728950403690888,
      "success_rate.epoch.env.math": 0.9116883116883117,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.7823803967327888,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.514621467224052,
      "success_rate.epoch.global": 0.7217478653942743,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.995954003407155,
      "tokens_p.mean_in_band": 0.6315104166666666,
      "tokens_rate.above_band": 0.9949152542372881,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005084745762711864
    },
    {
      "epoch": 0.9524601063829787,
      "grad_norm": 108.27536602654064,
      "learning_rate": 1.8216722117814074e-07,
      "loss": 0.3811,
      "step": 5730,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.4735023041474654,
      "success_rate.epoch.env.math": 0.9117647058823529,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.7825072886297376,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146951535758126,
      "success_rate.epoch.global": 0.7219224494917806,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9861680327868853,
      "tokens_p.mean_in_band": 0.8127170138888888,
      "tokens_rate.above_band": 0.9104477611940298,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08955223880597014
    },
    {
      "epoch": 0.9532912234042553,
      "grad_norm": 164.29866779636046,
      "learning_rate": 1.8214073216494804e-07,
      "loss": 0.3765,
      "step": 5735,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.47295742232451093,
      "success_rate.epoch.env.math": 0.9118409680207433,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.7825918010491548,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146602347335265,
      "success_rate.epoch.global": 0.7219365358083532,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99839514978602,
      "tokens_p.mean_in_band": 0.6144153225806451,
      "tokens_rate.above_band": 0.9576502732240437,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04234972677595628
    },
    {
      "epoch": 0.9541223404255319,
      "grad_norm": 95.65806487206133,
      "learning_rate": 1.8211423935248022e-07,
      "loss": 0.4464,
      "step": 5740,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47282608695652173,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.47295742232451093,
      "success_rate.epoch.env.math": 0.9119170984455959,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.7824820353466693,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146571769810145,
      "success_rate.epoch.global": 0.7219157472417251,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.978150406504065,
      "tokens_p.mean_in_band": 0.7730034722222222,
      "tokens_rate.above_band": 0.9318181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06818181818181818
    },
    {
      "epoch": 0.9549534574468085,
      "grad_norm": 114.87790922893703,
      "learning_rate": 1.820877427877555e-07,
      "loss": 0.3373,
      "step": 5745,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5102040816326531,
      "success_rate.epoch.env.logic": 0.4735632183908046,
      "success_rate.epoch.env.math": 0.911993097497843,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.782608695652174,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5144983259571776,
      "success_rate.epoch.global": 0.7219994988724631,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983175473579262,
      "tokens_p.mean_in_band": 0.68583984375,
      "tokens_rate.above_band": 0.9804496578690127,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019550342130987292
    },
    {
      "epoch": 0.9557845744680851,
      "grad_norm": 85.4252376742887,
      "learning_rate": 1.8206124251779882e-07,
      "loss": 0.4428,
      "step": 5750,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4730195177956372,
      "success_rate.epoch.env.math": 0.9120689655172414,
      "success_rate.epoch.env.sat": 0.10574018126888217,
      "success_rate.epoch.env.science": 0.7826508829807879,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146856558162813,
      "success_rate.epoch.global": 0.7220135236664162,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.72,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9942100650976464,
      "tokens_p.mean_in_band": 0.6355902777777778,
      "tokens_rate.above_band": 0.9779627815866797,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022037218413320275
    },
    {
      "epoch": 0.9566156914893617,
      "grad_norm": 195.25862102688197,
      "learning_rate": 1.8203473858964164e-07,
      "loss": 0.2643,
      "step": 5755,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4730195177956372,
      "success_rate.epoch.env.math": 0.9121447028423773,
      "success_rate.epoch.env.sat": 0.10542168674698796,
      "success_rate.epoch.env.science": 0.7827352085354026,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146712529397228,
      "success_rate.epoch.global": 0.7220275344180225,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9887724550898204,
      "tokens_p.mean_in_band": 0.6139322916666666,
      "tokens_rate.above_band": 0.9027027027027027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0972972972972973
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 97.77268051467541,
      "learning_rate": 1.8200823105032195e-07,
      "loss": 0.3047,
      "step": 5760,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4730195177956372,
      "success_rate.epoch.env.math": 0.9122203098106713,
      "success_rate.epoch.env.sat": 0.10542168674698796,
      "success_rate.epoch.env.science": 0.7828194686833431,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146857863139259,
      "success_rate.epoch.global": 0.7221318653822094,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9979047788873039,
      "tokens_p.mean_in_band": 0.5461128048780488,
      "tokens_rate.above_band": 0.944743935309973,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05525606469002695
    },
    {
      "epoch": 0.9582779255319149,
      "grad_norm": 70.86647272407083,
      "learning_rate": 1.8198171994688414e-07,
      "loss": 0.5016,
      "step": 5765,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4730195177956372,
      "success_rate.epoch.env.math": 0.9122203098106713,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7829036635006784,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146646602389671,
      "success_rate.epoch.global": 0.7221110555277639,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998405612244898,
      "tokens_p.mean_in_band": 0.5956029647435898,
      "tokens_rate.above_band": 0.9617271835132483,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038272816486751716
    },
    {
      "epoch": 0.9591090425531915,
      "grad_norm": 99.77237951397949,
      "learning_rate": 1.8195520532637894e-07,
      "loss": 0.3893,
      "step": 5770,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4724770642201835,
      "success_rate.epoch.env.math": 0.9122203098106713,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7830718574472206,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5146306366363388,
      "success_rate.epoch.global": 0.7221597300337458,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9999204834605598,
      "tokens_p.mean_in_band": 0.5905230978260869,
      "tokens_rate.above_band": 0.980865224625624,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01913477537437604
    },
    {
      "epoch": 0.9599401595744681,
      "grad_norm": 87.48859439512039,
      "learning_rate": 1.8192868723586328e-07,
      "loss": 0.3305,
      "step": 5775,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47368421052631576,
      "success_rate.epoch.env.math": 0.9122203098106713,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.783239790981227,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5147556438945332,
      "success_rate.epoch.global": 0.7223679280629449,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9914772727272727,
      "tokens_p.mean_in_band": 0.79296875,
      "tokens_rate.above_band": 0.9892086330935251,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01079136690647482
    },
    {
      "epoch": 0.9607712765957447,
      "grad_norm": 88.92169842872373,
      "learning_rate": 1.8190216572240028e-07,
      "loss": 0.4432,
      "step": 5780,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47368421052631576,
      "success_rate.epoch.env.math": 0.9122957867583835,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.783323660282453,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.514770129917164,
      "success_rate.epoch.global": 0.7224719101123596,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9895341981132075,
      "tokens_p.mean_in_band": 0.7091346153846154,
      "tokens_rate.above_band": 0.9422222222222222,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.057777777777777775
    },
    {
      "epoch": 0.9616023936170213,
      "grad_norm": 73.74395543092918,
      "learning_rate": 1.8187564083305913e-07,
      "loss": 0.4658,
      "step": 5785,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47368421052631576,
      "success_rate.epoch.env.math": 0.9123711340206185,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7834912043301759,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5147922109453419,
      "success_rate.epoch.global": 0.7226450405489707,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9928085774058577,
      "tokens_p.mean_in_band": 0.7260298295454546,
      "tokens_rate.above_band": 0.9157088122605364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0842911877394636
    },
    {
      "epoch": 0.9624335106382979,
      "grad_norm": 35.34862413943854,
      "learning_rate": 1.8184911261491501e-07,
      "loss": 0.2809,
      "step": 5790,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47368421052631576,
      "success_rate.epoch.env.math": 0.9125964010282777,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7836166924265843,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5148240977729844,
      "success_rate.epoch.global": 0.7228525121555915,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9941620879120879,
      "tokens_p.mean_in_band": 0.70751953125,
      "tokens_rate.above_band": 0.9191919191919192,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08080808080808081
    },
    {
      "epoch": 0.9632646276595744,
      "grad_norm": 86.21827267420791,
      "learning_rate": 1.8182258111504903e-07,
      "loss": 0.3023,
      "step": 5795,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4742857142857143,
      "success_rate.epoch.env.math": 0.9126712328767124,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7838255163095927,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5149045668176064,
      "success_rate.epoch.global": 0.7230941704035875,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9926282051282052,
      "tokens_p.mean_in_band": 0.6912286931818182,
      "tokens_rate.above_band": 0.8986175115207373,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10138248847926268
    },
    {
      "epoch": 0.964095744680851,
      "grad_norm": 82.54379671555498,
      "learning_rate": 1.8179604638054806e-07,
      "loss": 0.4659,
      "step": 5800,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4737442922374429,
      "success_rate.epoch.env.math": 0.9126712328767124,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7839089330503569,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5148629299714694,
      "success_rate.epoch.global": 0.7230730917693936,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9996764053254438,
      "tokens_p.mean_in_band": 0.5701593137254902,
      "tokens_rate.above_band": 0.9298486932599724,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07015130674002751
    },
    {
      "epoch": 0.9649268617021277,
      "grad_norm": 377.4709246861495,
      "learning_rate": 1.8176950845850482e-07,
      "loss": 0.3708,
      "step": 5805,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47434435575826683,
      "success_rate.epoch.env.math": 0.9127459366980325,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7839922854387656,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5149318499469742,
      "success_rate.epoch.global": 0.7232109520846297,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9914089347079038,
      "tokens_p.mean_in_band": 0.689203789893617,
      "tokens_rate.above_band": 0.8919540229885058,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10804597701149425
    },
    {
      "epoch": 0.9657579787234043,
      "grad_norm": 74.345270079809,
      "learning_rate": 1.817429673960175e-07,
      "loss": 0.3647,
      "step": 5810,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47554038680318544,
      "success_rate.epoch.env.math": 0.9128205128205128,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7840755735492577,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5150549313358733,
      "success_rate.epoch.global": 0.7233830845771144,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9932036247334755,
      "tokens_p.mean_in_band": 0.8349826388888889,
      "tokens_rate.above_band": 0.9542217700915565,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04577822990844354
    },
    {
      "epoch": 0.9665890957446809,
      "grad_norm": 130.62739845741018,
      "learning_rate": 1.8171642324019013e-07,
      "loss": 0.4013,
      "step": 5815,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47613636363636364,
      "success_rate.epoch.env.math": 0.9128949615713066,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7840077071290944,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151097094416741,
      "success_rate.epoch.global": 0.723430702299565,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9964710252600297,
      "tokens_p.mean_in_band": 0.599609375,
      "tokens_rate.above_band": 0.9492242595204513,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05077574047954866
    },
    {
      "epoch": 0.9674202127659575,
      "grad_norm": 132.90832053608324,
      "learning_rate": 1.8168987603813198e-07,
      "loss": 0.3129,
      "step": 5820,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47613636363636364,
      "success_rate.epoch.env.math": 0.9129692832764505,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.784298633827208,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151429138419702,
      "success_rate.epoch.global": 0.7237054513845772,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9918893129770993,
      "tokens_p.mean_in_band": 0.57861328125,
      "tokens_rate.above_band": 0.891156462585034,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10884353741496598
    },
    {
      "epoch": 0.968251329787234,
      "grad_norm": 169.92809722242012,
      "learning_rate": 1.8166332583695788e-07,
      "loss": 0.4216,
      "step": 5825,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47678369195922987,
      "success_rate.epoch.env.math": 0.9130434782608695,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.784340130819546,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5152122793237542,
      "success_rate.epoch.global": 0.7237870703561236,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6944444444444443,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9987476518472135,
      "tokens_p.mean_in_band": 0.6583136792452831,
      "tokens_rate.above_band": 0.9890586292320397,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010941370767960363
    },
    {
      "epoch": 0.9690824468085106,
      "grad_norm": 317.9623634523537,
      "learning_rate": 1.816367726837879e-07,
      "loss": 0.3503,
      "step": 5830,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4768361581920904,
      "success_rate.epoch.env.math": 0.9130434782608695,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7841214917339485,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151971727007781,
      "success_rate.epoch.global": 0.723620582765034,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.5,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9951388888888889,
      "tokens_p.mean_below_band": 8.458683753431728e-11,
      "tokens_p.mean_in_band": 0.5410610465116279,
      "tokens_rate.above_band": 0.9375,
      "tokens_rate.below_band": 0.002777777777777778,
      "tokens_rate.in_band": 0.059722222222222225
    },
    {
      "epoch": 0.9699135638297872,
      "grad_norm": 146.56793898190534,
      "learning_rate": 1.816102166257474e-07,
      "loss": 0.5242,
      "step": 5835,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4762979683972912,
      "success_rate.epoch.env.math": 0.9131175468483816,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7841629828944839,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151587517874371,
      "success_rate.epoch.global": 0.7235994050570154,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9996357808857809,
      "tokens_p.mean_in_band": 0.6042374320652174,
      "tokens_rate.above_band": 0.9491150442477876,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05088495575221239
    },
    {
      "epoch": 0.9707446808510638,
      "grad_norm": 48.895591592111934,
      "learning_rate": 1.8158365770996686e-07,
      "loss": 0.4177,
      "step": 5840,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47576099210823,
      "success_rate.epoch.env.math": 0.9131175468483816,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7842873607376104,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151212428378066,
      "success_rate.epoch.global": 0.7236124876114965,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965538259564891,
      "tokens_p.mean_in_band": 0.5791713169642857,
      "tokens_rate.above_band": 0.9596832253419726,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040316774658027354
    },
    {
      "epoch": 0.9715757978723404,
      "grad_norm": 98.08989534898663,
      "learning_rate": 1.8155709598358187e-07,
      "loss": 0.41,
      "step": 5845,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47576099210823,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7841367390051853,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151209826143195,
      "success_rate.epoch.global": 0.7235913312693498,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994098712446352,
      "tokens_p.mean_in_band": 0.6375177556818182,
      "tokens_rate.above_band": 0.9137254901960784,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08627450980392157
    },
    {
      "epoch": 0.972406914893617,
      "grad_norm": 65.55318611287204,
      "learning_rate": 1.81530531493733e-07,
      "loss": 0.3725,
      "step": 5850,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47635135135135137,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7843438219493477,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5151934773586181,
      "success_rate.epoch.global": 0.723796559831704,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9938063063063063,
      "tokens_p.mean_in_band": 0.569921875,
      "tokens_rate.above_band": 0.943342776203966,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056657223796033995
    },
    {
      "epoch": 0.9732380319148937,
      "grad_norm": 71.79185250514684,
      "learning_rate": 1.8150396428756568e-07,
      "loss": 0.3341,
      "step": 5855,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769403824521935,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7845092024539877,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5152620602318437,
      "success_rate.epoch.global": 0.7239673509769973,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964064774381368,
      "tokens_p.mean_in_band": 0.76171875,
      "tokens_rate.above_band": 0.9870689655172413,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01293103448275862
    },
    {
      "epoch": 0.9740691489361702,
      "grad_norm": 61.65205173501351,
      "learning_rate": 1.8147739441223021e-07,
      "loss": 0.5612,
      "step": 5860,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769403824521935,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7846330714696302,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5152733210514476,
      "success_rate.epoch.global": 0.7240697243169737,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9909206081081081,
      "tokens_p.mean_in_band": 0.7307942708333334,
      "tokens_rate.above_band": 0.925,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.075
    },
    {
      "epoch": 0.9749002659574468,
      "grad_norm": 118.51365042509147,
      "learning_rate": 1.8145082191488162e-07,
      "loss": 0.2667,
      "step": 5865,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4702702702702703,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769403824521935,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10510510510510511,
      "success_rate.epoch.env.science": 0.7847155717295538,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.515280821075077,
      "success_rate.epoch.global": 0.7241379310344828,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9979727056962026,
      "tokens_p.mean_in_band": 0.51591796875,
      "tokens_rate.above_band": 0.9693251533742331,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03067484662576687
    },
    {
      "epoch": 0.9757313829787234,
      "grad_norm": 81.44347307064916,
      "learning_rate": 1.8142424684267953e-07,
      "loss": 0.3328,
      "step": 5870,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769403824521935,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7848392036753445,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5155223624661666,
      "success_rate.epoch.global": 0.7241847826086957,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960841523341524,
      "tokens_p.mean_in_band": 0.7125,
      "tokens_rate.above_band": 0.9531615925058547,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0468384074941452
    },
    {
      "epoch": 0.9765625,
      "grad_norm": 149.1031706418972,
      "learning_rate": 1.8139766924278824e-07,
      "loss": 0.3841,
      "step": 5875,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769403824521935,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7850860420650095,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5155448023197725,
      "success_rate.epoch.global": 0.7243890397432733,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.7777777777777778,
      "tokens_p.mean_above_band": 0.9942306307603687,
      "tokens_p.mean_in_band": 0.5265157418952618,
      "tokens_rate.above_band": 0.8964626904208624,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10353730957913762
    },
    {
      "epoch": 0.9773936170212766,
      "grad_norm": 61.66881901678859,
      "learning_rate": 1.8137108916237645e-07,
      "loss": 0.5179,
      "step": 5880,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769403824521935,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7852502865876958,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5155597336400166,
      "success_rate.epoch.global": 0.7245250431778929,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9863696808510638,
      "tokens_p.mean_in_band": 0.7795138888888888,
      "tokens_rate.above_band": 0.912621359223301,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08737864077669903
    },
    {
      "epoch": 0.9782247340425532,
      "grad_norm": 72.2111997471744,
      "learning_rate": 1.813445066486173e-07,
      "loss": 0.4135,
      "step": 5885,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47752808988764045,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7852913085004776,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5156168908534919,
      "success_rate.epoch.global": 0.724592994573261,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988295880149812,
      "tokens_p.mean_in_band": 0.6165865384615384,
      "tokens_rate.above_band": 0.9535714285714286,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04642857142857143
    },
    {
      "epoch": 0.9790558510638298,
      "grad_norm": 66.40379563122467,
      "learning_rate": 1.8131792174868823e-07,
      "loss": 0.3098,
      "step": 5890,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769921436588103,
      "success_rate.epoch.env.math": 0.9132653061224489,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7854961832061069,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5155867934422919,
      "success_rate.epoch.global": 0.7246734039930983,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9982212160413971,
      "tokens_p.mean_in_band": 0.7091346153846154,
      "tokens_rate.above_band": 0.967459324155194,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03254067584480601
    },
    {
      "epoch": 0.9798869680851063,
      "grad_norm": 121.02380918566524,
      "learning_rate": 1.8129133450977095e-07,
      "loss": 0.3252,
      "step": 5895,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4769921436588103,
      "success_rate.epoch.env.math": 0.9134860050890585,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7853872567722243,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5155969545816307,
      "success_rate.epoch.global": 0.7247197930779653,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9862753378378378,
      "tokens_p.mean_in_band": 0.7822265625,
      "tokens_rate.above_band": 0.9487179487179487,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05128205128205128
    },
    {
      "epoch": 0.980718085106383,
      "grad_norm": 124.96733330899657,
      "learning_rate": 1.8126474497905126e-07,
      "loss": 0.3787,
      "step": 5900,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47757847533632286,
      "success_rate.epoch.env.math": 0.9135593220338983,
      "success_rate.epoch.env.sat": 0.10479041916167664,
      "success_rate.epoch.env.science": 0.7855100095328885,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5156680819800867,
      "success_rate.epoch.global": 0.7248892171344166,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9916424418604651,
      "tokens_p.mean_in_band": 0.8375,
      "tokens_rate.above_band": 0.9717514124293786,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02824858757062147
    },
    {
      "epoch": 0.9815492021276596,
      "grad_norm": 177.3154196555142,
      "learning_rate": 1.812381532037191e-07,
      "loss": 0.5138,
      "step": 5905,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47757847533632286,
      "success_rate.epoch.env.math": 0.9135593220338983,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7855917667238422,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5159184478524905,
      "success_rate.epoch.global": 0.7249907715023994,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9971289752650176,
      "tokens_p.mean_in_band": 0.7462827620967742,
      "tokens_rate.above_band": 0.9647727272727272,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.035227272727272725
    },
    {
      "epoch": 0.9823803191489362,
      "grad_norm": 58.090451073990245,
      "learning_rate": 1.8121155923096835e-07,
      "loss": 0.4662,
      "step": 5910,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47757847533632286,
      "success_rate.epoch.env.math": 0.9135593220338983,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7857958872810358,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5159370042667809,
      "success_rate.epoch.global": 0.7251598622725037,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9977570156502968,
      "tokens_p.mean_in_band": 0.7930871212121212,
      "tokens_rate.above_band": 0.9825026511134677,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017497348886532343
    },
    {
      "epoch": 0.9832114361702128,
      "grad_norm": 131.82925285618356,
      "learning_rate": 1.8118496310799674e-07,
      "loss": 0.3389,
      "step": 5915,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47704367301231804,
      "success_rate.epoch.env.math": 0.9137055837563451,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7859181731684111,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5159127992927642,
      "success_rate.epoch.global": 0.7252396166134185,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9986370716510904,
      "tokens_p.mean_in_band": 0.6609375,
      "tokens_rate.above_band": 0.9771689497716894,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0228310502283105
    },
    {
      "epoch": 0.9840425531914894,
      "grad_norm": 107.69429716799668,
      "learning_rate": 1.8115836488200594e-07,
      "loss": 0.3317,
      "step": 5920,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47704367301231804,
      "success_rate.epoch.env.math": 0.9137055837563451,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.785958904109589,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5159165021055986,
      "success_rate.epoch.global": 0.7252733751075071,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994140625,
      "tokens_p.mean_in_band": 0.7204241071428571,
      "tokens_rate.above_band": 0.973384030418251,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026615969581749048
    },
    {
      "epoch": 0.984873670212766,
      "grad_norm": 45.90095468635324,
      "learning_rate": 1.8113176460020125e-07,
      "loss": 0.3998,
      "step": 5925,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47704367301231804,
      "success_rate.epoch.env.math": 0.9139966273187183,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7860810039931546,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5159540606006839,
      "success_rate.epoch.global": 0.7255094524920206,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9911684782608695,
      "tokens_p.mean_in_band": 0.83125,
      "tokens_rate.above_band": 0.965034965034965,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03496503496503497
    },
    {
      "epoch": 0.9857047872340425,
      "grad_norm": 90.68505092317156,
      "learning_rate": 1.8110516230979167e-07,
      "loss": 0.2451,
      "step": 5930,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47762863534675615,
      "success_rate.epoch.env.math": 0.9139966273187183,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7862841945288754,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5160257108616075,
      "success_rate.epoch.global": 0.725711481844946,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994381051175657,
      "tokens_p.mean_in_band": 0.5784505208333334,
      "tokens_rate.above_band": 0.9678714859437751,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0321285140562249
    },
    {
      "epoch": 0.9865359042553191,
      "grad_norm": 68.6277486779169,
      "learning_rate": 1.8107855805798974e-07,
      "loss": 0.3264,
      "step": 5935,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4782122905027933,
      "success_rate.epoch.env.math": 0.9140690817186183,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7864059236757167,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.516096423470951,
      "success_rate.epoch.global": 0.7258796126026725,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967196132596685,
      "tokens_p.mean_in_band": 0.640869140625,
      "tokens_rate.above_band": 0.9826275787187839,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01737242128121607
    },
    {
      "epoch": 0.9873670212765957,
      "grad_norm": 120.3988100624948,
      "learning_rate": 1.810519518920115e-07,
      "loss": 0.3988,
      "step": 5940,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4782122905027933,
      "success_rate.epoch.env.math": 0.9141414141414141,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.786486999430632,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5161103696689247,
      "success_rate.epoch.global": 0.7259803921568627,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9910954301075269,
      "tokens_p.mean_in_band": 0.7744140625,
      "tokens_rate.above_band": 0.9789473684210527,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021052631578947368
    },
    {
      "epoch": 0.9881981382978723,
      "grad_norm": 81.62728703919721,
      "learning_rate": 1.8102534385907637e-07,
      "loss": 0.4603,
      "step": 5945,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4731182795698925,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4782122905027933,
      "success_rate.epoch.env.math": 0.9142136248948697,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.786608497723824,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5161279795822563,
      "success_rate.epoch.global": 0.7261146496815286,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9939365671641791,
      "tokens_p.mean_in_band": 0.6722470238095238,
      "tokens_rate.above_band": 0.9054054054054054,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0945945945945946
    },
    {
      "epoch": 0.989029255319149,
      "grad_norm": 128.11085635184202,
      "learning_rate": 1.809987340064071e-07,
      "loss": 0.4587,
      "step": 5950,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47593582887700536,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4782122905027933,
      "success_rate.epoch.env.math": 0.9144295302013423,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7867298578199052,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5164147809194988,
      "success_rate.epoch.global": 0.7263492840533594,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9964102176541717,
      "tokens_p.mean_in_band": 0.609375,
      "tokens_rate.above_band": 0.9605110336817654,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03948896631823461
    },
    {
      "epoch": 0.9898603723404256,
      "grad_norm": 74.15362753893264,
      "learning_rate": 1.809721223812296e-07,
      "loss": 0.2818,
      "step": 5955,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47593582887700536,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4782122905027933,
      "success_rate.epoch.env.math": 0.9144295302013423,
      "success_rate.epoch.env.sat": 0.10746268656716418,
      "success_rate.epoch.env.science": 0.7868106878908471,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5164221291077662,
      "success_rate.epoch.global": 0.7264162486235165,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.992870145631068,
      "tokens_p.mean_in_band": 0.7682291666666666,
      "tokens_rate.above_band": 0.9856459330143541,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014354066985645933
    },
    {
      "epoch": 0.9906914893617021,
      "grad_norm": 137.5463715068484,
      "learning_rate": 1.8094550903077308e-07,
      "loss": 0.3272,
      "step": 5960,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4787234042553192,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.4782122905027933,
      "success_rate.epoch.env.math": 0.9144295302013423,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.786891456715287,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5166538122694431,
      "success_rate.epoch.global": 0.7264277852513147,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986111111111111,
      "tokens_p.mean_in_band": 0.6121199324324325,
      "tokens_rate.above_band": 0.96051227321238,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03948772678762007
    },
    {
      "epoch": 0.9915226063829787,
      "grad_norm": 112.61926576065476,
      "learning_rate": 1.8091889400226964e-07,
      "loss": 0.4744,
      "step": 5965,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4787234042553192,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47767857142857145,
      "success_rate.epoch.env.math": 0.914501257334451,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.78697216436281,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5166191500609348,
      "success_rate.epoch.global": 0.7264393105977265,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9989551671732523,
      "tokens_p.mean_in_band": 0.6417410714285714,
      "tokens_rate.above_band": 0.9591836734693877,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04081632653061224
    },
    {
      "epoch": 0.9923537234042553,
      "grad_norm": 52.42686366849415,
      "learning_rate": 1.8089227734295448e-07,
      "loss": 0.419,
      "step": 5970,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47714604236343366,
      "success_rate.epoch.env.math": 0.9146443514644351,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.787052810902896,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5163319093530491,
      "success_rate.epoch.global": 0.7263067904250122,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9974769319492502,
      "tokens_p.mean_in_band": 0.6024169921875,
      "tokens_rate.above_band": 0.96440489432703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.035595105672969966
    },
    {
      "epoch": 0.9931848404255319,
      "grad_norm": 116.20765040075962,
      "learning_rate": 1.8086565910006565e-07,
      "loss": 0.4298,
      "step": 5975,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5126903553299492,
      "success_rate.epoch.env.logic": 0.47714604236343366,
      "success_rate.epoch.env.math": 0.9147157190635451,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7872139209381501,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5163530436834459,
      "success_rate.epoch.global": 0.7264738191138777,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9762414383561644,
      "tokens_p.mean_in_band": 0.833984375,
      "tokens_rate.above_band": 0.9733333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02666666666666667
    },
    {
      "epoch": 0.9940159574468085,
      "grad_norm": 51.800890905158255,
      "learning_rate": 1.8083903932084396e-07,
      "loss": 0.3847,
      "step": 5980,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47714604236343366,
      "success_rate.epoch.env.math": 0.9147157190635451,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7873747873747874,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.516591409706919,
      "success_rate.epoch.global": 0.7266406440595267,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9980273046092184,
      "tokens_p.mean_in_band": 0.6154119318181818,
      "tokens_rate.above_band": 0.967992240543162,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03200775945683802
    },
    {
      "epoch": 0.9948470744680851,
      "grad_norm": 60.096989962830364,
      "learning_rate": 1.8081241805253304e-07,
      "loss": 0.3745,
      "step": 5985,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.477728285077951,
      "success_rate.epoch.env.math": 0.9147869674185464,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7874551294162101,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5166581218079136,
      "success_rate.epoch.global": 0.726773957571324,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.8666666666666667,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9906572164948454,
      "tokens_p.mean_below_band": 5.400124791776761e-13,
      "tokens_p.mean_in_band": 0.6814453125,
      "tokens_rate.above_band": 0.9023255813953488,
      "tokens_rate.below_band": 0.004651162790697674,
      "tokens_rate.in_band": 0.09302325581395349
    },
    {
      "epoch": 0.9956781914893617,
      "grad_norm": 66.08985378757245,
      "learning_rate": 1.8078579534237912e-07,
      "loss": 0.3686,
      "step": 5990,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47888888888888886,
      "success_rate.epoch.env.math": 0.9147869674185464,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7875354107648725,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5167709295496954,
      "success_rate.epoch.global": 0.7269071411162564,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9998439450686641,
      "tokens_p.mean_in_band": 0.6608072916666666,
      "tokens_rate.above_band": 0.9709090909090909,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02909090909090909
    },
    {
      "epoch": 0.9965093085106383,
      "grad_norm": 41.40777159785019,
      "learning_rate": 1.8075917123763099e-07,
      "loss": 0.3019,
      "step": 5995,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4789473684210526,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47888888888888886,
      "success_rate.epoch.env.math": 0.9147869674185464,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7876957916588035,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5170361361973779,
      "success_rate.epoch.global": 0.7270734380708805,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9951978211009175,
      "tokens_p.mean_in_band": 0.82470703125,
      "tokens_rate.above_band": 0.9819819819819819,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018018018018018018
    },
    {
      "epoch": 0.9973404255319149,
      "grad_norm": 131.32301301341676,
      "learning_rate": 1.8073254578553986e-07,
      "loss": 0.3805,
      "step": 6000,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4789473684210526,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47888888888888886,
      "success_rate.epoch.env.math": 0.9148580968280468,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7877758913412564,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5170498842966463,
      "success_rate.epoch.global": 0.7271731190650109,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9977859311740891,
      "tokens_p.mean_in_band": 0.671875,
      "tokens_rate.above_band": 0.9801587301587301,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01984126984126984
    },
    {
      "epoch": 0.9981715425531915,
      "grad_norm": 86.19276176012748,
      "learning_rate": 1.8070591903335947e-07,
      "loss": 0.2964,
      "step": 6005,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4789473684210526,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47888888888888886,
      "success_rate.epoch.env.math": 0.9150707743547044,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7880158281514981,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5170910310545463,
      "success_rate.epoch.global": 0.7274717256475739,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9890625,
      "tokens_p.mean_in_band": 0.7578125,
      "tokens_rate.above_band": 0.9302325581395349,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06976744186046512
    },
    {
      "epoch": 0.9990026595744681,
      "grad_norm": 145.82618237619,
      "learning_rate": 1.8067929102834572e-07,
      "loss": 0.4313,
      "step": 6010,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4789473684210526,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47888888888888886,
      "success_rate.epoch.env.math": 0.9152119700748129,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7882153614457831,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5171220064194911,
      "success_rate.epoch.global": 0.7277035236938032,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.995042768273717,
      "tokens_p.mean_in_band": 0.6756036931818182,
      "tokens_rate.above_band": 0.9669172932330827,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03308270676691729
    },
    {
      "epoch": 0.9998337765957447,
      "grad_norm": 112.2731779726927,
      "learning_rate": 1.8065266181775683e-07,
      "loss": 0.4546,
      "step": 6015,
      "success_rate.epoch.env.abd": 0.46938775510204084,
      "success_rate.epoch.env.agentgym:alfworld": 0.4789473684210526,
      "success_rate.epoch.env.agentgym:sciworld": 0.2857142857142857,
      "success_rate.epoch.env.agentgym:textcraft": 0.4,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.47888888888888886,
      "success_rate.epoch.env.math": 0.9152119700748129,
      "success_rate.epoch.env.sat": 0.10682492581602374,
      "success_rate.epoch.env.science": 0.7883747178329571,
      "success_rate.epoch.env.webshop": 0.25,
      "success_rate.epoch.env_macro_mean": 0.5171364933637798,
      "success_rate.epoch.global": 0.7278358027690066,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9983678343949045,
      "tokens_p.mean_in_band": 0.6527157738095238,
      "tokens_rate.above_band": 0.9739454094292804,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026054590570719603
    },
    {
      "epoch": 1.0006648936170213,
      "grad_norm": 81.4455954098103,
      "learning_rate": 1.8062603144885308e-07,
      "loss": 0.4109,
      "step": 6020,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9953100315955766,
      "tokens_p.mean_in_band": 0.7556818181818182,
      "tokens_rate.above_band": 0.9829192546583851,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017080745341614908
    },
    {
      "epoch": 1.001496010638298,
      "grad_norm": 86.29712614751085,
      "learning_rate": 1.8059939996889688e-07,
      "loss": 0.3937,
      "step": 6025,
      "success_rate.epoch.env.logic": 0.3333333333333333,
      "success_rate.epoch.env.science": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6666666666666666,
      "success_rate.epoch.global": 0.8,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9960842148087876,
      "tokens_p.mean_in_band": 0.5748355263157895,
      "tokens_rate.above_band": 0.9700078926598263,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02999210734017364
    },
    {
      "epoch": 1.0023271276595744,
      "grad_norm": 86.52106065074864,
      "learning_rate": 1.8057276742515258e-07,
      "loss": 0.4293,
      "step": 6030,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.science": 0.8125,
      "success_rate.epoch.env_macro_mean": 0.65625,
      "success_rate.epoch.global": 0.75,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9908088235294118,
      "tokens_p.mean_below_band": 1.9326762412674725e-10,
      "tokens_p.mean_in_band": 0.740625,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.009259259259259259,
      "tokens_rate.in_band": 0.046296296296296294
    },
    {
      "epoch": 1.0031582446808511,
      "grad_norm": 50.01992623125245,
      "learning_rate": 1.8054613386488646e-07,
      "loss": 0.3652,
      "step": 6035,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.science": 0.875,
      "success_rate.epoch.env_macro_mean": 0.7916666666666666,
      "success_rate.epoch.global": 0.8333333333333334,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9872047244094488,
      "tokens_p.mean_in_band": 0.7990451388888888,
      "tokens_rate.above_band": 0.9338235294117647,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0661764705882353
    },
    {
      "epoch": 1.0039893617021276,
      "grad_norm": 82.87358076532286,
      "learning_rate": 1.805194993353665e-07,
      "loss": 0.5079,
      "step": 6040,
      "success_rate.epoch.env.ded": 1.0,
      "success_rate.epoch.env.logic": 0.4,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.9,
      "success_rate.epoch.env_macro_mean": 0.6599999999999999,
      "success_rate.epoch.global": 0.825,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995078125,
      "tokens_p.mean_in_band": 0.6329571759259259,
      "tokens_rate.above_band": 0.936768149882904,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06323185011709602
    },
    {
      "epoch": 1.0048204787234043,
      "grad_norm": 57.394727477190806,
      "learning_rate": 1.804928638838625e-07,
      "loss": 0.3625,
      "step": 6045,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.4,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.9166666666666666,
      "success_rate.epoch.env_macro_mean": 0.5966666666666666,
      "success_rate.epoch.global": 0.82,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9909754224270353,
      "tokens_p.mean_in_band": 0.6451198630136986,
      "tokens_rate.above_band": 0.8168130489335006,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18318695106649938
    },
    {
      "epoch": 1.0056515957446808,
      "grad_norm": 168.9779189069824,
      "learning_rate": 1.8046622755764583e-07,
      "loss": 0.4283,
      "step": 6050,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.3333333333333333,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0,
      "success_rate.epoch.env.science": 0.9302325581395349,
      "success_rate.epoch.env_macro_mean": 0.6027131782945736,
      "success_rate.epoch.global": 0.8333333333333334,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992829106280193,
      "tokens_p.mean_in_band": 0.4835069444444444,
      "tokens_rate.above_band": 0.9787234042553191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02127659574468085
    },
    {
      "epoch": 1.0064827127659575,
      "grad_norm": 62.9512422906743,
      "learning_rate": 1.804395904039895e-07,
      "loss": 0.3133,
      "step": 6055,
      "success_rate.epoch.env.agentgym:alfworld": 1.0,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.42857142857142855,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.9375,
      "success_rate.epoch.env_macro_mean": 0.7784863945578232,
      "success_rate.epoch.global": 0.8571428571428571,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9963942307692307,
      "tokens_p.mean_in_band": 0.7440011160714286,
      "tokens_rate.above_band": 0.9780564263322884,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0219435736677116
    },
    {
      "epoch": 1.007313829787234,
      "grad_norm": 107.14793771797173,
      "learning_rate": 1.8041295247016785e-07,
      "loss": 0.3398,
      "step": 6060,
      "success_rate.epoch.env.agentgym:alfworld": 1.0,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.375,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.9464285714285714,
      "success_rate.epoch.env_macro_mean": 0.772108843537415,
      "success_rate.epoch.global": 0.8625,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963235294117647,
      "tokens_p.mean_in_band": 0.7119891826923077,
      "tokens_rate.above_band": 0.9622641509433962,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03773584905660377
    },
    {
      "epoch": 1.0081449468085106,
      "grad_norm": 69.63853529149704,
      "learning_rate": 1.803863138034568e-07,
      "loss": 0.492,
      "step": 6065,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.375,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.9516129032258065,
      "success_rate.epoch.env_macro_mean": 0.7252304147465438,
      "success_rate.epoch.global": 0.8666666666666667,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994745575221239,
      "tokens_p.mean_in_band": 0.8005642361111112,
      "tokens_rate.above_band": 0.9617021276595744,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03829787234042553
    },
    {
      "epoch": 1.0089760638297873,
      "grad_norm": 36.047487996641635,
      "learning_rate": 1.8035967445113334e-07,
      "loss": 0.2962,
      "step": 6070,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.375,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.3333333333333333,
      "success_rate.epoch.env.science": 0.9420289855072463,
      "success_rate.epoch.env_macro_mean": 0.7238612836438924,
      "success_rate.epoch.global": 0.8686868686868687,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9792613636363636,
      "tokens_p.mean_in_band": 0.717092803030303,
      "tokens_rate.above_band": 0.7692307692307693,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.23076923076923078
    },
    {
      "epoch": 1.0098071808510638,
      "grad_norm": 26.297947848747945,
      "learning_rate": 1.8033303446047585e-07,
      "loss": 0.4284,
      "step": 6075,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.75,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.25,
      "success_rate.epoch.env.science": 0.9466666666666667,
      "success_rate.epoch.env_macro_mean": 0.7304761904761905,
      "success_rate.epoch.global": 0.8715596330275229,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9928977272727273,
      "tokens_p.mean_in_band": 0.7604166666666666,
      "tokens_rate.above_band": 0.9407894736842105,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05921052631578947
    },
    {
      "epoch": 1.0106382978723405,
      "grad_norm": 54.82936353437266,
      "learning_rate": 1.803063938787638e-07,
      "loss": 0.351,
      "step": 6080,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.8,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.2,
      "success_rate.epoch.env.science": 0.9382716049382716,
      "success_rate.epoch.env_macro_mean": 0.7292768959435626,
      "success_rate.epoch.global": 0.865546218487395,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99235807860262,
      "tokens_p.mean_in_band": 0.7141335227272727,
      "tokens_rate.above_band": 0.9123505976095617,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08764940239043825
    },
    {
      "epoch": 1.011469414893617,
      "grad_norm": 78.10722897562525,
      "learning_rate": 1.8027975275327767e-07,
      "loss": 0.3234,
      "step": 6085,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.8,
      "success_rate.epoch.env.logic": 0.45454545454545453,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.2,
      "success_rate.epoch.env.science": 0.9438202247191011,
      "success_rate.epoch.env_macro_mean": 0.7235760494187461,
      "success_rate.epoch.global": 0.8682170542635659,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972826086956522,
      "tokens_p.mean_in_band": 0.6544596354166666,
      "tokens_rate.above_band": 0.9640718562874252,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03592814371257485
    },
    {
      "epoch": 1.0123005319148937,
      "grad_norm": 134.99715335078903,
      "learning_rate": 1.8025311113129895e-07,
      "loss": 0.5774,
      "step": 6090,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.8,
      "success_rate.epoch.env.logic": 0.42857142857142855,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.16666666666666666,
      "success_rate.epoch.env.science": 0.9473684210526315,
      "success_rate.epoch.env_macro_mean": 0.7156104547081991,
      "success_rate.epoch.global": 0.8561151079136691,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9997014331210191,
      "tokens_p.mean_in_band": 0.5558792372881356,
      "tokens_rate.above_band": 0.9551330798479087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044866920152091254
    },
    {
      "epoch": 1.0131316489361701,
      "grad_norm": 78.76696622476783,
      "learning_rate": 1.8022646906010995e-07,
      "loss": 0.3835,
      "step": 6095,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.42857142857142855,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9306930693069307,
      "success_rate.epoch.env_macro_mean": 0.6907792820098335,
      "success_rate.epoch.global": 0.8389261744966443,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9854878917378918,
      "tokens_p.mean_in_band": 0.7460039511494253,
      "tokens_rate.above_band": 0.8897338403041825,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11026615969581749
    },
    {
      "epoch": 1.0139627659574468,
      "grad_norm": 74.47510169912339,
      "learning_rate": 1.8019982658699388e-07,
      "loss": 0.352,
      "step": 6100,
      "success_rate.epoch.env.agentgym:alfworld": 0.75,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.4375,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9333333333333333,
      "success_rate.epoch.env_macro_mean": 0.7043367346938776,
      "success_rate.epoch.global": 0.8417721518987342,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9994179278230501,
      "tokens_p.mean_in_band": 0.7449776785714286,
      "tokens_rate.above_band": 0.983963344788087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016036655211912942
    },
    {
      "epoch": 1.0147938829787233,
      "grad_norm": 75.40758578290753,
      "learning_rate": 1.8017318375923458e-07,
      "loss": 0.4668,
      "step": 6105,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.47058823529411764,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9272727272727272,
      "success_rate.epoch.env_macro_mean": 0.6884230965113318,
      "success_rate.epoch.global": 0.8392857142857143,
      "success_rate.window.env.abd": 0.5,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.86,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988132911392406,
      "tokens_p.mean_below_band": 7.188646122813225e-09,
      "tokens_p.mean_in_band": 0.20199046415441177,
      "tokens_rate.above_band": 0.88268156424581,
      "tokens_rate.below_band": 0.0004297378599054577,
      "tokens_rate.in_band": 0.11688869789428448
    },
    {
      "epoch": 1.015625,
      "grad_norm": 470.57805880278977,
      "learning_rate": 1.801465406241165e-07,
      "loss": 0.2557,
      "step": 6110,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6666666666666666,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9316239316239316,
      "success_rate.epoch.env_macro_mean": 0.6926434676434676,
      "success_rate.epoch.global": 0.848314606741573,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.992602657004831,
      "tokens_p.mean_in_band": 0.87890625,
      "tokens_rate.above_band": 0.9904306220095693,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009569377990430622
    },
    {
      "epoch": 1.0164561170212767,
      "grad_norm": 106.38473771486551,
      "learning_rate": 1.8011989722892476e-07,
      "loss": 0.3066,
      "step": 6115,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.47368421052631576,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.936,
      "success_rate.epoch.env_macro_mean": 0.6779962406015038,
      "success_rate.epoch.global": 0.8457446808510638,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9931662515566625,
      "tokens_p.mean_in_band": 0.5221354166666666,
      "tokens_rate.above_band": 0.9083710407239819,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0916289592760181
    },
    {
      "epoch": 1.0172872340425532,
      "grad_norm": 313.3548378664921,
      "learning_rate": 1.8009325362094475e-07,
      "loss": 0.3481,
      "step": 6120,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9236641221374046,
      "success_rate.epoch.env_macro_mean": 0.6708151581243185,
      "success_rate.epoch.global": 0.8383838383838383,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9889705882352942,
      "tokens_p.mean_in_band": 0.6956313775510204,
      "tokens_rate.above_band": 0.8525576730190572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14744232698094284
    },
    {
      "epoch": 1.0181183510638299,
      "grad_norm": 73.79436235774392,
      "learning_rate": 1.8006660984746248e-07,
      "loss": 0.3822,
      "step": 6125,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.47619047619047616,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.927536231884058,
      "success_rate.epoch.env_macro_mean": 0.675267425810904,
      "success_rate.epoch.global": 0.8413461538461539,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9998553240740741,
      "tokens_p.mean_in_band": 0.5331307870370371,
      "tokens_rate.above_band": 0.9696969696969697,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030303030303030304
    },
    {
      "epoch": 1.0189494680851063,
      "grad_norm": 89.67487704445716,
      "learning_rate": 1.80039965955764e-07,
      "loss": 0.2539,
      "step": 6130,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.9310344827586207,
      "success_rate.epoch.env_macro_mean": 0.6695043103448276,
      "success_rate.epoch.global": 0.8394495412844036,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9932097615499255,
      "tokens_p.mean_in_band": 0.5382197342519685,
      "tokens_rate.above_band": 0.8408521303258145,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15914786967418545
    },
    {
      "epoch": 1.019780585106383,
      "grad_norm": 54.95808526334416,
      "learning_rate": 1.8001332199313574e-07,
      "loss": 0.3467,
      "step": 6135,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.9290322580645162,
      "success_rate.epoch.env_macro_mean": 0.6692540322580646,
      "success_rate.epoch.global": 0.8421052631578947,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9890086206896552,
      "tokens_p.mean_below_band": 4.172325134277344e-07,
      "tokens_p.mean_in_band": 0.6712239583333334,
      "tokens_rate.above_band": 0.9731543624161074,
      "tokens_rate.below_band": 0.006711409395973154,
      "tokens_rate.in_band": 0.020134228187919462
    },
    {
      "epoch": 1.0206117021276595,
      "grad_norm": 64.5118722245273,
      "learning_rate": 1.7998667800686425e-07,
      "loss": 0.347,
      "step": 6140,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.8,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9259259259259259,
      "success_rate.epoch.env_macro_mean": 0.6657407407407407,
      "success_rate.epoch.global": 0.8361344537815126,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9926321138211383,
      "tokens_p.mean_in_band": 0.57734375,
      "tokens_rate.above_band": 0.8601398601398601,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13986013986013987
    },
    {
      "epoch": 1.0214428191489362,
      "grad_norm": 161.87507300151358,
      "learning_rate": 1.7996003404423597e-07,
      "loss": 0.4571,
      "step": 6145,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9285714285714286,
      "success_rate.epoch.env_macro_mean": 0.6494047619047619,
      "success_rate.epoch.global": 0.8340080971659919,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9993191721132898,
      "tokens_p.mean_in_band": 0.6783854166666666,
      "tokens_rate.above_band": 0.9870967741935484,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012903225806451613
    },
    {
      "epoch": 1.0222739361702127,
      "grad_norm": 89.62905185994916,
      "learning_rate": 1.7993339015253752e-07,
      "loss": 0.414,
      "step": 6150,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.9310344827586207,
      "success_rate.epoch.env_macro_mean": 0.6433679467084639,
      "success_rate.epoch.global": 0.83203125,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9973233404710921,
      "tokens_p.mean_in_band": 0.6585286458333334,
      "tokens_rate.above_band": 0.9511201629327902,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.048879837067209775
    },
    {
      "epoch": 1.0231050531914894,
      "grad_norm": 85.80830560137224,
      "learning_rate": 1.7990674637905524e-07,
      "loss": 0.304,
      "step": 6155,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5185185185185185,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.9337016574585635,
      "success_rate.epoch.env_macro_mean": 0.6460161583607715,
      "success_rate.epoch.global": 0.8345864661654135,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940476190476191,
      "tokens_p.mean_in_band": 0.573046875,
      "tokens_rate.above_band": 0.9742268041237113,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02577319587628866
    },
    {
      "epoch": 1.023936170212766,
      "grad_norm": 57.54340260769104,
      "learning_rate": 1.7988010277107526e-07,
      "loss": 0.3435,
      "step": 6160,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5185185185185185,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.9312169312169312,
      "success_rate.epoch.env_macro_mean": 0.6457055675805676,
      "success_rate.epoch.global": 0.8369565217391305,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9819630872483222,
      "tokens_p.mean_in_band": 0.7358630952380952,
      "tokens_rate.above_band": 0.8764705882352941,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12352941176470589
    },
    {
      "epoch": 1.0247672872340425,
      "grad_norm": 74.82932852390653,
      "learning_rate": 1.7985345937588348e-07,
      "loss": 0.3236,
      "step": 6165,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.9336734693877551,
      "success_rate.epoch.env_macro_mean": 0.6436978200371057,
      "success_rate.epoch.global": 0.8385964912280702,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9989341746248295,
      "tokens_p.mean_in_band": 0.615625,
      "tokens_rate.above_band": 0.9734395750332006,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02656042496679947
    },
    {
      "epoch": 1.0255984042553192,
      "grad_norm": 265.49353350126614,
      "learning_rate": 1.7982681624076542e-07,
      "loss": 0.3662,
      "step": 6170,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5172413793103449,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9356435643564357,
      "success_rate.epoch.env_macro_mean": 0.6508341028068324,
      "success_rate.epoch.global": 0.8406779661016949,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9863398203592815,
      "tokens_p.mean_in_band": 0.8110795454545454,
      "tokens_rate.above_band": 0.9192660550458716,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08073394495412844
    },
    {
      "epoch": 1.0264295212765957,
      "grad_norm": 42.00687446440549,
      "learning_rate": 1.7980017341300612e-07,
      "loss": 0.4013,
      "step": 6175,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5172413793103449,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9330143540669856,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6893381791294677,
      "success_rate.epoch.global": 0.8426229508196721,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9962657232704403,
      "tokens_p.mean_in_band": 0.4541015625,
      "tokens_rate.above_band": 0.9298245614035088,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07017543859649122
    },
    {
      "epoch": 1.0272606382978724,
      "grad_norm": 38.88415792190259,
      "learning_rate": 1.7977353093989004e-07,
      "loss": 0.4684,
      "step": 6180,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5333333333333333,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9348837209302325,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6728153629316419,
      "success_rate.epoch.global": 0.8444444444444444,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9901706231454006,
      "tokens_p.mean_in_band": 0.4854589332460733,
      "tokens_rate.above_band": 0.6382575757575758,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.36174242424242425
    },
    {
      "epoch": 1.0280917553191489,
      "grad_norm": 167.1843122622322,
      "learning_rate": 1.7974688886870105e-07,
      "loss": 0.2353,
      "step": 6185,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5161290322580645,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9363636363636364,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.670355958259184,
      "success_rate.epoch.global": 0.8421052631578947,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9949462166172107,
      "tokens_p.mean_in_band": 0.5779513888888889,
      "tokens_rate.above_band": 0.9374130737134909,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06258692628650904
    },
    {
      "epoch": 1.0289228723404256,
      "grad_norm": 74.98156226040037,
      "learning_rate": 1.7972024724672232e-07,
      "loss": 0.4866,
      "step": 6190,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.9385964912280702,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.66820143793828,
      "success_rate.epoch.global": 0.8408408408408409,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9991444524495677,
      "tokens_p.mean_in_band": 0.6401909722222222,
      "tokens_rate.above_band": 0.9506849315068493,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049315068493150684
    },
    {
      "epoch": 1.029753989361702,
      "grad_norm": 60.056797413462895,
      "learning_rate": 1.796936061212362e-07,
      "loss": 0.4229,
      "step": 6195,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.625,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.9361702127659575,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6679318514424897,
      "success_rate.epoch.global": 0.8396501457725948,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943265007320644,
      "tokens_p.mean_below_band": 2.648448571562767e-09,
      "tokens_p.mean_in_band": 0.6730143229166666,
      "tokens_rate.above_band": 0.9646892655367232,
      "tokens_rate.below_band": 0.0014124293785310734,
      "tokens_rate.in_band": 0.03389830508474576
    },
    {
      "epoch": 1.0305851063829787,
      "grad_norm": 104.44929057153388,
      "learning_rate": 1.7966696553952414e-07,
      "loss": 0.3785,
      "step": 6200,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4722222222222222,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.9377593360995851,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6573059515659793,
      "success_rate.epoch.global": 0.8352272727272727,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9991003787878788,
      "tokens_p.mean_in_band": 0.5951171875,
      "tokens_rate.above_band": 0.9777777777777777,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022222222222222223
    },
    {
      "epoch": 1.0314162234042552,
      "grad_norm": 99.00103191760212,
      "learning_rate": 1.7964032554886666e-07,
      "loss": 0.4355,
      "step": 6205,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4594594594594595,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9397590361445783,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6555809551793488,
      "success_rate.epoch.global": 0.8342541436464088,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9946516973125884,
      "tokens_p.mean_in_band": 0.5326360887096774,
      "tokens_rate.above_band": 0.9579945799457995,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04200542005420054
    },
    {
      "epoch": 1.032247340425532,
      "grad_norm": 93.44815773226698,
      "learning_rate": 1.796136861965432e-07,
      "loss": 0.3163,
      "step": 6210,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.475,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9372549019607843,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6570294447745427,
      "success_rate.epoch.global": 0.8328840970350404,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7619047619047619,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942839951865222,
      "tokens_p.mean_below_band": 9.549694368615746e-12,
      "tokens_p.mean_in_band": 0.6758840460526315,
      "tokens_rate.above_band": 0.9551724137931035,
      "tokens_rate.below_band": 0.0011494252873563218,
      "tokens_rate.in_band": 0.04367816091954023
    },
    {
      "epoch": 1.0330784574468086,
      "grad_norm": 179.41227965376063,
      "learning_rate": 1.7958704752983215e-07,
      "loss": 0.301,
      "step": 6215,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4878048780487805,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9391634980988594,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.658201312276786,
      "success_rate.epoch.global": 0.8346456692913385,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9905711206896551,
      "tokens_p.mean_in_band": 0.7565104166666666,
      "tokens_rate.above_band": 0.928,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.072
    },
    {
      "epoch": 1.033909574468085,
      "grad_norm": 75.83439667964703,
      "learning_rate": 1.795604095960105e-07,
      "loss": 0.2932,
      "step": 6220,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4883720930232558,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.937037037037037,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6580280627115251,
      "success_rate.epoch.global": 0.8333333333333334,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9874387254901961,
      "tokens_p.mean_in_band": 0.6391059027777778,
      "tokens_rate.above_band": 0.9577464788732394,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04225352112676056
    },
    {
      "epoch": 1.0347406914893618,
      "grad_norm": 77.95757712974655,
      "learning_rate": 1.7953377244235416e-07,
      "loss": 0.4604,
      "step": 6225,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4883720930232558,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9347826086956522,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6573690739415674,
      "success_rate.epoch.global": 0.8316582914572864,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9870125145518044,
      "tokens_p.mean_in_band": 0.7482341609589042,
      "tokens_rate.above_band": 0.9216738197424893,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07832618025751073
    },
    {
      "epoch": 1.0355718085106382,
      "grad_norm": 59.45374740288453,
      "learning_rate": 1.795071361161375e-07,
      "loss": 0.488,
      "step": 6230,
      "success_rate.epoch.env.abd": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4666666666666667,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9363957597173145,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6551365989043533,
      "success_rate.epoch.global": 0.8308823529411765,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9928075396825397,
      "tokens_p.mean_in_band": 0.6340401785714286,
      "tokens_rate.above_band": 0.9557522123893806,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04424778761061947
    },
    {
      "epoch": 1.036402925531915,
      "grad_norm": 56.436265925759805,
      "learning_rate": 1.7948050066463348e-07,
      "loss": 0.3691,
      "step": 6235,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4666666666666667,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9342560553633218,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6734173724946504,
      "success_rate.epoch.global": 0.8321342925659473,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9905405405405405,
      "tokens_p.mean_below_band": 9.74978320300579e-10,
      "tokens_p.mean_in_band": 0.873046875,
      "tokens_rate.above_band": 0.9840425531914894,
      "tokens_rate.below_band": 0.005319148936170213,
      "tokens_rate.in_band": 0.010638297872340425
    },
    {
      "epoch": 1.0372340425531914,
      "grad_norm": 66.65812229181546,
      "learning_rate": 1.7945386613511354e-07,
      "loss": 0.4033,
      "step": 6240,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.4782608695652174,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9355932203389831,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6737318566916728,
      "success_rate.epoch.global": 0.8337236533957846,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950579073482428,
      "tokens_p.mean_in_band": 0.6744791666666666,
      "tokens_rate.above_band": 0.990506329113924,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00949367088607595
    },
    {
      "epoch": 1.038065159574468,
      "grad_norm": 76.09320827494683,
      "learning_rate": 1.794272325748474e-07,
      "loss": 0.3254,
      "step": 6245,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.5833333333333334,
      "success_rate.epoch.env.logic": 0.4791666666666667,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9364548494983278,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6781369915960709,
      "success_rate.epoch.global": 0.8348623853211009,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.0004812628336757,
      "tokens_p.mean_in_band": 0.73779296875,
      "tokens_rate.above_band": 0.9918533604887984,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008146639511201629
    },
    {
      "epoch": 1.0388962765957448,
      "grad_norm": 66.14419189038723,
      "learning_rate": 1.7940060003110311e-07,
      "loss": 0.3707,
      "step": 6250,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.46,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9375,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6796847433612139,
      "success_rate.epoch.global": 0.8337078651685393,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9970873257839721,
      "tokens_p.mean_in_band": 0.6041666666666666,
      "tokens_rate.above_band": 0.9795221843003413,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020477815699658702
    },
    {
      "epoch": 1.0397273936170213,
      "grad_norm": 95.2713935391227,
      "learning_rate": 1.7937396855114691e-07,
      "loss": 0.4349,
      "step": 6255,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46153846153846156,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.46,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9385113268608414,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6704731036884092,
      "success_rate.epoch.global": 0.832967032967033,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9975961538461539,
      "tokens_p.mean_in_band": 0.7001953125,
      "tokens_rate.above_band": 0.9896193771626297,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010380622837370242
    },
    {
      "epoch": 1.040558510638298,
      "grad_norm": 75.09997445156134,
      "learning_rate": 1.793473381822432e-07,
      "loss": 0.3879,
      "step": 6260,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.46153846153846156,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.9391025641025641,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6666836250169583,
      "success_rate.epoch.global": 0.8297413793103449,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9975609756097561,
      "tokens_p.mean_in_band": 0.5548023897058824,
      "tokens_rate.above_band": 0.9414466130884042,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05855338691159587
    },
    {
      "epoch": 1.0413896276595744,
      "grad_norm": 89.63266635755804,
      "learning_rate": 1.7932070897165428e-07,
      "loss": 0.5164,
      "step": 6265,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.4444444444444444,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.047619047619047616,
      "success_rate.epoch.env.science": 0.9365079365079365,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6604395604395604,
      "success_rate.epoch.global": 0.8185654008438819,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.3,
      "tokens_p.mean_above_band": 0.9976211776187378,
      "tokens_p.mean_in_band": 0.5923295454545454,
      "tokens_rate.above_band": 0.9522924411400248,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04770755885997522
    },
    {
      "epoch": 1.0422207446808511,
      "grad_norm": 81.12761027992248,
      "learning_rate": 1.7929408096664053e-07,
      "loss": 0.3965,
      "step": 6270,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.4444444444444444,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.047619047619047616,
      "success_rate.epoch.env.science": 0.934984520123839,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6644369586191051,
      "success_rate.epoch.global": 0.8198757763975155,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9942819148936171,
      "tokens_p.mean_below_band": 6.693881005048752e-10,
      "tokens_p.mean_in_band": 0.7464192708333334,
      "tokens_rate.above_band": 0.9730848861283644,
      "tokens_rate.below_band": 0.002070393374741201,
      "tokens_rate.in_band": 0.024844720496894408
    },
    {
      "epoch": 1.0430518617021276,
      "grad_norm": 79.21504409639203,
      "learning_rate": 1.7926745421446013e-07,
      "loss": 0.3663,
      "step": 6275,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.4642857142857143,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.047619047619047616,
      "success_rate.epoch.env.science": 0.9335347432024169,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6664804578324216,
      "success_rate.epoch.global": 0.821501014198783,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9934895833333334,
      "tokens_p.mean_below_band": 3.694822225952521e-13,
      "tokens_p.mean_in_band": 0.826171875,
      "tokens_rate.above_band": 0.9876543209876543,
      "tokens_rate.below_band": 0.00411522633744856,
      "tokens_rate.in_band": 0.00823045267489712
    },
    {
      "epoch": 1.0438829787234043,
      "grad_norm": 307.2952993639155,
      "learning_rate": 1.79240828762369e-07,
      "loss": 0.4458,
      "step": 6280,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47058823529411764,
      "success_rate.epoch.env.agentgym:textcraft": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.47368421052631576,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.045454545454545456,
      "success_rate.epoch.env.science": 0.9317507418397626,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6818735942777062,
      "success_rate.epoch.global": 0.8210735586481114,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7666666666666667,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.992853139013453,
      "tokens_p.mean_in_band": 0.6858974358974359,
      "tokens_rate.above_band": 0.9195876288659793,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08041237113402062
    },
    {
      "epoch": 1.0447140957446808,
      "grad_norm": 60.99663879620861,
      "learning_rate": 1.7921420465762087e-07,
      "loss": 0.463,
      "step": 6285,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47058823529411764,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.4915254237288136,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.045454545454545456,
      "success_rate.epoch.env.science": 0.9327485380116959,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6284112619859764,
      "success_rate.epoch.global": 0.8226120857699805,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9941683569979716,
      "tokens_p.mean_in_band": 0.700218023255814,
      "tokens_rate.above_band": 0.9197761194029851,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08022388059701492
    },
    {
      "epoch": 1.0455452127659575,
      "grad_norm": 47.09905959276588,
      "learning_rate": 1.7918758194746696e-07,
      "loss": 0.4526,
      "step": 6290,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47058823529411764,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.5081967213114754,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.043478260869565216,
      "success_rate.epoch.env.science": 0.9310344827586207,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.629853590624266,
      "success_rate.epoch.global": 0.8221797323135756,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9917332848837209,
      "tokens_p.mean_below_band": 7.566995918750763e-10,
      "tokens_p.mean_in_band": 0.7288411458333334,
      "tokens_rate.above_band": 0.9322493224932249,
      "tokens_rate.below_band": 0.0027100271002710027,
      "tokens_rate.in_band": 0.06504065040650407
    },
    {
      "epoch": 1.046376329787234,
      "grad_norm": 51.89258922885982,
      "learning_rate": 1.7916096067915603e-07,
      "loss": 0.3259,
      "step": 6295,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47058823529411764,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5161290322580645,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9323943661971831,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6304303931679188,
      "success_rate.epoch.global": 0.8236397748592871,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9924469899169632,
      "tokens_p.mean_below_band": 5.327165126800537e-07,
      "tokens_p.mean_in_band": 0.5034611600449775,
      "tokens_rate.above_band": 0.8344469190794358,
      "tokens_rate.below_band": 0.0004949269982677555,
      "tokens_rate.in_band": 0.16505815392229647
    },
    {
      "epoch": 1.0472074468085106,
      "grad_norm": 59.66471598390848,
      "learning_rate": 1.7913434089993435e-07,
      "loss": 0.31,
      "step": 6300,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47058823529411764,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5238095238095238,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.08,
      "success_rate.epoch.env.science": 0.9279778393351801,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6261898813080172,
      "success_rate.epoch.global": 0.8195211786372008,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.993120884289746,
      "tokens_p.mean_in_band": 0.6705643503289473,
      "tokens_rate.above_band": 0.8748971193415638,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12510288065843622
    },
    {
      "epoch": 1.0480385638297873,
      "grad_norm": 77.71552600905194,
      "learning_rate": 1.791077226570455e-07,
      "loss": 0.3766,
      "step": 6305,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5303030303030303,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.08,
      "success_rate.epoch.env.science": 0.9291553133514986,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6241373468258118,
      "success_rate.epoch.global": 0.8191681735985533,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967592592592592,
      "tokens_p.mean_in_band": 0.5816200657894737,
      "tokens_rate.above_band": 0.9827115559599636,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017288444040036398
    },
    {
      "epoch": 1.0488696808510638,
      "grad_norm": 39.880896829744565,
      "learning_rate": 1.7908110599773035e-07,
      "loss": 0.4901,
      "step": 6310,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5373134328358209,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.93048128342246,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6247217301065705,
      "success_rate.epoch.global": 0.8206039076376554,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9918478260869565,
      "tokens_p.mean_in_band": 0.7622282608695652,
      "tokens_rate.above_band": 0.9230769230769231,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07692307692307693
    },
    {
      "epoch": 1.0497007978723405,
      "grad_norm": 32.31999004305457,
      "learning_rate": 1.7905449096922691e-07,
      "loss": 0.2728,
      "step": 6315,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5441176470588235,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9315789473684211,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6255997165697887,
      "success_rate.epoch.global": 0.8237347294938918,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9911202185792349,
      "tokens_p.mean_in_band": 0.82578125,
      "tokens_rate.above_band": 0.973404255319149,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026595744680851064
    },
    {
      "epoch": 1.050531914893617,
      "grad_norm": 56.92973727992401,
      "learning_rate": 1.790278776187704e-07,
      "loss": 0.2816,
      "step": 6320,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5362318840579711,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9305912596401028,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6246137775998809,
      "success_rate.epoch.global": 0.823327615780446,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963037634408602,
      "tokens_p.mean_in_band": 0.6315569196428571,
      "tokens_rate.above_band": 0.9587628865979382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041237113402061855
    },
    {
      "epoch": 1.0513630319148937,
      "grad_norm": 57.56350150387045,
      "learning_rate": 1.790012659935929e-07,
      "loss": 0.2943,
      "step": 6325,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5362318840579711,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9321608040201005,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6247881714198806,
      "success_rate.epoch.global": 0.8263069139966274,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.98974609375,
      "tokens_p.mean_in_band": 0.8359375,
      "tokens_rate.above_band": 0.9770992366412213,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022900763358778626
    },
    {
      "epoch": 1.0521941489361701,
      "grad_norm": 108.81535078273247,
      "learning_rate": 1.7897465614092362e-07,
      "loss": 0.3824,
      "step": 6330,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9328358208955224,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6270102479057703,
      "success_rate.epoch.global": 0.8289036544850499,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9962201873935264,
      "tokens_p.mean_in_band": 0.6884765625,
      "tokens_rate.above_band": 0.9966044142614601,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003395585738539898
    },
    {
      "epoch": 1.0530252659574468,
      "grad_norm": 1050.5492452358776,
      "learning_rate": 1.7894804810798848e-07,
      "loss": 0.3721,
      "step": 6335,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5466666666666666,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9339853300733496,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6261503168267635,
      "success_rate.epoch.global": 0.8284313725490197,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963932181971357,
      "tokens_p.mean_in_band": 0.512890625,
      "tokens_rate.above_band": 0.967400162999185,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.032599837000814993
    },
    {
      "epoch": 1.0538563829787233,
      "grad_norm": 90.25205218720191,
      "learning_rate": 1.7892144194201025e-07,
      "loss": 0.3748,
      "step": 6340,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5454545454545454,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9346246973365617,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5634780097491962,
      "success_rate.epoch.global": 0.8276972624798712,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9962559117183395,
      "tokens_p.mean_below_band": 5.7980287238024175e-12,
      "tokens_p.mean_in_band": 0.602156929347826,
      "tokens_rate.above_band": 0.9758974358974359,
      "tokens_rate.below_band": 0.0005128205128205128,
      "tokens_rate.in_band": 0.02358974358974359
    },
    {
      "epoch": 1.0546875,
      "grad_norm": 110.66002278027692,
      "learning_rate": 1.7889483769020832e-07,
      "loss": 0.3198,
      "step": 6345,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5487804878048781,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9328537170263789,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5636335059532112,
      "success_rate.epoch.global": 0.8256735340729001,
      "success_rate.window.env.logic": 0.6,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.7833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9983033749082906,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.6125,
      "tokens_rate.above_band": 0.9777618364418939,
      "tokens_rate.below_band": 0.0007173601147776184,
      "tokens_rate.in_band": 0.021520803443328552
    },
    {
      "epoch": 1.0555186170212767,
      "grad_norm": 129.08926692631837,
      "learning_rate": 1.7886823539979875e-07,
      "loss": 0.2167,
      "step": 6350,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5487804878048781,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9314420803782506,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5634923422883983,
      "success_rate.epoch.global": 0.8268330733229329,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9166666666666667,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.987037037037037,
      "tokens_p.mean_in_band": 0.74765625,
      "tokens_rate.above_band": 0.9310344827586207,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06896551724137931
    },
    {
      "epoch": 1.0563497340425532,
      "grad_norm": 67.39747282118377,
      "learning_rate": 1.7884163511799405e-07,
      "loss": 0.3422,
      "step": 6355,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5487804878048781,
      "success_rate.epoch.env.math": 1.0,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.9327146171693735,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5670383993863141,
      "success_rate.epoch.global": 0.8294930875576036,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.985479797979798,
      "tokens_p.mean_in_band": 0.826171875,
      "tokens_rate.above_band": 0.9705882352941176,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029411764705882353
    },
    {
      "epoch": 1.0571808510638299,
      "grad_norm": 41.85017480121167,
      "learning_rate": 1.7881503689200325e-07,
      "loss": 0.3681,
      "step": 6360,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5487804878048781,
      "success_rate.epoch.env.math": 0.9861111111111112,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.9269406392694064,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5650721127074284,
      "success_rate.epoch.global": 0.8260211800302572,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9877717391304348,
      "tokens_p.mean_below_band": 1.0878364875566149e-10,
      "tokens_p.mean_in_band": 0.6533954326923077,
      "tokens_rate.above_band": 0.8313253012048193,
      "tokens_rate.below_band": 0.012048192771084338,
      "tokens_rate.in_band": 0.1566265060240964
    },
    {
      "epoch": 1.0580119680851063,
      "grad_norm": 66.71791944353244,
      "learning_rate": 1.7878844076903165e-07,
      "loss": 0.2858,
      "step": 6365,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.5476190476190477,
      "success_rate.epoch.env.math": 0.9861111111111112,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.9255079006772009,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5703028909080563,
      "success_rate.epoch.global": 0.8253731343283582,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.825,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.991164353859497,
      "tokens_p.mean_in_band": 0.5632560483870968,
      "tokens_rate.above_band": 0.9738175675675675,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026182432432432432
    },
    {
      "epoch": 1.058843085106383,
      "grad_norm": 59.06345597476102,
      "learning_rate": 1.787618467962809e-07,
      "loss": 0.4183,
      "step": 6370,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.5402298850574713,
      "success_rate.epoch.env.math": 0.9861111111111112,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.9220489977728286,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5668789030749116,
      "success_rate.epoch.global": 0.8205882352941176,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.996594982078853,
      "tokens_p.mean_in_band": 0.5979073660714286,
      "tokens_rate.above_band": 0.9522184300341296,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04778156996587031
    },
    {
      "epoch": 1.0596742021276595,
      "grad_norm": 368.11241159578213,
      "learning_rate": 1.7873525502094873e-07,
      "loss": 0.2308,
      "step": 6375,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.5454545454545454,
      "success_rate.epoch.env.math": 0.9861111111111112,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.9234135667396062,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5671410006144715,
      "success_rate.epoch.global": 0.8217391304347826,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963835311572701,
      "tokens_p.mean_in_band": 0.6975911458333334,
      "tokens_rate.above_band": 0.9656160458452722,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034383954154727794
    },
    {
      "epoch": 1.0605053191489362,
      "grad_norm": 88.12338112833083,
      "learning_rate": 1.7870866549022904e-07,
      "loss": 0.3233,
      "step": 6380,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5882352941176471,
      "success_rate.epoch.env.logic": 0.5454545454545454,
      "success_rate.epoch.env.math": 0.9864864864864865,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.9225806451612903,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5670952459941774,
      "success_rate.epoch.global": 0.8228571428571428,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.985248447204969,
      "tokens_p.mean_below_band": 2.9976945370435715e-09,
      "tokens_p.mean_in_band": 0.787109375,
      "tokens_rate.above_band": 0.9583333333333334,
      "tokens_rate.below_band": 0.005952380952380952,
      "tokens_rate.in_band": 0.03571428571428571
    },
    {
      "epoch": 1.0613364361702127,
      "grad_norm": 1415.1440546492604,
      "learning_rate": 1.7868207825131177e-07,
      "loss": 0.4223,
      "step": 6385,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.5454545454545454,
      "success_rate.epoch.env.math": 0.9866666666666667,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.9234042553191489,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5694414356329249,
      "success_rate.epoch.global": 0.8236953455571228,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9874859392575928,
      "tokens_p.mean_in_band": 0.47511691560324826,
      "tokens_rate.above_band": 0.6734848484848485,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.32651515151515154
    },
    {
      "epoch": 1.0621675531914894,
      "grad_norm": 77.17081729545556,
      "learning_rate": 1.786554933513827e-07,
      "loss": 0.249,
      "step": 6390,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9868421052631579,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9242105263157895,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5701802494742603,
      "success_rate.epoch.global": 0.8245125348189415,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953703703703703,
      "tokens_p.mean_in_band": 0.7235753676470589,
      "tokens_rate.above_band": 0.945859872611465,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054140127388535034
    },
    {
      "epoch": 1.062998670212766,
      "grad_norm": 54.746022349568634,
      "learning_rate": 1.7862891083762354e-07,
      "loss": 0.3422,
      "step": 6395,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47619047619047616,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.5494505494505495,
      "success_rate.epoch.env.math": 0.9873417721518988,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9251559251559252,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5697142554366474,
      "success_rate.epoch.global": 0.8255494505494505,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9997550940438872,
      "tokens_p.mean_in_band": 0.4545641447368421,
      "tokens_rate.above_band": 0.9710806697108066,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0289193302891933
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 691.6460849750772,
      "learning_rate": 1.7860233075721175e-07,
      "loss": 0.2917,
      "step": 6400,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5555555555555556,
      "success_rate.epoch.env.logic": 0.5483870967741935,
      "success_rate.epoch.env.math": 0.9875,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9260780287474333,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5720968956939252,
      "success_rate.epoch.global": 0.8265582655826558,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9971846846846847,
      "tokens_p.mean_in_band": 0.6029947916666667,
      "tokens_rate.above_band": 0.9866666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013333333333333334
    },
    {
      "epoch": 1.0646609042553192,
      "grad_norm": 84.08086629675827,
      "learning_rate": 1.7857575315732046e-07,
      "loss": 0.3328,
      "step": 6405,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5789473684210527,
      "success_rate.epoch.env.logic": 0.5425531914893617,
      "success_rate.epoch.env.math": 0.9875,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9271255060728745,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5739574341845357,
      "success_rate.epoch.global": 0.8273092369477911,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954007056451613,
      "tokens_p.mean_in_band": 0.6981336805555556,
      "tokens_rate.above_band": 0.9821782178217822,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01782178217821782
    },
    {
      "epoch": 1.0654920212765957,
      "grad_norm": 580.8719720104739,
      "learning_rate": 1.7854917808511837e-07,
      "loss": 0.4677,
      "step": 6410,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5789473684210527,
      "success_rate.epoch.env.logic": 0.5473684210526316,
      "success_rate.epoch.env.math": 0.9875,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9243027888446215,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5738118578318305,
      "success_rate.epoch.global": 0.8256274768824307,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9911629098360656,
      "tokens_p.mean_below_band": 5.502442945726216e-11,
      "tokens_p.mean_in_band": 0.6705729166666666,
      "tokens_rate.above_band": 0.8591549295774648,
      "tokens_rate.below_band": 0.0035211267605633804,
      "tokens_rate.in_band": 0.13732394366197184
    },
    {
      "epoch": 1.0663231382978724,
      "grad_norm": 50.41168610189158,
      "learning_rate": 1.7852260558776978e-07,
      "loss": 0.3104,
      "step": 6415,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.55,
      "success_rate.epoch.env.logic": 0.5416666666666666,
      "success_rate.epoch.env.math": 0.9875,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.9250493096646942,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5629215976331361,
      "success_rate.epoch.global": 0.8226857887874837,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9934703712517848,
      "tokens_p.mean_in_band": 0.537900967413442,
      "tokens_rate.above_band": 0.8953760920519923,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10462390794800767
    },
    {
      "epoch": 1.0671542553191489,
      "grad_norm": 69.21058405606163,
      "learning_rate": 1.784960357124343e-07,
      "loss": 0.3487,
      "step": 6420,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.55,
      "success_rate.epoch.env.logic": 0.5510204081632653,
      "success_rate.epoch.env.math": 0.9875,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.9259259259259259,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5710874905517762,
      "success_rate.epoch.global": 0.8247422680412371,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9933928571428572,
      "tokens_p.mean_in_band": 0.6655815972222222,
      "tokens_rate.above_band": 0.9510869565217391,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04891304347826087
    },
    {
      "epoch": 1.0679853723404256,
      "grad_norm": 71.70631679231734,
      "learning_rate": 1.7846946850626697e-07,
      "loss": 0.3446,
      "step": 6425,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9876543209876543,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.9267822736030829,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5666420721574864,
      "success_rate.epoch.global": 0.8256997455470738,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9885817307692307,
      "tokens_p.mean_below_band": 8.307397365570068e-07,
      "tokens_p.mean_in_band": 0.24333618936426635,
      "tokens_rate.above_band": 0.22934076137418755,
      "tokens_rate.below_band": 0.00023212627669452182,
      "tokens_rate.in_band": 0.7704271123491179
    },
    {
      "epoch": 1.068816489361702,
      "grad_norm": 24.557658215998572,
      "learning_rate": 1.784429040164181e-07,
      "loss": 0.2392,
      "step": 6430,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4782608695652174,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9759036144578314,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.9276190476190476,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5629979779838343,
      "success_rate.epoch.global": 0.8241206030150754,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9966643258426966,
      "tokens_p.mean_below_band": 6.314393452555578e-16,
      "tokens_p.mean_in_band": 0.6741071428571429,
      "tokens_rate.above_band": 0.9595687331536388,
      "tokens_rate.below_band": 0.0026954177897574125,
      "tokens_rate.in_band": 0.03773584905660377
    },
    {
      "epoch": 1.0696476063829787,
      "grad_norm": 102.28341051783671,
      "learning_rate": 1.7841634229003313e-07,
      "loss": 0.5238,
      "step": 6435,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4782608695652174,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9761904761904762,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.9287054409005628,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.568690859040806,
      "success_rate.epoch.global": 0.826302729528536,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9941939890710383,
      "tokens_p.mean_in_band": 0.8984375,
      "tokens_rate.above_band": 0.9945652173913043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005434782608695652
    },
    {
      "epoch": 1.0704787234042552,
      "grad_norm": 98.75339140149212,
      "learning_rate": 1.7838978337425262e-07,
      "loss": 0.3406,
      "step": 6440,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4782608695652174,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9770114942528736,
      "success_rate.epoch.env.sat": 0.12121212121212122,
      "success_rate.epoch.env.science": 0.9277777777777778,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5686801945347671,
      "success_rate.epoch.global": 0.8272058823529411,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9868881118881119,
      "tokens_p.mean_below_band": 5.3085386753082275e-08,
      "tokens_p.mean_in_band": 0.8541666666666666,
      "tokens_rate.above_band": 0.9727891156462585,
      "tokens_rate.below_band": 0.006802721088435374,
      "tokens_rate.in_band": 0.02040816326530612
    },
    {
      "epoch": 1.071309840425532,
      "grad_norm": 50.849622236817034,
      "learning_rate": 1.7836322731621209e-07,
      "loss": 0.4295,
      "step": 6445,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.52,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9772727272727273,
      "success_rate.epoch.env.sat": 0.14705882352941177,
      "success_rate.epoch.env.science": 0.9285714285714286,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.575544266191325,
      "success_rate.epoch.global": 0.8292978208232445,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9977713178294574,
      "tokens_p.mean_in_band": 0.6614583333333334,
      "tokens_rate.above_band": 0.9862385321100917,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013761467889908258
    },
    {
      "epoch": 1.0721409574468086,
      "grad_norm": 55.12315168420935,
      "learning_rate": 1.7833667416304212e-07,
      "loss": 0.286,
      "step": 6450,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5643564356435643,
      "success_rate.epoch.env.math": 0.9775280898876404,
      "success_rate.epoch.env.sat": 0.14705882352941177,
      "success_rate.epoch.env.science": 0.9274047186932849,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.5743332194738028,
      "success_rate.epoch.global": 0.8287425149700599,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9966887417218543,
      "tokens_p.mean_below_band": 6.927791673660977e-13,
      "tokens_p.mean_in_band": 0.6494140625,
      "tokens_rate.above_band": 0.993421052631579,
      "tokens_rate.below_band": 0.0021929824561403508,
      "tokens_rate.in_band": 0.0043859649122807015
    },
    {
      "epoch": 1.072972074468085,
      "grad_norm": 287.51365033763386,
      "learning_rate": 1.7831012396186802e-07,
      "loss": 0.3523,
      "step": 6455,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5686274509803921,
      "success_rate.epoch.env.math": 0.978021978021978,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9279279279279279,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6131289660701426,
      "success_rate.epoch.global": 0.8293838862559242,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978508364312267,
      "tokens_p.mean_in_band": 0.5879836309523809,
      "tokens_rate.above_band": 0.962432915921288,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03756708407871199
    },
    {
      "epoch": 1.0738031914893618,
      "grad_norm": 1.863389303347459,
      "learning_rate": 1.7828357675980987e-07,
      "loss": 0.2139,
      "step": 6460,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.5686274509803921,
      "success_rate.epoch.env.math": 0.978021978021978,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9273049645390071,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6148432893511969,
      "success_rate.epoch.global": 0.8302107728337237,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9918650793650794,
      "tokens_p.mean_below_band": 2.2851054382044822e-11,
      "tokens_p.mean_in_band": 0.8486328125,
      "tokens_rate.above_band": 0.984375,
      "tokens_rate.below_band": 0.003125,
      "tokens_rate.in_band": 0.0125
    },
    {
      "epoch": 1.0746343085106382,
      "grad_norm": 46.544767362918385,
      "learning_rate": 1.7825703260398247e-07,
      "loss": 0.2961,
      "step": 6465,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.5728155339805825,
      "success_rate.epoch.env.math": 0.9782608695652174,
      "success_rate.epoch.env.sat": 0.14285714285714285,
      "success_rate.epoch.env.science": 0.9279437609841827,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6153038139865248,
      "success_rate.epoch.global": 0.8315911730545877,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9898897058823529,
      "tokens_p.mean_below_band": 6.314393452555578e-16,
      "tokens_p.mean_in_band": 0.8684895833333334,
      "tokens_rate.above_band": 0.966824644549763,
      "tokens_rate.below_band": 0.004739336492890996,
      "tokens_rate.in_band": 0.02843601895734597
    },
    {
      "epoch": 1.075465425531915,
      "grad_norm": 51.803318841664115,
      "learning_rate": 1.782304915414952e-07,
      "loss": 0.3279,
      "step": 6470,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.5673076923076923,
      "success_rate.epoch.env.math": 0.978494623655914,
      "success_rate.epoch.env.sat": 0.1388888888888889,
      "success_rate.epoch.env.science": 0.926829268292683,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6143622836008931,
      "success_rate.epoch.global": 0.8296892980437284,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9945089285714286,
      "tokens_p.mean_in_band": 0.6749526515151515,
      "tokens_rate.above_band": 0.9549795361527967,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.045020463847203276
    },
    {
      "epoch": 1.0762965425531914,
      "grad_norm": 110.85756928903345,
      "learning_rate": 1.7820395361945194e-07,
      "loss": 0.396,
      "step": 6475,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.5,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5909090909090909,
      "success_rate.epoch.env.logic": 0.5660377358490566,
      "success_rate.epoch.env.math": 0.9787234042553191,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.9258620689655173,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6138384536972431,
      "success_rate.epoch.global": 0.8282138794084186,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9948894101876675,
      "tokens_p.mean_in_band": 0.6570638020833334,
      "tokens_rate.above_band": 0.9395465994962217,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.060453400503778336
    },
    {
      "epoch": 1.077127659574468,
      "grad_norm": 513.1445763710295,
      "learning_rate": 1.7817741888495096e-07,
      "loss": 0.4539,
      "step": 6480,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.48148148148148145,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6086956521739131,
      "success_rate.epoch.env.logic": 0.5596330275229358,
      "success_rate.epoch.env.math": 0.9787234042553191,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.9264957264957265,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6132472711472787,
      "success_rate.epoch.global": 0.8267716535433071,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9951459560792716,
      "tokens_p.mean_in_band": 0.7315705128205128,
      "tokens_rate.above_band": 0.9598971722365038,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04010282776349614
    },
    {
      "epoch": 1.0779587765957448,
      "grad_norm": 145.08457463701905,
      "learning_rate": 1.7815088738508498e-07,
      "loss": 0.3923,
      "step": 6485,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6086956521739131,
      "success_rate.epoch.env.logic": 0.5596330275229358,
      "success_rate.epoch.env.math": 0.979381443298969,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.9271186440677966,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6134798253130872,
      "success_rate.epoch.global": 0.8275862068965517,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.998003992015968,
      "tokens_p.mean_in_band": 0.719140625,
      "tokens_rate.above_band": 0.9901185770750988,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009881422924901186
    },
    {
      "epoch": 1.0787898936170213,
      "grad_norm": 12.707820758060128,
      "learning_rate": 1.7812435916694087e-07,
      "loss": 0.2818,
      "step": 6490,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4827586206896552,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5833333333333334,
      "success_rate.epoch.env.logic": 0.5585585585585585,
      "success_rate.epoch.env.math": 0.9795918367346939,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.9278523489932886,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6111623080909291,
      "success_rate.epoch.global": 0.8272827282728272,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952233895174325,
      "tokens_p.mean_in_band": 0.5006917317708334,
      "tokens_rate.above_band": 0.9575502984744638,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04244970152553615
    },
    {
      "epoch": 1.079621010638298,
      "grad_norm": 92.89104092271577,
      "learning_rate": 1.7809783427759971e-07,
      "loss": 0.3989,
      "step": 6495,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6,
      "success_rate.epoch.env.logic": 0.5585585585585585,
      "success_rate.epoch.env.math": 0.9795918367346939,
      "success_rate.epoch.env.sat": 0.13513513513513514,
      "success_rate.epoch.env.science": 0.9269102990033222,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6262804289382362,
      "success_rate.epoch.global": 0.826797385620915,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9953051643192489,
      "tokens_p.mean_in_band": 0.59912109375,
      "tokens_rate.above_band": 0.9953271028037384,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004672897196261682
    },
    {
      "epoch": 1.0804521276595744,
      "grad_norm": 53.10069115599052,
      "learning_rate": 1.7807131276413672e-07,
      "loss": 0.3364,
      "step": 6500,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6,
      "success_rate.epoch.env.logic": 0.5585585585585585,
      "success_rate.epoch.env.math": 0.9803921568627451,
      "success_rate.epoch.env.sat": 0.13157894736842105,
      "success_rate.epoch.env.science": 0.9275123558484349,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6260846279570044,
      "success_rate.epoch.global": 0.8275862068965517,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9896472392638037,
      "tokens_p.mean_in_band": 0.5596217105263158,
      "tokens_rate.above_band": 0.8956043956043956,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1043956043956044
    },
    {
      "epoch": 1.0812832446808511,
      "grad_norm": 191.37010940700353,
      "learning_rate": 1.7804479467362105e-07,
      "loss": 0.2535,
      "step": 6505,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4666666666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.6153846153846154,
      "success_rate.epoch.env.logic": 0.5585585585585585,
      "success_rate.epoch.env.math": 0.9809523809523809,
      "success_rate.epoch.env.sat": 0.13157894736842105,
      "success_rate.epoch.env.science": 0.9263502454991817,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6274285124229133,
      "success_rate.epoch.global": 0.8279914529914529,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9847248134328358,
      "tokens_p.mean_in_band": 0.7765066964285714,
      "tokens_rate.above_band": 0.950354609929078,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04964539007092199
    },
    {
      "epoch": 1.0821143617021276,
      "grad_norm": 46.93725625490084,
      "learning_rate": 1.7801828005311586e-07,
      "loss": 0.4796,
      "step": 6510,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5925925925925926,
      "success_rate.epoch.env.logic": 0.5585585585585585,
      "success_rate.epoch.env.math": 0.9813084112149533,
      "success_rate.epoch.env.sat": 0.13157894736842105,
      "success_rate.epoch.env.science": 0.9270664505672609,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6240854623408922,
      "success_rate.epoch.global": 0.8276955602536998,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941420014094433,
      "tokens_p.mean_below_band": 6.780028343200684e-07,
      "tokens_p.mean_in_band": 0.3543172554347826,
      "tokens_rate.above_band": 0.7109218436873748,
      "tokens_rate.below_band": 0.001002004008016032,
      "tokens_rate.in_band": 0.2880761523046092
    },
    {
      "epoch": 1.0829454787234043,
      "grad_norm": 105.94141958340671,
      "learning_rate": 1.7799176894967804e-07,
      "loss": 0.333,
      "step": 6515,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5663716814159292,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.927536231884058,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6223320992416426,
      "success_rate.epoch.global": 0.8263598326359832,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9935429676893837,
      "tokens_p.mean_below_band": 7.338821887969971e-07,
      "tokens_p.mean_in_band": 0.5341239429175476,
      "tokens_rate.above_band": 0.8859754630743325,
      "tokens_rate.below_band": 0.00024055809477988935,
      "tokens_rate.in_band": 0.11378397883088766
    },
    {
      "epoch": 1.0837765957446808,
      "grad_norm": 174.17597693767556,
      "learning_rate": 1.7796526141035836e-07,
      "loss": 0.3843,
      "step": 6520,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5739130434782609,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.9267515923566879,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.622946346744821,
      "success_rate.epoch.global": 0.8269430051813471,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9924380466472303,
      "tokens_p.mean_below_band": 1.6916601452976465e-10,
      "tokens_p.mean_in_band": 0.8662683823529411,
      "tokens_rate.above_band": 0.9501385041551247,
      "tokens_rate.below_band": 0.002770083102493075,
      "tokens_rate.in_band": 0.04709141274238227
    },
    {
      "epoch": 1.0846077127659575,
      "grad_norm": 89.97509558787614,
      "learning_rate": 1.7793875748220117e-07,
      "loss": 0.3639,
      "step": 6525,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5641025641025641,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.925984251968504,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6219847267662864,
      "success_rate.epoch.global": 0.8254620123203286,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9958263888888889,
      "tokens_p.mean_below_band": 7.82310962677002e-07,
      "tokens_p.mean_in_band": 0.5351166328600405,
      "tokens_rate.above_band": 0.9010812975570685,
      "tokens_rate.below_band": 0.00020024028834601522,
      "tokens_rate.in_band": 0.0987184621545855
    },
    {
      "epoch": 1.085438829787234,
      "grad_norm": 105.98294587238055,
      "learning_rate": 1.779122572122445e-07,
      "loss": 0.4785,
      "step": 6530,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.46875,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5677966101694916,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.125,
      "success_rate.epoch.env.science": 0.926791277258567,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6279922370004344,
      "success_rate.epoch.global": 0.8272357723577236,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9921153846153846,
      "tokens_p.mean_in_band": 0.7970252403846154,
      "tokens_rate.above_band": 0.9615384615384616,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038461538461538464
    },
    {
      "epoch": 1.0862699468085106,
      "grad_norm": 31.33804722027422,
      "learning_rate": 1.778857606475198e-07,
      "loss": 0.4783,
      "step": 6535,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.48484848484848486,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.12195121951219512,
      "success_rate.epoch.env.science": 0.9274691358024691,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6295703755607672,
      "success_rate.epoch.global": 0.8277945619335347,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9960848519362187,
      "tokens_p.mean_in_band": 0.58734375,
      "tokens_rate.above_band": 0.8977505112474438,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10224948875255624
    },
    {
      "epoch": 1.0871010638297873,
      "grad_norm": 73.4969904114429,
      "learning_rate": 1.7785926783505195e-07,
      "loss": 0.2282,
      "step": 6540,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.48484848484848486,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5714285714285714,
      "success_rate.epoch.env.logic": 0.575,
      "success_rate.epoch.env.math": 0.981651376146789,
      "success_rate.epoch.env.sat": 0.11904761904761904,
      "success_rate.epoch.env.science": 0.9282442748091603,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6297169993588446,
      "success_rate.epoch.global": 0.8285144566301097,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940277777777777,
      "tokens_p.mean_in_band": 0.6640625,
      "tokens_rate.above_band": 0.9183673469387755,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08163265306122448
    },
    {
      "epoch": 1.0879321808510638,
      "grad_norm": 89.49092934806677,
      "learning_rate": 1.7783277882185925e-07,
      "loss": 0.3395,
      "step": 6545,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.48484848484848486,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5772357723577236,
      "success_rate.epoch.env.math": 0.981651376146789,
      "success_rate.epoch.env.sat": 0.11904761904761904,
      "success_rate.epoch.env.science": 0.9288956127080181,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.628188151791485,
      "success_rate.epoch.global": 0.8282329713721619,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9958591811414392,
      "tokens_p.mean_below_band": 4.4330954551696777e-07,
      "tokens_p.mean_in_band": 0.5228365384615384,
      "tokens_rate.above_band": 0.8904109589041096,
      "tokens_rate.below_band": 0.0004418912947414936,
      "tokens_rate.in_band": 0.10914714980114892
    },
    {
      "epoch": 1.0887632978723405,
      "grad_norm": 100.66617837587154,
      "learning_rate": 1.7780629365495322e-07,
      "loss": 0.3668,
      "step": 6550,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47058823529411764,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5772357723577236,
      "success_rate.epoch.env.math": 0.981651376146789,
      "success_rate.epoch.env.sat": 0.11904761904761904,
      "success_rate.epoch.env.science": 0.9296407185628742,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6269595023642568,
      "success_rate.epoch.global": 0.8285994123408423,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9940181518151815,
      "tokens_p.mean_below_band": 1.8361788534093648e-08,
      "tokens_rate.above_band": 0.9934426229508196,
      "tokens_rate.below_band": 0.006557377049180328,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.089594414893617,
      "grad_norm": 33.818722055195266,
      "learning_rate": 1.777798123813385e-07,
      "loss": 0.3124,
      "step": 6555,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5725806451612904,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.11627906976744186,
      "success_rate.epoch.env.science": 0.9300595238095238,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6251450688746975,
      "success_rate.epoch.global": 0.8273520853540253,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975676121372031,
      "tokens_p.mean_in_band": 0.5640836148648649,
      "tokens_rate.above_band": 0.9534591194968554,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04654088050314465
    },
    {
      "epoch": 1.0904255319148937,
      "grad_norm": 68.87325475131094,
      "learning_rate": 1.7775333504801289e-07,
      "loss": 0.3797,
      "step": 6560,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.43243243243243246,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5634920634920635,
      "success_rate.epoch.env.math": 0.9823008849557522,
      "success_rate.epoch.env.sat": 0.11627906976744186,
      "success_rate.epoch.env.science": 0.9289940828402367,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6295656974017237,
      "success_rate.epoch.global": 0.8242074927953891,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.55,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9982399874843555,
      "tokens_p.mean_in_band": 0.5787550403225806,
      "tokens_rate.above_band": 0.9809699201964396,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019030079803560467
    },
    {
      "epoch": 1.0912566489361701,
      "grad_norm": 61.59442021774853,
      "learning_rate": 1.7772686170196716e-07,
      "loss": 0.3156,
      "step": 6565,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.43243243243243246,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5590551181102362,
      "success_rate.epoch.env.math": 0.9823008849557522,
      "success_rate.epoch.env.sat": 0.1111111111111111,
      "success_rate.epoch.env.science": 0.9296187683284457,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6287493138971829,
      "success_rate.epoch.global": 0.8228571428571428,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9955481843575419,
      "tokens_p.mean_in_band": 0.6449468085106383,
      "tokens_rate.above_band": 0.9384010484927916,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061598951507208385
    },
    {
      "epoch": 1.0920877659574468,
      "grad_norm": 130.11674023574747,
      "learning_rate": 1.77700392390185e-07,
      "loss": 0.3977,
      "step": 6570,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.425,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5590551181102362,
      "success_rate.epoch.env.math": 0.9823008849557522,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.9302325581395349,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6279098501191337,
      "success_rate.epoch.global": 0.8216981132075472,
      "success_rate.window.env.agentgym:alfworld": 0.3333333333333333,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9972098214285714,
      "tokens_p.mean_in_band": 0.68271484375,
      "tokens_rate.above_band": 0.9710982658959537,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028901734104046242
    },
    {
      "epoch": 1.0929188829787233,
      "grad_norm": 78.33227863288644,
      "learning_rate": 1.7767392715964298e-07,
      "loss": 0.3319,
      "step": 6575,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4146341463414634,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5581395348837209,
      "success_rate.epoch.env.math": 0.9826086956521739,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.9305354558610709,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6269397838948524,
      "success_rate.epoch.global": 0.8211610486891385,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9961391235480465,
      "tokens_p.mean_in_band": 0.6548887310606061,
      "tokens_rate.above_band": 0.9663265306122449,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0336734693877551
    },
    {
      "epoch": 1.09375,
      "grad_norm": 40.57218284438359,
      "learning_rate": 1.7764746605731038e-07,
      "loss": 0.4888,
      "step": 6580,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4146341463414634,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5581395348837209,
      "success_rate.epoch.env.math": 0.9826086956521739,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.9296987087517934,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6268637159758271,
      "success_rate.epoch.global": 0.8212290502793296,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.990530303030303,
      "tokens_p.mean_in_band": 0.7130681818181818,
      "tokens_rate.above_band": 0.8333333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16666666666666666
    },
    {
      "epoch": 1.0945811170212767,
      "grad_norm": 58.64597739572771,
      "learning_rate": 1.776210091301492e-07,
      "loss": 0.4177,
      "step": 6585,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4146341463414634,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5581395348837209,
      "success_rate.epoch.env.math": 0.9826086956521739,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.9292786421499293,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6268255281029305,
      "success_rate.epoch.global": 0.8219557195571956,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9874543795620438,
      "tokens_p.mean_in_band": 0.6271033653846154,
      "tokens_rate.above_band": 0.8404907975460123,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15950920245398773
    },
    {
      "epoch": 1.0954122340425532,
      "grad_norm": 180.39151512763016,
      "learning_rate": 1.7759455642511398e-07,
      "loss": 0.2981,
      "step": 6590,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4146341463414634,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5517241379310345,
      "success_rate.epoch.env.logic": 0.5538461538461539,
      "success_rate.epoch.env.math": 0.9827586206896551,
      "success_rate.epoch.env.sat": 0.10869565217391304,
      "success_rate.epoch.env.science": 0.9297752808988764,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6264939992619177,
      "success_rate.epoch.global": 0.8221814848762603,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9969713656387665,
      "tokens_p.mean_in_band": 0.75390625,
      "tokens_rate.above_band": 0.9869565217391304,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013043478260869565
    },
    {
      "epoch": 1.0962433510638299,
      "grad_norm": 81.61788518495,
      "learning_rate": 1.775681079891518e-07,
      "loss": 0.3315,
      "step": 6595,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4146341463414634,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.556390977443609,
      "success_rate.epoch.env.math": 0.9829059829059829,
      "success_rate.epoch.env.sat": 0.10638297872340426,
      "success_rate.epoch.env.science": 0.9301675977653632,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6248922742284687,
      "success_rate.epoch.global": 0.821071752951862,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.994911369193154,
      "tokens_p.mean_in_band": 0.5670432220039293,
      "tokens_rate.above_band": 0.8893237660360948,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11067623396390519
    },
    {
      "epoch": 1.0970744680851063,
      "grad_norm": 66.41083767815665,
      "learning_rate": 1.7754166386920214e-07,
      "loss": 0.3743,
      "step": 6600,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4146341463414634,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5597014925373134,
      "success_rate.epoch.env.math": 0.975,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.9305555555555556,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6243082904031211,
      "success_rate.epoch.global": 0.8207207207207208,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5416666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9997384937238494,
      "tokens_p.mean_below_band": 1.2931877790833823e-12,
      "tokens_p.mean_in_band": 0.5482954545454546,
      "tokens_rate.above_band": 0.9689189189189189,
      "tokens_rate.below_band": 0.0013513513513513514,
      "tokens_rate.in_band": 0.02972972972972973
    },
    {
      "epoch": 1.097905585106383,
      "grad_norm": 60.52325472022653,
      "learning_rate": 1.7751522411219688e-07,
      "loss": 0.2481,
      "step": 6605,
      "success_rate.epoch.env.abd": 0.6363636363636364,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9752066115702479,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.9297520661157025,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6262854340333679,
      "success_rate.epoch.global": 0.8196428571428571,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9991512345679012,
      "tokens_p.mean_below_band": 1.525040715932846e-08,
      "tokens_p.mean_in_band": 0.5091145833333334,
      "tokens_rate.above_band": 0.9842041312272175,
      "tokens_rate.below_band": 0.001215066828675577,
      "tokens_rate.in_band": 0.014580801944106925
    },
    {
      "epoch": 1.0987367021276595,
      "grad_norm": 84.84879206854862,
      "learning_rate": 1.7748878876506007e-07,
      "loss": 0.2854,
      "step": 6610,
      "success_rate.epoch.env.abd": 0.6363636363636364,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5333333333333333,
      "success_rate.epoch.env.logic": 0.5514705882352942,
      "success_rate.epoch.env.math": 0.975609756097561,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.9275956284153005,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6257546830794269,
      "success_rate.epoch.global": 0.8184233835252436,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9992070895522388,
      "tokens_p.mean_below_band": 1.4915713109076023e-10,
      "tokens_p.mean_in_band": 0.552801724137931,
      "tokens_rate.above_band": 0.9571428571428572,
      "tokens_rate.below_band": 0.0014285714285714286,
      "tokens_rate.in_band": 0.041428571428571426
    },
    {
      "epoch": 1.0995678191489362,
      "grad_norm": 307.9009780617586,
      "learning_rate": 1.7746235787470795e-07,
      "loss": 0.4203,
      "step": 6615,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5434782608695652,
      "success_rate.epoch.env.math": 0.9682539682539683,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.9277929155313351,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.625374869515276,
      "success_rate.epoch.global": 0.8156277436347673,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.994165868836764,
      "tokens_p.mean_below_band": 9.942959877662361e-08,
      "tokens_p.mean_in_band": 0.5082828177257525,
      "tokens_rate.above_band": 0.8744244453746337,
      "tokens_rate.below_band": 0.0004185851820845542,
      "tokens_rate.in_band": 0.1251569694432817
    },
    {
      "epoch": 1.1003989361702127,
      "grad_norm": 63.74198812391206,
      "learning_rate": 1.7743593148804894e-07,
      "loss": 0.2712,
      "step": 6620,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.0,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5467625899280576,
      "success_rate.epoch.env.math": 0.96875,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.927027027027027,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6256489124516592,
      "success_rate.epoch.global": 0.8162020905923345,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9901315789473685,
      "tokens_p.mean_below_band": 2.648448571562767e-09,
      "tokens_p.mean_in_band": 0.7890625,
      "tokens_rate.above_band": 0.9178743961352657,
      "tokens_rate.below_band": 0.004830917874396135,
      "tokens_rate.in_band": 0.07729468599033816
    },
    {
      "epoch": 1.1012300531914894,
      "grad_norm": 67.92180948075969,
      "learning_rate": 1.7740950965198335e-07,
      "loss": 0.3405,
      "step": 6625,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5454545454545454,
      "success_rate.epoch.env.math": 0.9615384615384616,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.927321668909825,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6703557359923635,
      "success_rate.epoch.global": 0.8151986183074266,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9990313653136531,
      "tokens_p.mean_below_band": 1.7497114868092467e-13,
      "tokens_p.mean_in_band": 0.5560897435897436,
      "tokens_rate.above_band": 0.9713261648745519,
      "tokens_rate.below_band": 0.0007168458781362007,
      "tokens_rate.in_band": 0.02795698924731183
    },
    {
      "epoch": 1.102061170212766,
      "grad_norm": 95.70924124375362,
      "learning_rate": 1.7738309241340352e-07,
      "loss": 0.3161,
      "step": 6630,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5486111111111112,
      "success_rate.epoch.env.math": 0.9615384615384616,
      "success_rate.epoch.env.sat": 0.10204081632653061,
      "success_rate.epoch.env.science": 0.928,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.67070436296934,
      "success_rate.epoch.global": 0.8164665523156089,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9894770408163265,
      "tokens_p.mean_in_band": 0.8190104166666666,
      "tokens_rate.above_band": 0.9849246231155779,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01507537688442211
    },
    {
      "epoch": 1.1028922872340425,
      "grad_norm": 83.48372274800138,
      "learning_rate": 1.773566798191935e-07,
      "loss": 0.425,
      "step": 6635,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.547945205479452,
      "success_rate.epoch.env.math": 0.9618320610687023,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.928476821192053,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6705283355842585,
      "success_rate.epoch.global": 0.8161702127659575,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9961801040312094,
      "tokens_p.mean_in_band": 0.583984375,
      "tokens_rate.above_band": 0.9412484700122399,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0587515299877601
    },
    {
      "epoch": 1.1037234042553192,
      "grad_norm": 187.5878506578719,
      "learning_rate": 1.7733027191622926e-07,
      "loss": 0.3096,
      "step": 6640,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5540540540540541,
      "success_rate.epoch.env.math": 0.9548872180451128,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9289473684210526,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6704951131097142,
      "success_rate.epoch.global": 0.816722972972973,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7222222222222222,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983529819694869,
      "tokens_p.mean_below_band": 7.048583938740194e-11,
      "tokens_p.mean_in_band": 0.5127840909090909,
      "tokens_rate.above_band": 0.9836289222373806,
      "tokens_rate.below_band": 0.001364256480218281,
      "tokens_rate.in_band": 0.015006821282401092
    },
    {
      "epoch": 1.1045545212765957,
      "grad_norm": 78.48493565379526,
      "learning_rate": 1.773038687513783e-07,
      "loss": 0.3308,
      "step": 6645,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.75,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5540540540540541,
      "success_rate.epoch.env.math": 0.9558823529411765,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9295039164490861,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6706361751937231,
      "success_rate.epoch.global": 0.818105616093881,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9897629310344828,
      "tokens_p.mean_in_band": 0.83984375,
      "tokens_rate.above_band": 0.943089430894309,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056910569105691054
    },
    {
      "epoch": 1.1053856382978724,
      "grad_norm": 82.13432992845564,
      "learning_rate": 1.7727747037149975e-07,
      "loss": 0.2639,
      "step": 6650,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.40476190476190477,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5503355704697986,
      "success_rate.epoch.env.math": 0.9562043795620438,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9287564766839378,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6748049118547651,
      "success_rate.epoch.global": 0.8178036605657238,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941502463054187,
      "tokens_p.mean_in_band": 0.5443816489361702,
      "tokens_rate.above_band": 0.9452852153667055,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05471478463329453
    },
    {
      "epoch": 1.1062167553191489,
      "grad_norm": 184.8600193428981,
      "learning_rate": 1.7725107682344434e-07,
      "loss": 0.2572,
      "step": 6655,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.3953488372093023,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5503355704697986,
      "success_rate.epoch.env.math": 0.9571428571428572,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.9291237113402062,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6737182292037038,
      "success_rate.epoch.global": 0.8168316831683168,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977882420091324,
      "tokens_p.mean_in_band": 0.6877872242647058,
      "tokens_rate.above_band": 0.9279661016949152,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07203389830508475
    },
    {
      "epoch": 1.1070478723404256,
      "grad_norm": 84.57176337533897,
      "learning_rate": 1.772246881540541e-07,
      "loss": 0.2634,
      "step": 6660,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.3953488372093023,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5503355704697986,
      "success_rate.epoch.env.math": 0.9577464788732394,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.929757343550447,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6738307068346695,
      "success_rate.epoch.global": 0.8181818181818182,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9863138686131386,
      "tokens_p.mean_in_band": 0.62890625,
      "tokens_rate.above_band": 0.9856115107913669,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014388489208633094
    },
    {
      "epoch": 1.107878989361702,
      "grad_norm": 86.256842118094,
      "learning_rate": 1.7719830441016246e-07,
      "loss": 0.5245,
      "step": 6665,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4090909090909091,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5533333333333333,
      "success_rate.epoch.env.math": 0.958041958041958,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.9289340101522843,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6753045232451874,
      "success_rate.epoch.global": 0.8185516680227828,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9988137603795967,
      "tokens_p.mean_in_band": 0.4981219951923077,
      "tokens_rate.above_band": 0.9418994413407821,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05810055865921788
    },
    {
      "epoch": 1.1087101063829787,
      "grad_norm": 59.28796511278705,
      "learning_rate": 1.771719256385941e-07,
      "loss": 0.3414,
      "step": 6670,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4222222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5533333333333333,
      "success_rate.epoch.env.math": 0.958041958041958,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.9297365119196989,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6765712336905264,
      "success_rate.epoch.global": 0.8200161420500404,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9939963054187192,
      "tokens_p.mean_in_band": 0.79052734375,
      "tokens_rate.above_band": 0.9806763285024155,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01932367149758454
    },
    {
      "epoch": 1.1095412234042552,
      "grad_norm": 30.41967006378997,
      "learning_rate": 1.771455518861649e-07,
      "loss": 0.5756,
      "step": 6675,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4222222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5562913907284768,
      "success_rate.epoch.env.math": 0.9583333333333334,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.9291044776119403,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6768091789976863,
      "success_rate.epoch.global": 0.8205128205128205,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9942567567567567,
      "tokens_p.mean_in_band": 0.7315912246704102,
      "tokens_rate.above_band": 0.9585492227979274,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04145077720207254
    },
    {
      "epoch": 1.110372340425532,
      "grad_norm": 99.66065630389684,
      "learning_rate": 1.771191831996818e-07,
      "loss": 0.2703,
      "step": 6680,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4222222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.5526315789473685,
      "success_rate.epoch.env.math": 0.958904109589041,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.9294554455445545,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6765602637619785,
      "success_rate.epoch.global": 0.8207171314741036,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9936715070643642,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.6063368055555556,
      "tokens_rate.above_band": 0.9710365853658537,
      "tokens_rate.below_band": 0.001524390243902439,
      "tokens_rate.in_band": 0.027439024390243903
    },
    {
      "epoch": 1.1112034574468086,
      "grad_norm": 60.95736748176639,
      "learning_rate": 1.7709281962594272e-07,
      "loss": 0.2887,
      "step": 6685,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4222222222222222,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.551948051948052,
      "success_rate.epoch.env.math": 0.9594594594594594,
      "success_rate.epoch.env.sat": 0.09615384615384616,
      "success_rate.epoch.env.science": 0.9298029556650246,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6765802031248488,
      "success_rate.epoch.global": 0.8210609659540776,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9978861043194784,
      "tokens_p.mean_in_band": 0.5142045454545454,
      "tokens_rate.above_band": 0.9653815892997639,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03461841070023604
    },
    {
      "epoch": 1.112034574468085,
      "grad_norm": 317.2967101021701,
      "learning_rate": 1.7706646121173662e-07,
      "loss": 0.5627,
      "step": 6690,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.53125,
      "success_rate.epoch.env.logic": 0.5414012738853503,
      "success_rate.epoch.env.math": 0.9594594594594594,
      "success_rate.epoch.env.sat": 0.09433962264150944,
      "success_rate.epoch.env.science": 0.9300613496932515,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6760201682370098,
      "success_rate.epoch.global": 0.8183962264150944,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9959561638591118,
      "tokens_p.mean_in_band": 0.6730891047297297,
      "tokens_rate.above_band": 0.9724497393894267,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027550260610573342
    },
    {
      "epoch": 1.1128656914893618,
      "grad_norm": 63.73480798988222,
      "learning_rate": 1.7704010800384317e-07,
      "loss": 0.373,
      "step": 6695,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5408805031446541,
      "success_rate.epoch.env.math": 0.959731543624161,
      "success_rate.epoch.env.sat": 0.09433962264150944,
      "success_rate.epoch.env.science": 0.9305724725943971,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6773353483988003,
      "success_rate.epoch.global": 0.8190327613104524,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9955694211409396,
      "tokens_p.mean_in_band": 0.75,
      "tokens_rate.above_band": 0.9770491803278688,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022950819672131147
    },
    {
      "epoch": 1.1136968085106382,
      "grad_norm": 321.201272462513,
      "learning_rate": 1.7701376004903286e-07,
      "loss": 0.2956,
      "step": 6700,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5454545454545454,
      "success_rate.epoch.env.logic": 0.5403726708074534,
      "success_rate.epoch.env.math": 0.96,
      "success_rate.epoch.env.sat": 0.09433962264150944,
      "success_rate.epoch.env.science": 0.9311594202898551,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6773669458291728,
      "success_rate.epoch.global": 0.8196594427244582,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953330893118595,
      "tokens_p.mean_in_band": 0.48674242424242425,
      "tokens_rate.above_band": 0.9539106145251397,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.046089385474860335
    },
    {
      "epoch": 1.114527925531915,
      "grad_norm": 33.41784353791032,
      "learning_rate": 1.7698741739406688e-07,
      "loss": 0.28,
      "step": 6705,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5142857142857142,
      "success_rate.epoch.env.logic": 0.5403726708074534,
      "success_rate.epoch.env.math": 0.9536423841059603,
      "success_rate.epoch.env.sat": 0.09259259259259259,
      "success_rate.epoch.env.science": 0.9316546762589928,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6738416529980227,
      "success_rate.epoch.global": 0.8179723502304147,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9920530439249936,
      "tokens_p.mean_below_band": 8.195638656616211e-08,
      "tokens_p.mean_in_band": 0.5544701506955177,
      "tokens_rate.above_band": 0.8571114046675473,
      "tokens_rate.below_band": 0.00044033465433729633,
      "tokens_rate.in_band": 0.14244826067811536
    },
    {
      "epoch": 1.1153590425531914,
      "grad_norm": 127.26792432193703,
      "learning_rate": 1.7696108008569696e-07,
      "loss": 0.4732,
      "step": 6710,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5142857142857142,
      "success_rate.epoch.env.logic": 0.5403726708074534,
      "success_rate.epoch.env.math": 0.954248366013072,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.930952380952381,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6736798516268407,
      "success_rate.epoch.global": 0.8176964149504196,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9922794117647059,
      "tokens_p.mean_in_band": 0.5978190104166666,
      "tokens_rate.above_band": 0.8762886597938144,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12371134020618557
    },
    {
      "epoch": 1.116190159574468,
      "grad_norm": 129.62614352338232,
      "learning_rate": 1.7693474817066541e-07,
      "loss": 0.4258,
      "step": 6715,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5142857142857142,
      "success_rate.epoch.env.logic": 0.5432098765432098,
      "success_rate.epoch.env.math": 0.9545454545454546,
      "success_rate.epoch.env.sat": 0.08928571428571429,
      "success_rate.epoch.env.science": 0.9303423848878394,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6737617535886791,
      "success_rate.epoch.global": 0.817562452687358,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9890046296296297,
      "tokens_p.mean_in_band": 0.6699695121951219,
      "tokens_rate.above_band": 0.8404669260700389,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15953307392996108
    },
    {
      "epoch": 1.1170212765957448,
      "grad_norm": 69.63332027970154,
      "learning_rate": 1.7690842169570488e-07,
      "loss": 0.4512,
      "step": 6720,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.41304347826086957,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5142857142857142,
      "success_rate.epoch.env.logic": 0.5432098765432098,
      "success_rate.epoch.env.math": 0.9487179487179487,
      "success_rate.epoch.env.sat": 0.08928571428571429,
      "success_rate.epoch.env.science": 0.9309941520467836,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6732912318915371,
      "success_rate.epoch.global": 0.8181818181818182,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_below_band": 3.688037395477295e-07,
      "tokens_p.mean_in_band": 0.7065972222222222,
      "tokens_rate.above_band": 0.8875739644970414,
      "tokens_rate.below_band": 0.005917159763313609,
      "tokens_rate.in_band": 0.10650887573964497
    },
    {
      "epoch": 1.1178523936170213,
      "grad_norm": 39.59744733736173,
      "learning_rate": 1.7688210070753845e-07,
      "loss": 0.3412,
      "step": 6725,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5460122699386503,
      "success_rate.epoch.env.math": 0.9487179487179487,
      "success_rate.epoch.env.sat": 0.08928571428571429,
      "success_rate.epoch.env.science": 0.9292343387470998,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6732226230226998,
      "success_rate.epoch.global": 0.8173005219985086,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.6785714285714286,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9921013570822731,
      "tokens_p.mean_in_band": 0.5661638166520979,
      "tokens_rate.above_band": 0.8607933803845218,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13920661961547823
    },
    {
      "epoch": 1.118683510638298,
      "grad_norm": 98.55493715977076,
      "learning_rate": 1.7685578525287943e-07,
      "loss": 0.2633,
      "step": 6730,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5460122699386503,
      "success_rate.epoch.env.math": 0.9493670886075949,
      "success_rate.epoch.env.sat": 0.08771929824561403,
      "success_rate.epoch.env.science": 0.9295612009237876,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6731689490250846,
      "success_rate.epoch.global": 0.8175074183976261,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9980101302460203,
      "tokens_p.mean_in_band": 0.5940504807692307,
      "tokens_rate.above_band": 0.9300134589502019,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06998654104979811
    },
    {
      "epoch": 1.1195146276595744,
      "grad_norm": 152.38908670459642,
      "learning_rate": 1.7682947537843127e-07,
      "loss": 0.3353,
      "step": 6735,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5481927710843374,
      "success_rate.epoch.env.math": 0.9493670886075949,
      "success_rate.epoch.env.sat": 0.08771929824561403,
      "success_rate.epoch.env.science": 0.9298850574712644,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6746251191347826,
      "success_rate.epoch.global": 0.8178466076696165,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998750734861846,
      "tokens_p.mean_in_band": 0.6797572544642857,
      "tokens_rate.above_band": 0.989145183175034,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010854816824966078
    },
    {
      "epoch": 1.1203457446808511,
      "grad_norm": 39.96993542782013,
      "learning_rate": 1.7680317113088756e-07,
      "loss": 0.2907,
      "step": 6740,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5481927710843374,
      "success_rate.epoch.env.math": 0.94375,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.9304446978335233,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6740278600493984,
      "success_rate.epoch.global": 0.8177159590043924,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9905598958333334,
      "tokens_p.mean_below_band": 3.342393029015511e-11,
      "tokens_p.mean_in_band": 0.6711309523809523,
      "tokens_rate.above_band": 0.897196261682243,
      "tokens_rate.below_band": 0.004672897196261682,
      "tokens_rate.in_band": 0.09813084112149532
    },
    {
      "epoch": 1.1211768617021276,
      "grad_norm": 35.22668115796592,
      "learning_rate": 1.7677687255693193e-07,
      "loss": 0.461,
      "step": 6745,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5562130177514792,
      "success_rate.epoch.env.math": 0.9440993788819876,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.9308390022675737,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.659673065805445,
      "success_rate.epoch.global": 0.8183139534883721,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966302952503209,
      "tokens_p.mean_in_band": 0.7945667613636364,
      "tokens_rate.above_band": 0.9860759493670886,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013924050632911392
    },
    {
      "epoch": 1.1220079787234043,
      "grad_norm": 101.40195444705066,
      "learning_rate": 1.7675057970323786e-07,
      "loss": 0.282,
      "step": 6750,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5529411764705883,
      "success_rate.epoch.env.math": 0.9440993788819876,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.9302587176602924,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6593228725428839,
      "success_rate.epoch.global": 0.8179190751445087,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.4375,
      "success_rate.window.global": 0.7777777777777778,
      "tokens_p.mean_above_band": 0.9962630792227205,
      "tokens_p.mean_below_band": 1.2278178473934531e-11,
      "tokens_p.mean_in_band": 0.6395474137931034,
      "tokens_rate.above_band": 0.9570815450643777,
      "tokens_rate.below_band": 0.001430615164520744,
      "tokens_rate.in_band": 0.04148783977110158
    },
    {
      "epoch": 1.1228390957446808,
      "grad_norm": 62.65569055804822,
      "learning_rate": 1.7672429261646874e-07,
      "loss": 0.2613,
      "step": 6755,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5523255813953488,
      "success_rate.epoch.env.math": 0.9440993788819876,
      "success_rate.epoch.env.sat": 0.0847457627118644,
      "success_rate.epoch.env.science": 0.9305711086226204,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6591624781835411,
      "success_rate.epoch.global": 0.8173975557153127,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9998337765957447,
      "tokens_p.mean_in_band": 0.7383897569444444,
      "tokens_rate.above_band": 0.9543147208121827,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04568527918781726
    },
    {
      "epoch": 1.1236702127659575,
      "grad_norm": 25.068913038088763,
      "learning_rate": 1.7669801134327773e-07,
      "loss": 0.3015,
      "step": 6760,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5523255813953488,
      "success_rate.epoch.env.math": 0.9454545454545454,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9309576837416481,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6591924156665461,
      "success_rate.epoch.global": 0.8179871520342612,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9948660714285714,
      "tokens_p.mean_in_band": 0.5250459558823529,
      "tokens_rate.above_band": 0.89171974522293,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10828025477707007
    },
    {
      "epoch": 1.124501329787234,
      "grad_norm": 99.21289280221266,
      "learning_rate": 1.7667173593030764e-07,
      "loss": 0.3883,
      "step": 6765,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5491329479768786,
      "success_rate.epoch.env.math": 0.9457831325301205,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9314159292035398,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6589737064955457,
      "success_rate.epoch.global": 0.8184397163120567,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9922843855693348,
      "tokens_p.mean_in_band": 0.6683238636363636,
      "tokens_rate.above_band": 0.9641304347826087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.035869565217391305
    },
    {
      "epoch": 1.1253324468085106,
      "grad_norm": 30.03715969336156,
      "learning_rate": 1.7664546642419087e-07,
      "loss": 0.2374,
      "step": 6770,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.425531914893617,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5517241379310345,
      "success_rate.epoch.env.math": 0.9461077844311377,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.9308452250274424,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6590627080828636,
      "success_rate.epoch.global": 0.8183098591549296,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9915865384615384,
      "tokens_p.mean_in_band": 0.5603298611111112,
      "tokens_rate.above_band": 0.9059233449477352,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09407665505226481
    },
    {
      "epoch": 1.1261635638297873,
      "grad_norm": 133.4325439584598,
      "learning_rate": 1.7661920287154938e-07,
      "loss": 0.327,
      "step": 6775,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5517241379310345,
      "success_rate.epoch.env.math": 0.9467455621301775,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.9312977099236641,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6602498306011949,
      "success_rate.epoch.global": 0.8194541637508748,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9962197580645161,
      "tokens_p.mean_in_band": 0.849609375,
      "tokens_rate.above_band": 0.992,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008
    },
    {
      "epoch": 1.1269946808510638,
      "grad_norm": 65.87937973731965,
      "learning_rate": 1.7659294531899452e-07,
      "loss": 0.3323,
      "step": 6780,
      "success_rate.epoch.env.abd": 0.6666666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5511363636363636,
      "success_rate.epoch.env.math": 0.9473684210526315,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.9315960912052117,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6602801456838613,
      "success_rate.epoch.global": 0.8197633959638135,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9927536231884058,
      "tokens_p.mean_in_band": 0.7765213815789473,
      "tokens_rate.above_band": 0.9355932203389831,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06440677966101695
    },
    {
      "epoch": 1.1278257978723405,
      "grad_norm": 391.60418009006275,
      "learning_rate": 1.7656669381312709e-07,
      "loss": 0.5243,
      "step": 6785,
      "success_rate.epoch.env.abd": 0.6153846153846154,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5511363636363636,
      "success_rate.epoch.env.math": 0.9473684210526315,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.9311087190527448,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6555738344625414,
      "success_rate.epoch.global": 0.8195020746887967,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9906754032258065,
      "tokens_p.mean_in_band": 0.30725400309917356,
      "tokens_rate.above_band": 0.6720867208672087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.32791327913279134
    },
    {
      "epoch": 1.128656914893617,
      "grad_norm": 40.94470397575009,
      "learning_rate": 1.7654044840053695e-07,
      "loss": 0.2547,
      "step": 6790,
      "success_rate.epoch.env.abd": 0.6153846153846154,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5135135135135135,
      "success_rate.epoch.env.logic": 0.5480225988700564,
      "success_rate.epoch.env.math": 0.9476744186046512,
      "success_rate.epoch.env.sat": 0.08196721311475409,
      "success_rate.epoch.env.science": 0.9305555555555556,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6552682953069526,
      "success_rate.epoch.global": 0.8192439862542955,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995751953125,
      "tokens_p.mean_below_band": 1.0277290130034089e-10,
      "tokens_p.mean_in_band": 0.6383634868421053,
      "tokens_rate.above_band": 0.9696969696969697,
      "tokens_rate.below_band": 0.0015151515151515152,
      "tokens_rate.in_band": 0.02878787878787879
    },
    {
      "epoch": 1.1294880319148937,
      "grad_norm": 28.70464866070665,
      "learning_rate": 1.7651420912780338e-07,
      "loss": 0.3405,
      "step": 6795,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5480225988700564,
      "success_rate.epoch.env.math": 0.9479768786127167,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.9288747346072187,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.649798298012929,
      "success_rate.epoch.global": 0.8170648464163822,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9929052638927673,
      "tokens_p.mean_below_band": 3.4051481634378433e-09,
      "tokens_p.mean_in_band": 0.45220144752714114,
      "tokens_rate.above_band": 0.8118340512355475,
      "tokens_rate.below_band": 0.00022670596236681024,
      "tokens_rate.in_band": 0.18793924280208568
    },
    {
      "epoch": 1.1303191489361701,
      "grad_norm": 47.05704692588445,
      "learning_rate": 1.764879760414946e-07,
      "loss": 0.3716,
      "step": 6800,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5480225988700564,
      "success_rate.epoch.env.math": 0.9485714285714286,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.9294736842105263,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6499067979731126,
      "success_rate.epoch.global": 0.8183050847457627,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9880208333333333,
      "tokens_p.mean_in_band": 0.8515625,
      "tokens_rate.above_band": 0.96,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04
    },
    {
      "epoch": 1.1311502659574468,
      "grad_norm": 38.91865692725673,
      "learning_rate": 1.7646174918816797e-07,
      "loss": 0.3599,
      "step": 6805,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.550561797752809,
      "success_rate.epoch.env.math": 0.949438202247191,
      "success_rate.epoch.env.sat": 0.08064516129032258,
      "success_rate.epoch.env.science": 0.9296956977964324,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6502366148953326,
      "success_rate.epoch.global": 0.8191632928475033,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.989321608040201,
      "tokens_p.mean_in_band": 0.8216145833333334,
      "tokens_rate.above_band": 0.9707317073170731,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02926829268292683
    },
    {
      "epoch": 1.1319813829787235,
      "grad_norm": 95.56899990127589,
      "learning_rate": 1.7643552861436969e-07,
      "loss": 0.29,
      "step": 6810,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.55,
      "success_rate.epoch.env.math": 0.9497206703910615,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.9301355578727841,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501348374900754,
      "success_rate.epoch.global": 0.8190348525469169,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99528452685422,
      "tokens_p.mean_in_band": 0.7050189393939394,
      "tokens_rate.above_band": 0.9595092024539877,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04049079754601227
    },
    {
      "epoch": 1.1328125,
      "grad_norm": 96.3758866676662,
      "learning_rate": 1.7640931436663485e-07,
      "loss": 0.4175,
      "step": 6815,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.546448087431694,
      "success_rate.epoch.env.math": 0.95,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.9304257528556594,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6498637113103943,
      "success_rate.epoch.global": 0.8186666666666667,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9983157319737801,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_p.mean_in_band": 0.4875616776315789,
      "tokens_rate.above_band": 0.9723796033994334,
      "tokens_rate.below_band": 0.000708215297450425,
      "tokens_rate.in_band": 0.026912181303116147
    },
    {
      "epoch": 1.1336436170212765,
      "grad_norm": 53.3378040922987,
      "learning_rate": 1.7638310649148736e-07,
      "loss": 0.182,
      "step": 6820,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.546448087431694,
      "success_rate.epoch.env.math": 0.9505494505494505,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.9307851239669421,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6511118326268712,
      "success_rate.epoch.global": 0.8196286472148541,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9907309322033898,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9957805907172996,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004219409282700422
    },
    {
      "epoch": 1.1344747340425532,
      "grad_norm": 50.54492177090908,
      "learning_rate": 1.7635690503543972e-07,
      "loss": 0.3292,
      "step": 6825,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.546448087431694,
      "success_rate.epoch.env.math": 0.9513513513513514,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.9301848049281314,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6511301582416976,
      "success_rate.epoch.global": 0.8200395517468688,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9855603448275863,
      "tokens_p.mean_in_band": 0.6984375,
      "tokens_rate.above_band": 0.9354838709677419,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06451612903225806
    },
    {
      "epoch": 1.1353058510638299,
      "grad_norm": 68.55294102550499,
      "learning_rate": 1.7633071004499315e-07,
      "loss": 0.3155,
      "step": 6830,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.5489130434782609,
      "success_rate.epoch.env.math": 0.9521276595744681,
      "success_rate.epoch.env.sat": 0.07936507936507936,
      "success_rate.epoch.env.science": 0.9306122448979591,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6514636768089259,
      "success_rate.epoch.global": 0.8212180746561886,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9915730337078652,
      "tokens_p.mean_in_band": 0.876953125,
      "tokens_rate.above_band": 0.978021978021978,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02197802197802198
    },
    {
      "epoch": 1.1361369680851063,
      "grad_norm": 42.58266757112919,
      "learning_rate": 1.763045215666373e-07,
      "loss": 0.3828,
      "step": 6835,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.5459459459459459,
      "success_rate.epoch.env.math": 0.9528795811518325,
      "success_rate.epoch.env.sat": 0.078125,
      "success_rate.epoch.env.science": 0.9309644670050762,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6511815828804792,
      "success_rate.epoch.global": 0.8210800260247235,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9936170212765958,
      "tokens_p.mean_in_band": 0.6022518382352942,
      "tokens_rate.above_band": 0.9325396825396826,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06746031746031746
    },
    {
      "epoch": 1.136968085106383,
      "grad_norm": 69.81921572926505,
      "learning_rate": 1.762783396468503e-07,
      "loss": 0.2686,
      "step": 6840,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.5508021390374331,
      "success_rate.epoch.env.math": 0.953125,
      "success_rate.epoch.env.sat": 0.078125,
      "success_rate.epoch.env.science": 0.9313131313131313,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6553180643946495,
      "success_rate.epoch.global": 0.8222365869424693,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9946714031971581,
      "tokens_p.mean_in_band": 0.8251953125,
      "tokens_rate.above_band": 0.9791304347826087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020869565217391306
    },
    {
      "epoch": 1.1377992021276595,
      "grad_norm": 94.35806235990412,
      "learning_rate": 1.7625216433209866e-07,
      "loss": 0.2955,
      "step": 6845,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5478723404255319,
      "success_rate.epoch.env.math": 0.9533678756476683,
      "success_rate.epoch.env.sat": 0.07575757575757576,
      "success_rate.epoch.env.science": 0.9306532663316583,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6536330893938638,
      "success_rate.epoch.global": 0.8201669877970456,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.36,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9957966141001855,
      "tokens_p.mean_in_band": 0.6857638888888888,
      "tokens_rate.above_band": 0.9089376053962901,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09106239460370995
    },
    {
      "epoch": 1.1386303191489362,
      "grad_norm": 70.99910087080949,
      "learning_rate": 1.7622599566883721e-07,
      "loss": 0.3005,
      "step": 6850,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5478723404255319,
      "success_rate.epoch.env.math": 0.9540816326530612,
      "success_rate.epoch.env.sat": 0.07575757575757576,
      "success_rate.epoch.env.science": 0.9301397205588823,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6536512904150108,
      "success_rate.epoch.global": 0.8206764518187619,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9888059701492538,
      "tokens_p.mean_in_band": 0.69375,
      "tokens_rate.above_band": 0.8993288590604027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10067114093959731
    },
    {
      "epoch": 1.1394614361702127,
      "grad_norm": 108.21024004665557,
      "learning_rate": 1.761998337035088e-07,
      "loss": 0.3995,
      "step": 6855,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5478723404255319,
      "success_rate.epoch.env.math": 0.9545454545454546,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.9295634920634921,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6535382798069261,
      "success_rate.epoch.global": 0.8204314720812182,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9898026315789473,
      "tokens_p.mean_in_band": 0.5434027777777778,
      "tokens_rate.above_band": 0.9134615384615384,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08653846153846154
    },
    {
      "epoch": 1.1402925531914894,
      "grad_norm": 92.3439269604249,
      "learning_rate": 1.7617367848254458e-07,
      "loss": 0.3623,
      "step": 6860,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5478723404255319,
      "success_rate.epoch.env.math": 0.9547738693467337,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.9301868239921337,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.653615711327828,
      "success_rate.epoch.global": 0.8215636822194199,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9861778846153846,
      "tokens_p.mean_in_band": 0.8470052083333334,
      "tokens_rate.above_band": 0.9629629629629629,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037037037037037035
    },
    {
      "epoch": 1.141123670212766,
      "grad_norm": 73.52560284614265,
      "learning_rate": 1.7614753005236367e-07,
      "loss": 0.2576,
      "step": 6865,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5121951219512195,
      "success_rate.epoch.env.logic": 0.5473684210526316,
      "success_rate.epoch.env.math": 0.9552238805970149,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.9303921568627451,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6547381246641201,
      "success_rate.epoch.global": 0.821831869510665,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9905007102272727,
      "tokens_p.mean_in_band": 0.7652439024390244,
      "tokens_rate.above_band": 0.971704623878537,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028295376121463076
    },
    {
      "epoch": 1.1419547872340425,
      "grad_norm": 152.0024369408406,
      "learning_rate": 1.7612138845937307e-07,
      "loss": 0.311,
      "step": 6870,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5121951219512195,
      "success_rate.epoch.env.logic": 0.5416666666666666,
      "success_rate.epoch.env.math": 0.9554455445544554,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.9307992202729045,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6541771718527291,
      "success_rate.epoch.global": 0.821072319201995,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.998793242156074,
      "tokens_p.mean_in_band": 0.5978190104166666,
      "tokens_rate.above_band": 0.9628195197521301,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037180480247869865
    },
    {
      "epoch": 1.1427859042553192,
      "grad_norm": 61.435888614597644,
      "learning_rate": 1.7609525374996777e-07,
      "loss": 0.2541,
      "step": 6875,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5121951219512195,
      "success_rate.epoch.env.logic": 0.5440414507772021,
      "success_rate.epoch.env.math": 0.9556650246305419,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.9312015503875969,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6544495895164849,
      "success_rate.epoch.global": 0.8219602977667494,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9869909502262444,
      "tokens_p.mean_in_band": 0.7719350961538461,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05555555555555555
    },
    {
      "epoch": 1.1436170212765957,
      "grad_norm": 59.507457528148194,
      "learning_rate": 1.7606912597053042e-07,
      "loss": 0.2177,
      "step": 6880,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5121951219512195,
      "success_rate.epoch.env.logic": 0.5412371134020618,
      "success_rate.epoch.env.math": 0.9556650246305419,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.9315992292870906,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6542308023823352,
      "success_rate.epoch.global": 0.8221124150710315,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9889838129496403,
      "tokens_p.mean_in_band": 0.7447150735294118,
      "tokens_rate.above_band": 0.9423728813559322,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0576271186440678
    },
    {
      "epoch": 1.1444481382978724,
      "grad_norm": 62.537202015013435,
      "learning_rate": 1.7604300516743147e-07,
      "loss": 0.3482,
      "step": 6885,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5238095238095238,
      "success_rate.epoch.env.logic": 0.5412371134020618,
      "success_rate.epoch.env.math": 0.9514563106796117,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.9319271332694151,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6549338561904897,
      "success_rate.epoch.global": 0.8224815724815725,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9900778931750742,
      "tokens_p.mean_below_band": 4.3655745685100555e-09,
      "tokens_p.mean_in_band": 0.827880859375,
      "tokens_rate.above_band": 0.975397973950796,
      "tokens_rate.below_band": 0.001447178002894356,
      "tokens_rate.in_band": 0.023154848046309694
    },
    {
      "epoch": 1.1452792553191489,
      "grad_norm": 123.77716928348676,
      "learning_rate": 1.7601689138702892e-07,
      "loss": 0.2899,
      "step": 6890,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5238095238095238,
      "success_rate.epoch.env.logic": 0.5459183673469388,
      "success_rate.epoch.env.math": 0.9519230769230769,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.9322519083969466,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6554313830373872,
      "success_rate.epoch.global": 0.8234575442883323,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.989406779661017,
      "tokens_p.mean_in_band": 0.7365056818181818,
      "tokens_rate.above_band": 0.9554655870445344,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044534412955465584
    },
    {
      "epoch": 1.1461103723404256,
      "grad_norm": 57.1500794088816,
      "learning_rate": 1.7599078467566835e-07,
      "loss": 0.5215,
      "step": 6895,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5238095238095238,
      "success_rate.epoch.env.logic": 0.5482233502538071,
      "success_rate.epoch.env.math": 0.9473684210526315,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.9324452901998097,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6550534619922191,
      "success_rate.epoch.global": 0.8223844282238443,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9996141975308642,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.6627394153225806,
      "tokens_rate.above_band": 0.9278350515463918,
      "tokens_rate.below_band": 0.001145475372279496,
      "tokens_rate.in_band": 0.07101947308132875
    },
    {
      "epoch": 1.146941489361702,
      "grad_norm": 101.67079559653851,
      "learning_rate": 1.7596468507968277e-07,
      "loss": 0.4918,
      "step": 6900,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5238095238095238,
      "success_rate.epoch.env.logic": 0.545,
      "success_rate.epoch.env.math": 0.9481132075471698,
      "success_rate.epoch.env.sat": 0.07142857142857142,
      "success_rate.epoch.env.science": 0.9326375711574952,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6548456181011661,
      "success_rate.epoch.global": 0.822141560798548,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6944444444444443,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973605577689243,
      "tokens_p.mean_below_band": 3.4051481634378433e-09,
      "tokens_p.mean_in_band": 0.5270743534482759,
      "tokens_rate.above_band": 0.9766536964980544,
      "tokens_rate.below_band": 0.0007782101167315176,
      "tokens_rate.in_band": 0.022568093385214007
    },
    {
      "epoch": 1.1477726063829787,
      "grad_norm": 178.91768525544094,
      "learning_rate": 1.7593859264539255e-07,
      "loss": 0.3124,
      "step": 6905,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4489795918367347,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5238095238095238,
      "success_rate.epoch.env.logic": 0.5495049504950495,
      "success_rate.epoch.env.math": 0.9485981308411215,
      "success_rate.epoch.env.sat": 0.07042253521126761,
      "success_rate.epoch.env.science": 0.9328922495274102,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6552309377322219,
      "success_rate.epoch.global": 0.822503008423586,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9923433048433048,
      "tokens_p.mean_in_band": 0.7178308823529411,
      "tokens_rate.above_band": 0.9116883116883117,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08831168831168831
    },
    {
      "epoch": 1.1486037234042552,
      "grad_norm": 24.327930505453125,
      "learning_rate": 1.7591250741910537e-07,
      "loss": 0.3752,
      "step": 6910,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5517241379310345,
      "success_rate.epoch.env.math": 0.9488372093023256,
      "success_rate.epoch.env.sat": 0.06944444444444445,
      "success_rate.epoch.env.science": 0.9332079021636877,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6534704485592336,
      "success_rate.epoch.global": 0.8217703349282297,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942561267980821,
      "tokens_p.mean_below_band": 3.4051481634378433e-09,
      "tokens_p.mean_in_band": 0.5106281725888325,
      "tokens_rate.above_band": 0.9047963364666185,
      "tokens_rate.below_band": 0.00024102193299590263,
      "tokens_rate.in_band": 0.09496264160038563
    },
    {
      "epoch": 1.149434840425532,
      "grad_norm": 79.71076470764915,
      "learning_rate": 1.7588642944711615e-07,
      "loss": 0.3466,
      "step": 6915,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5517241379310345,
      "success_rate.epoch.env.math": 0.9444444444444444,
      "success_rate.epoch.env.sat": 0.06944444444444445,
      "success_rate.epoch.env.science": 0.9337068160597572,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6531164621081598,
      "success_rate.epoch.global": 0.8221296847114813,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9874031007751938,
      "tokens_p.mean_below_band": 2.9976945370435715e-09,
      "tokens_p.mean_in_band": 0.87109375,
      "tokens_rate.above_band": 0.9772727272727273,
      "tokens_rate.below_band": 0.007575757575757576,
      "tokens_rate.in_band": 0.015151515151515152
    },
    {
      "epoch": 1.1502659574468086,
      "grad_norm": 84.51212873306991,
      "learning_rate": 1.758603587757069e-07,
      "loss": 0.3921,
      "step": 6920,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5485436893203883,
      "success_rate.epoch.env.math": 0.944954128440367,
      "success_rate.epoch.env.sat": 0.0684931506849315,
      "success_rate.epoch.env.science": 0.933953488372093,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6528096088298052,
      "success_rate.epoch.global": 0.8214074512123004,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981060606060606,
      "tokens_p.mean_in_band": 0.6362847222222222,
      "tokens_rate.above_band": 0.9720930232558139,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027906976744186046
    },
    {
      "epoch": 1.151097074468085,
      "grad_norm": 76.92137550398597,
      "learning_rate": 1.7583429545114663e-07,
      "loss": 0.3761,
      "step": 6925,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5485436893203883,
      "success_rate.epoch.env.math": 0.9459459459459459,
      "success_rate.epoch.env.sat": 0.0684931506849315,
      "success_rate.epoch.env.science": 0.9342592592592592,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6529275714109638,
      "success_rate.epoch.global": 0.8223529411764706,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.990625,
      "tokens_p.mean_in_band": 0.6796875,
      "tokens_rate.above_band": 0.9917355371900827,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008264462809917356
    },
    {
      "epoch": 1.1519281914893618,
      "grad_norm": 100.83000719757341,
      "learning_rate": 1.758082395196914e-07,
      "loss": 0.3032,
      "step": 6930,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5528846153846154,
      "success_rate.epoch.env.math": 0.9459459459459459,
      "success_rate.epoch.env.sat": 0.06756756756756757,
      "success_rate.epoch.env.science": 0.9337626494940202,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6531929107911115,
      "success_rate.epoch.global": 0.8222222222222222,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943181818181818,
      "tokens_p.mean_in_band": 0.5801630434782609,
      "tokens_rate.above_band": 0.928125,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.071875
    },
    {
      "epoch": 1.1527593085106382,
      "grad_norm": 47.26800670644467,
      "learning_rate": 1.7578219102758406e-07,
      "loss": 0.1893,
      "step": 6935,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5476190476190477,
      "success_rate.epoch.env.math": 0.9459459459459459,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9340659340659341,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6526598940552429,
      "success_rate.epoch.global": 0.8213038416763678,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977334104938271,
      "tokens_p.mean_in_band": 0.5945172991071429,
      "tokens_rate.above_band": 0.9585798816568047,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04142011834319527
    },
    {
      "epoch": 1.153590425531915,
      "grad_norm": 123.17156960894862,
      "learning_rate": 1.7575615002105437e-07,
      "loss": 0.5311,
      "step": 6940,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5450236966824644,
      "success_rate.epoch.env.math": 0.9461883408071748,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9335154826958105,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6523959479238358,
      "success_rate.epoch.global": 0.8209733487833141,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9989905196629213,
      "tokens_p.mean_in_band": 0.63648681640625,
      "tokens_rate.above_band": 0.9468085106382979,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05319148936170213
    },
    {
      "epoch": 1.1544215425531914,
      "grad_norm": 35.35487462564525,
      "learning_rate": 1.757301165463187e-07,
      "loss": 0.2618,
      "step": 6945,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4423076923076923,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5116279069767442,
      "success_rate.epoch.env.logic": 0.5492957746478874,
      "success_rate.epoch.env.math": 0.9461883408071748,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9337568058076225,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6529363025058786,
      "success_rate.epoch.global": 0.8207492795389049,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982972756410257,
      "tokens_p.mean_in_band": 0.6156684027777778,
      "tokens_rate.above_band": 0.9719626168224299,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028037383177570093
    },
    {
      "epoch": 1.155252659574468,
      "grad_norm": 157.5594518718164,
      "learning_rate": 1.7570409064958004e-07,
      "loss": 0.2543,
      "step": 6950,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4423076923076923,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5492957746478874,
      "success_rate.epoch.env.math": 0.9464285714285714,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9341155234657039,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6519336698970363,
      "success_rate.epoch.global": 0.8209982788296041,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9911369554924242,
      "tokens_p.mean_in_band": 0.5535351138828634,
      "tokens_rate.above_band": 0.8208317139525846,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.17916828604741547
    },
    {
      "epoch": 1.1560837765957448,
      "grad_norm": 72.8843058128863,
      "learning_rate": 1.7567807237702804e-07,
      "loss": 0.3149,
      "step": 6955,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4423076923076923,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5492957746478874,
      "success_rate.epoch.env.math": 0.9469026548672567,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9336917562724014,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6519382441011619,
      "success_rate.epoch.global": 0.8214489446662864,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9887019230769231,
      "tokens_p.mean_below_band": 8.754432201385498e-08,
      "tokens_p.mean_in_band": 0.86328125,
      "tokens_rate.above_band": 0.9629629629629629,
      "tokens_rate.below_band": 0.007407407407407408,
      "tokens_rate.in_band": 0.02962962962962963
    },
    {
      "epoch": 1.1569148936170213,
      "grad_norm": 56.63815850444694,
      "learning_rate": 1.7565206177483877e-07,
      "loss": 0.2096,
      "step": 6960,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4423076923076923,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5514018691588785,
      "success_rate.epoch.env.math": 0.9475982532751092,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9339875111507583,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6522198302645438,
      "success_rate.epoch.global": 0.822360953461975,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9891877637130801,
      "tokens_p.mean_in_band": 0.8441051136363636,
      "tokens_rate.above_band": 0.9556451612903226,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04435483870967742
    },
    {
      "epoch": 1.157746010638298,
      "grad_norm": 84.65821011976759,
      "learning_rate": 1.7562605888917462e-07,
      "loss": 0.3921,
      "step": 6965,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5488372093023256,
      "success_rate.epoch.env.math": 0.9475982532751092,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9342806394316163,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6502445510969479,
      "success_rate.epoch.global": 0.8214689265536723,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.2,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9986020108450068,
      "tokens_p.mean_below_band": 1.6880221664905548e-09,
      "tokens_p.mean_in_band": 0.3689205545774648,
      "tokens_rate.above_band": 0.9391046042860174,
      "tokens_rate.below_band": 0.0006365372374283895,
      "tokens_rate.in_band": 0.06025885847655421
    },
    {
      "epoch": 1.1585771276595744,
      "grad_norm": 33.6778048202698,
      "learning_rate": 1.7560006376618442e-07,
      "loss": 0.2421,
      "step": 6970,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5462962962962963,
      "success_rate.epoch.env.math": 0.9478260869565217,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9347442680776014,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6500764192170723,
      "success_rate.epoch.global": 0.8219101123595506,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.999420401854714,
      "tokens_p.mean_in_band": 0.5535714285714286,
      "tokens_rate.above_band": 0.9788199697428139,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02118003025718608
    },
    {
      "epoch": 1.1594082446808511,
      "grad_norm": 248.1887875816634,
      "learning_rate": 1.7557407645200306e-07,
      "loss": 0.3623,
      "step": 6975,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5458715596330275,
      "success_rate.epoch.env.math": 0.9484978540772532,
      "success_rate.epoch.env.sat": 0.06578947368421052,
      "success_rate.epoch.env.science": 0.9348591549295775,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501093207906576,
      "success_rate.epoch.global": 0.8220481253497481,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9999571917808219,
      "tokens_p.mean_in_band": 0.6028645833333334,
      "tokens_rate.above_band": 0.9878213802435724,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012178619756427604
    },
    {
      "epoch": 1.1602393617021276,
      "grad_norm": 106.84248333089963,
      "learning_rate": 1.7554809699275171e-07,
      "loss": 0.4171,
      "step": 6980,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5458715596330275,
      "success_rate.epoch.env.math": 0.9487179487179487,
      "success_rate.epoch.env.sat": 0.06493506493506493,
      "success_rate.epoch.env.science": 0.9351446099912357,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6510877073419594,
      "success_rate.epoch.global": 0.8222841225626741,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9938563327032136,
      "tokens_p.mean_in_band": 0.729248046875,
      "tokens_rate.above_band": 0.9429590017825312,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0570409982174688
    },
    {
      "epoch": 1.1610704787234043,
      "grad_norm": 42.32926787228792,
      "learning_rate": 1.7552212543453752e-07,
      "loss": 0.5429,
      "step": 6985,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5458715596330275,
      "success_rate.epoch.env.math": 0.9491525423728814,
      "success_rate.epoch.env.sat": 0.06493506493506493,
      "success_rate.epoch.env.science": 0.9346689895470384,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6510839776338444,
      "success_rate.epoch.global": 0.8226164079822617,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9949723974763407,
      "tokens_p.mean_below_band": 2.8405338525772095e-08,
      "tokens_p.mean_in_band": 0.5094572368421053,
      "tokens_rate.above_band": 0.9694189602446484,
      "tokens_rate.below_band": 0.0015290519877675841,
      "tokens_rate.in_band": 0.0290519877675841
    },
    {
      "epoch": 1.1619015957446808,
      "grad_norm": 95.57475233336709,
      "learning_rate": 1.7549616182345367e-07,
      "loss": 0.3074,
      "step": 6990,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.547945205479452,
      "success_rate.epoch.env.math": 0.9497907949790795,
      "success_rate.epoch.env.sat": 0.06493506493506493,
      "success_rate.epoch.env.science": 0.9349522983521249,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.651356269202727,
      "success_rate.epoch.global": 0.8234969663541092,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9937042124542125,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9927272727272727,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007272727272727273
    },
    {
      "epoch": 1.1627327127659575,
      "grad_norm": 44.23898971664997,
      "learning_rate": 1.7547020620557919e-07,
      "loss": 0.2919,
      "step": 6995,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.55,
      "success_rate.epoch.env.math": 0.95,
      "success_rate.epoch.env.sat": 0.0641025641025641,
      "success_rate.epoch.env.science": 0.9351771823681936,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6515068494504577,
      "success_rate.epoch.global": 0.8236263736263736,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9955357142857143,
      "tokens_p.mean_below_band": 1.418811734765768e-09,
      "tokens_p.mean_in_band": 0.6554276315789473,
      "tokens_rate.above_band": 0.9180327868852459,
      "tokens_rate.below_band": 0.004098360655737705,
      "tokens_rate.in_band": 0.0778688524590164
    },
    {
      "epoch": 1.163563829787234,
      "grad_norm": 79.46399248260443,
      "learning_rate": 1.7544425862697895e-07,
      "loss": 0.3625,
      "step": 7000,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.545045045045045,
      "success_rate.epoch.env.math": 0.9504132231404959,
      "success_rate.epoch.env.sat": 0.06329113924050633,
      "success_rate.epoch.env.science": 0.9354005167958657,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6510405019732899,
      "success_rate.epoch.global": 0.8228540185893931,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9970846972176759,
      "tokens_p.mean_in_band": 0.5802859042553191,
      "tokens_rate.above_band": 0.9629629629629629,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037037037037037035
    },
    {
      "epoch": 1.1643949468085106,
      "grad_norm": 53.458921458680706,
      "learning_rate": 1.7541831913370352e-07,
      "loss": 0.3968,
      "step": 7005,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.545045045045045,
      "success_rate.epoch.env.math": 0.9504132231404959,
      "success_rate.epoch.env.sat": 0.06329113924050633,
      "success_rate.epoch.env.science": 0.9359521776259607,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6510906529578441,
      "success_rate.epoch.global": 0.8238172920065253,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9827205882352941,
      "tokens_p.mean_in_band": 0.80390625,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05555555555555555
    },
    {
      "epoch": 1.1652260638297873,
      "grad_norm": 82.14597967312726,
      "learning_rate": 1.753923877717892e-07,
      "loss": 0.2984,
      "step": 7010,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.545045045045045,
      "success_rate.epoch.env.math": 0.9508196721311475,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9361702127659575,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6510755024933115,
      "success_rate.epoch.global": 0.823943661971831,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9885714285714285,
      "tokens_p.mean_in_band": 0.609765625,
      "tokens_rate.above_band": 0.8974358974358975,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10256410256410256
    },
    {
      "epoch": 1.1660571808510638,
      "grad_norm": 72.68839523037914,
      "learning_rate": 1.7536646458725774e-07,
      "loss": 0.4131,
      "step": 7015,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5466666666666666,
      "success_rate.epoch.env.math": 0.9508196721311475,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9364944961896697,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6512524029519782,
      "success_rate.epoch.global": 0.8242587601078167,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9946911196911197,
      "tokens_p.mean_in_band": 0.7075520833333333,
      "tokens_rate.above_band": 0.9810606060606061,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01893939393939394
    },
    {
      "epoch": 1.1668882978723405,
      "grad_norm": 24.258893229879263,
      "learning_rate": 1.753405496261165e-07,
      "loss": 0.4125,
      "step": 7020,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4339622641509434,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4791666666666667,
      "success_rate.epoch.env.logic": 0.5466666666666666,
      "success_rate.epoch.env.math": 0.9510204081632653,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9359730412805392,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6493293072964922,
      "success_rate.epoch.global": 0.8234978540772532,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9940845792138896,
      "tokens_p.mean_below_band": 3.241002559661865e-07,
      "tokens_p.mean_in_band": 0.5438189338235294,
      "tokens_rate.above_band": 0.8901051727838591,
      "tokens_rate.below_band": 0.00042927666881305,
      "tokens_rate.in_band": 0.10946555054732775
    },
    {
      "epoch": 1.167719414893617,
      "grad_norm": 108.22967084602361,
      "learning_rate": 1.7531464293435813e-07,
      "loss": 0.3902,
      "step": 7025,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.5482456140350878,
      "success_rate.epoch.env.math": 0.951417004048583,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9361344537815126,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6495875095222728,
      "success_rate.epoch.global": 0.8233724653148345,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971825485382727,
      "tokens_p.mean_below_band": 3.9301812648773193e-07,
      "tokens_p.mean_in_band": 0.5773082386363636,
      "tokens_rate.above_band": 0.9529987239472565,
      "tokens_rate.below_band": 0.0002126754572522331,
      "tokens_rate.in_band": 0.04678860059549128
    },
    {
      "epoch": 1.1685505319148937,
      "grad_norm": 171.43690665886163,
      "learning_rate": 1.752887445579607e-07,
      "loss": 0.3781,
      "step": 7030,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.5478260869565217,
      "success_rate.epoch.env.math": 0.9516129032258065,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9363484087102177,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.649586630161124,
      "success_rate.epoch.global": 0.823498139287613,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976572958500669,
      "tokens_p.mean_in_band": 0.609619140625,
      "tokens_rate.above_band": 0.9790301441677588,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020969855832241154
    },
    {
      "epoch": 1.1693816489361701,
      "grad_norm": 83.67632789272761,
      "learning_rate": 1.752628545428875e-07,
      "loss": 0.2859,
      "step": 7035,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.5478260869565217,
      "success_rate.epoch.env.math": 0.952,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9358333333333333,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6487215634606938,
      "success_rate.epoch.global": 0.8232804232804233,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9886773875943551,
      "tokens_p.mean_in_band": 0.5463895281933256,
      "tokens_rate.above_band": 0.7780898876404494,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.22191011235955055
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 56.60002714041991,
      "learning_rate": 1.752369729350869e-07,
      "loss": 0.2696,
      "step": 7040,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.5497835497835498,
      "success_rate.epoch.env.math": 0.952191235059761,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.9360995850622407,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6498593779803944,
      "success_rate.epoch.global": 0.8240252897787145,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9947493224932249,
      "tokens_p.mean_in_band": 0.49609375,
      "tokens_rate.above_band": 0.9972972972972973,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.002702702702702703
    },
    {
      "epoch": 1.1710438829787235,
      "grad_norm": 164.5444256938949,
      "learning_rate": 1.7521109978049248e-07,
      "loss": 0.3965,
      "step": 7045,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.5536480686695279,
      "success_rate.epoch.env.math": 0.952191235059761,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.9363110008271298,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501597715906304,
      "success_rate.epoch.global": 0.8241469816272966,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9925271739130435,
      "tokens_p.mean_in_band": 0.7728125,
      "tokens_rate.above_band": 0.9169435215946844,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08305647840531562
    },
    {
      "epoch": 1.171875,
      "grad_norm": 85.49191193379976,
      "learning_rate": 1.751852351250227e-07,
      "loss": 0.3958,
      "step": 7050,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.5512820512820513,
      "success_rate.epoch.env.math": 0.952191235059761,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.9366776315789473,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6499780091692068,
      "success_rate.epoch.global": 0.8243596445373759,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972826086956522,
      "tokens_p.mean_in_band": 0.704483695652174,
      "tokens_rate.above_band": 0.9666666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03333333333333333
    },
    {
      "epoch": 1.1727061170212765,
      "grad_norm": 87.56327753569607,
      "learning_rate": 1.7515937901458102e-07,
      "loss": 0.3397,
      "step": 7055,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.5531914893617021,
      "success_rate.epoch.env.math": 0.9523809523809523,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.936988543371522,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501971061867902,
      "success_rate.epoch.global": 0.8250910983862572,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9916452442159382,
      "tokens_p.mean_in_band": 0.4782151442307692,
      "tokens_rate.above_band": 0.681260945709282,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.318739054290718
    },
    {
      "epoch": 1.1735372340425532,
      "grad_norm": 61.69552485540957,
      "learning_rate": 1.751335314950557e-07,
      "loss": 0.2666,
      "step": 7060,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.5508474576271186,
      "success_rate.epoch.env.math": 0.952755905511811,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.9372964169381107,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6510086543919703,
      "success_rate.epoch.global": 0.8254790264111859,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9942141089108911,
      "tokens_p.mean_in_band": 0.783125,
      "tokens_rate.above_band": 0.9758454106280193,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024154589371980676
    },
    {
      "epoch": 1.1743683510638299,
      "grad_norm": 56.7892630894906,
      "learning_rate": 1.7510769261231972e-07,
      "loss": 0.258,
      "step": 7065,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47058823529411764,
      "success_rate.epoch.env.logic": 0.5527426160337553,
      "success_rate.epoch.env.math": 0.9529411764705882,
      "success_rate.epoch.env.sat": 0.06172839506172839,
      "success_rate.epoch.env.science": 0.9376518218623482,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6512300938728477,
      "success_rate.epoch.global": 0.8262886597938144,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.990983606557377,
      "tokens_p.mean_in_band": 0.83359375,
      "tokens_rate.above_band": 0.9838709677419355,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016129032258064516
    },
    {
      "epoch": 1.1751994680851063,
      "grad_norm": 72.62855285085922,
      "learning_rate": 1.7508186241223083e-07,
      "loss": 0.3656,
      "step": 7070,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.5504201680672269,
      "success_rate.epoch.env.math": 0.953307392996109,
      "success_rate.epoch.env.sat": 0.06097560975609756,
      "success_rate.epoch.env.science": 0.9378531073446328,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501794115983014,
      "success_rate.epoch.global": 0.8255515649050795,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9942074970484062,
      "tokens_p.mean_in_band": 0.6224574183558559,
      "tokens_rate.above_band": 0.884133611691023,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11586638830897704
    },
    {
      "epoch": 1.176030585106383,
      "grad_norm": 74.54143651156309,
      "learning_rate": 1.7505604094063124e-07,
      "loss": 0.2546,
      "step": 7075,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.5523012552301255,
      "success_rate.epoch.env.math": 0.9534883720930233,
      "success_rate.epoch.env.sat": 0.06097560975609756,
      "success_rate.epoch.env.science": 0.9381028938906752,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6503895800351973,
      "success_rate.epoch.global": 0.8261758691206544,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9891581632653061,
      "tokens_p.mean_in_band": 0.890625,
      "tokens_rate.above_band": 0.98989898989899,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010101010101010102
    },
    {
      "epoch": 1.1768617021276595,
      "grad_norm": 152.26976873196566,
      "learning_rate": 1.7503022824334778e-07,
      "loss": 0.4121,
      "step": 7080,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.5541666666666667,
      "success_rate.epoch.env.math": 0.9538461538461539,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.9376,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6504791848895901,
      "success_rate.epoch.global": 0.8260427263479145,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9951171875,
      "tokens_p.mean_below_band": 1.6555645743210334e-12,
      "tokens_p.mean_in_band": 0.74560546875,
      "tokens_rate.above_band": 0.9186602870813397,
      "tokens_rate.below_band": 0.004784688995215311,
      "tokens_rate.in_band": 0.07655502392344497
    },
    {
      "epoch": 1.1776928191489362,
      "grad_norm": 38.62991362871605,
      "learning_rate": 1.7500442436619164e-07,
      "loss": 0.2349,
      "step": 7085,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.5532786885245902,
      "success_rate.epoch.env.math": 0.9538461538461539,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.9370517928286852,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6503486225883727,
      "success_rate.epoch.global": 0.8253164556962025,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.43333333333333335,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9986267605633803,
      "tokens_p.mean_in_band": 0.6198814655172413,
      "tokens_rate.above_band": 0.9683578832515003,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.031642116748499725
    },
    {
      "epoch": 1.1785239361702127,
      "grad_norm": 107.29877957976451,
      "learning_rate": 1.749786293549584e-07,
      "loss": 0.2544,
      "step": 7090,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46153846153846156,
      "success_rate.epoch.env.logic": 0.5528455284552846,
      "success_rate.epoch.env.math": 0.9541984732824428,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.9373015873015873,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6503639820283623,
      "success_rate.epoch.global": 0.8256048387096774,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9998670212765958,
      "tokens_p.mean_in_band": 0.5771484375,
      "tokens_rate.above_band": 0.9832635983263598,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016736401673640166
    },
    {
      "epoch": 1.1793550531914894,
      "grad_norm": 39.65841618223465,
      "learning_rate": 1.7495284325542785e-07,
      "loss": 0.2593,
      "step": 7095,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4642857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5528455284552846,
      "success_rate.epoch.env.math": 0.9543726235741445,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.9375987361769352,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6505006443963708,
      "success_rate.epoch.global": 0.8258906171600602,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9953606007944389,
      "tokens_p.mean_below_band": 1.4466543992360434e-07,
      "tokens_p.mean_in_band": 0.5897534320809249,
      "tokens_rate.above_band": 0.9581351094196003,
      "tokens_rate.below_band": 0.0007136060894386299,
      "tokens_rate.in_band": 0.04115128449096099
    },
    {
      "epoch": 1.180186170212766,
      "grad_norm": 49.91994618426111,
      "learning_rate": 1.7492706611336405e-07,
      "loss": 0.3344,
      "step": 7100,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4642857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5528455284552846,
      "success_rate.epoch.env.math": 0.9545454545454546,
      "success_rate.epoch.env.sat": 0.060240963855421686,
      "success_rate.epoch.env.science": 0.9378930817610063,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6505431149923144,
      "success_rate.epoch.global": 0.8265,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954187657430731,
      "tokens_p.mean_in_band": 0.5658413951120163,
      "tokens_rate.above_band": 0.8899349921542256,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11006500784577448
    },
    {
      "epoch": 1.1810172872340425,
      "grad_norm": 288.99483276656537,
      "learning_rate": 1.7490129797451506e-07,
      "loss": 0.3402,
      "step": 7105,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4642857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5542168674698795,
      "success_rate.epoch.env.math": 0.9545454545454546,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9380877742946708,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6506202856483733,
      "success_rate.epoch.global": 0.826195219123506,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977879665379665,
      "tokens_p.mean_below_band": 4.94765117764473e-09,
      "tokens_p.mean_in_band": 0.7008023648648649,
      "tokens_rate.above_band": 0.9533742331288344,
      "tokens_rate.below_band": 0.001226993865030675,
      "tokens_rate.in_band": 0.04539877300613497
    },
    {
      "epoch": 1.1818484042553192,
      "grad_norm": 55.133019757459614,
      "learning_rate": 1.7487553888461307e-07,
      "loss": 0.3324,
      "step": 7110,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4642857142857143,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5537848605577689,
      "success_rate.epoch.env.math": 0.9547169811320755,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9383775351014041,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6506229475103046,
      "success_rate.epoch.global": 0.8264749628160635,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 1.0003165701881331,
      "tokens_p.mean_in_band": 0.5994791666666667,
      "tokens_rate.above_band": 0.9787535410764873,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021246458923512748
    },
    {
      "epoch": 1.1826795212765957,
      "grad_norm": 169.01561704980205,
      "learning_rate": 1.7484978888937412e-07,
      "loss": 0.4208,
      "step": 7115,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.47368421052631576,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5533596837944664,
      "success_rate.epoch.env.math": 0.9547169811320755,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9386169386169386,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6514604677823803,
      "success_rate.epoch.global": 0.8266666666666667,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9969466600199401,
      "tokens_p.mean_in_band": 0.6034307065217391,
      "tokens_rate.above_band": 0.9561487130600572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0438512869399428
    },
    {
      "epoch": 1.1835106382978724,
      "grad_norm": 203.43035540605297,
      "learning_rate": 1.7482404803449814e-07,
      "loss": 0.2213,
      "step": 7120,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.46551724137931033,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5511811023622047,
      "success_rate.epoch.env.math": 0.9547169811320755,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9382239382239382,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6504842358758105,
      "success_rate.epoch.global": 0.826044226044226,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973795369211514,
      "tokens_p.mean_below_band": 1.2278178473934531e-11,
      "tokens_p.mean_in_band": 0.6227463942307693,
      "tokens_rate.above_band": 0.982779827798278,
      "tokens_rate.below_band": 0.0012300123001230013,
      "tokens_rate.in_band": 0.015990159901599015
    },
    {
      "epoch": 1.1843417553191489,
      "grad_norm": 90.52725854615451,
      "learning_rate": 1.7479831636566884e-07,
      "loss": 0.2953,
      "step": 7125,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5511811023622047,
      "success_rate.epoch.env.math": 0.9553903345724907,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9384141647421094,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6498454592597509,
      "success_rate.epoch.global": 0.826320939334638,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9973421391752577,
      "tokens_p.mean_in_band": 0.5625,
      "tokens_rate.above_band": 0.9627791563275434,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03722084367245657
    },
    {
      "epoch": 1.1851728723404256,
      "grad_norm": 84.21501005622059,
      "learning_rate": 1.7477259392855363e-07,
      "loss": 0.4298,
      "step": 7130,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.546875,
      "success_rate.epoch.env.math": 0.9553903345724907,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9386503067484663,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6494754628637648,
      "success_rate.epoch.global": 0.825938566552901,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.997867803837953,
      "tokens_p.mean_in_band": 0.5989040798611112,
      "tokens_rate.above_band": 0.975051975051975,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02494802494802495
    },
    {
      "epoch": 1.186003989361702,
      "grad_norm": 36.77602723989091,
      "learning_rate": 1.7474688076880356e-07,
      "loss": 0.2917,
      "step": 7135,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46296296296296297,
      "success_rate.epoch.env.logic": 0.5447470817120622,
      "success_rate.epoch.env.math": 0.9553903345724907,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9389312977099237,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.650228721678059,
      "success_rate.epoch.global": 0.8261291889266634,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951693702290076,
      "tokens_p.mean_in_band": 0.680921052631579,
      "tokens_rate.above_band": 0.9821930646672915,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01780693533270853
    },
    {
      "epoch": 1.1868351063829787,
      "grad_norm": 49.01055505193855,
      "learning_rate": 1.7472117693205316e-07,
      "loss": 0.2247,
      "step": 7140,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46296296296296297,
      "success_rate.epoch.env.logic": 0.5447470817120622,
      "success_rate.epoch.env.math": 0.9553903345724907,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9385898407884761,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501976801397457,
      "success_rate.epoch.global": 0.8264023210831721,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9895833333333334,
      "tokens_p.mean_in_band": 0.6135110294117647,
      "tokens_rate.above_band": 0.8903225806451613,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10967741935483871
    },
    {
      "epoch": 1.1876662234042552,
      "grad_norm": 133.21010695596706,
      "learning_rate": 1.7469548246392044e-07,
      "loss": 0.2524,
      "step": 7145,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46296296296296297,
      "success_rate.epoch.env.logic": 0.5444015444015444,
      "success_rate.epoch.env.math": 0.9553903345724907,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9389140271493213,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6501957391443208,
      "success_rate.epoch.global": 0.8266730861819933,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9994478798586572,
      "tokens_p.mean_below_band": 3.510081114654895e-12,
      "tokens_p.mean_in_band": 0.6101190476190477,
      "tokens_rate.above_band": 0.9846903270702854,
      "tokens_rate.below_band": 0.0006958942240779402,
      "tokens_rate.in_band": 0.014613778705636743
    },
    {
      "epoch": 1.188497340425532,
      "grad_norm": 155.33858523778767,
      "learning_rate": 1.7466979741000682e-07,
      "loss": 0.4628,
      "step": 7150,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46296296296296297,
      "success_rate.epoch.env.logic": 0.549618320610687,
      "success_rate.epoch.env.math": 0.9553903345724907,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9391891891891891,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6506950062578672,
      "success_rate.epoch.global": 0.8274209012464045,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9932208994708994,
      "tokens_p.mean_in_band": 0.8370535714285714,
      "tokens_rate.above_band": 0.9818181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01818181818181818
    },
    {
      "epoch": 1.1893284574468086,
      "grad_norm": 63.59817003667413,
      "learning_rate": 1.7464412181589697e-07,
      "loss": 0.4984,
      "step": 7155,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.549618320610687,
      "success_rate.epoch.env.math": 0.9555555555555556,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9387602688573562,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6515586981138256,
      "success_rate.epoch.global": 0.8276849642004773,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9952242524916943,
      "tokens_p.mean_in_band": 0.6396484375,
      "tokens_rate.above_band": 0.9868852459016394,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013114754098360656
    },
    {
      "epoch": 1.190159574468085,
      "grad_norm": 168.22055137422205,
      "learning_rate": 1.7461845572715875e-07,
      "loss": 0.3207,
      "step": 7160,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5547169811320755,
      "success_rate.epoch.env.math": 0.9555555555555556,
      "success_rate.epoch.env.sat": 0.05952380952380952,
      "success_rate.epoch.env.science": 0.9390787518573551,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.652051165706679,
      "success_rate.epoch.global": 0.8285035629453682,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9951584507042254,
      "tokens_p.mean_in_band": 0.8229166666666666,
      "tokens_rate.above_band": 0.9895470383275261,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010452961672473868
    },
    {
      "epoch": 1.1909906914893618,
      "grad_norm": 59.1696786261031,
      "learning_rate": 1.7459279918934317e-07,
      "loss": 0.4115,
      "step": 7165,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.556390977443609,
      "success_rate.epoch.env.math": 0.9560439560439561,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9392142327650111,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6521964018517286,
      "success_rate.epoch.global": 0.828679602460956,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9997452445652174,
      "tokens_p.mean_in_band": 0.6395089285714286,
      "tokens_rate.above_band": 0.9633507853403142,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03664921465968586
    },
    {
      "epoch": 1.1918218085106382,
      "grad_norm": 108.83992066461903,
      "learning_rate": 1.7456715224798435e-07,
      "loss": 0.3053,
      "step": 7170,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4576271186440678,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.556390977443609,
      "success_rate.epoch.env.math": 0.9562043795620438,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9396170839469808,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6522476086426429,
      "success_rate.epoch.global": 0.8294865756005653,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9919642857142857,
      "tokens_p.mean_in_band": 0.840625,
      "tokens_rate.above_band": 0.9655172413793104,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034482758620689655
    },
    {
      "epoch": 1.192652925531915,
      "grad_norm": 36.42211282594382,
      "learning_rate": 1.745415149485993e-07,
      "loss": 0.2745,
      "step": 7175,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4426229508196721,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.556390977443609,
      "success_rate.epoch.env.math": 0.9563636363636364,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9398826979472141,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6509222180042274,
      "success_rate.epoch.global": 0.8292682926829268,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998784046692607,
      "tokens_p.mean_in_band": 0.700390625,
      "tokens_rate.above_band": 0.9903660886319846,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009633911368015413
    },
    {
      "epoch": 1.1934840425531914,
      "grad_norm": 67.20591533191127,
      "learning_rate": 1.7451588733668793e-07,
      "loss": 0.3741,
      "step": 7180,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4426229508196721,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5543071161048689,
      "success_rate.epoch.env.math": 0.9565217391304348,
      "success_rate.epoch.env.sat": 0.058823529411764705,
      "success_rate.epoch.env.science": 0.9393718042366691,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.650700704160365,
      "success_rate.epoch.global": 0.8288920056100981,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994257656458056,
      "tokens_p.mean_in_band": 0.5396075581395349,
      "tokens_rate.above_band": 0.9458438287153652,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05415617128463476
    },
    {
      "epoch": 1.194315159574468,
      "grad_norm": 130.2437482582585,
      "learning_rate": 1.7449026945773302e-07,
      "loss": 0.2298,
      "step": 7185,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5522388059701493,
      "success_rate.epoch.env.math": 0.9568345323741008,
      "success_rate.epoch.env.sat": 0.05747126436781609,
      "success_rate.epoch.env.science": 0.9395484340859432,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6512515041894928,
      "success_rate.epoch.global": 0.8282922289436947,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9954782958199357,
      "tokens_p.mean_in_band": 0.6380013992537313,
      "tokens_rate.above_band": 0.933,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.067
    },
    {
      "epoch": 1.1951462765957448,
      "grad_norm": 87.47231132390999,
      "learning_rate": 1.7446466135719997e-07,
      "loss": 0.3221,
      "step": 7190,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5522388059701493,
      "success_rate.epoch.env.math": 0.9572953736654805,
      "success_rate.epoch.env.sat": 0.05747126436781609,
      "success_rate.epoch.env.science": 0.9390862944162437,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6512513861551001,
      "success_rate.epoch.global": 0.8285449490268767,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9285714285714286,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9855263157894737,
      "tokens_p.mean_in_band": 0.5767045454545454,
      "tokens_rate.above_band": 0.8962264150943396,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10377358490566038
    },
    {
      "epoch": 1.1959773936170213,
      "grad_norm": 47.18650746120833,
      "learning_rate": 1.7443906308053696e-07,
      "loss": 0.2442,
      "step": 7195,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5539033457249071,
      "success_rate.epoch.env.math": 0.9575971731448764,
      "success_rate.epoch.env.sat": 0.05747126436781609,
      "success_rate.epoch.env.science": 0.9393063583815029,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6514501500823194,
      "success_rate.epoch.global": 0.8291782086795937,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9919444444444444,
      "tokens_p.mean_in_band": 0.8658854166666666,
      "tokens_rate.above_band": 0.9868421052631579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013157894736842105
    },
    {
      "epoch": 1.196808510638298,
      "grad_norm": 54.65375532986128,
      "learning_rate": 1.7441347467317455e-07,
      "loss": 0.3442,
      "step": 7200,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5571955719557196,
      "success_rate.epoch.env.math": 0.9578947368421052,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.93943763518385,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6517290577351154,
      "success_rate.epoch.global": 0.8293468261269549,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9917834394904459,
      "tokens_p.mean_in_band": 0.5362582076848249,
      "tokens_rate.above_band": 0.8842081549898626,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11579184501013742
    },
    {
      "epoch": 1.1976396276595744,
      "grad_norm": 78.06349294447963,
      "learning_rate": 1.74387896180526e-07,
      "loss": 0.3545,
      "step": 7205,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5571955719557196,
      "success_rate.epoch.env.math": 0.9581881533101045,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.93974175035868,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6525747021655228,
      "success_rate.epoch.global": 0.8301282051282052,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9970868644067796,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.1984707446808511,
      "grad_norm": 157.83051673803342,
      "learning_rate": 1.7436232764798683e-07,
      "loss": 0.2677,
      "step": 7210,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5567765567765568,
      "success_rate.epoch.env.math": 0.9581881533101045,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.9400855920114123,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6525678682085746,
      "success_rate.epoch.global": 0.8304466727438469,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9988954344624448,
      "tokens_p.mean_in_band": 0.5855334051724138,
      "tokens_rate.above_band": 0.9590395480225988,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04096045197740113
    },
    {
      "epoch": 1.1993018617021276,
      "grad_norm": 77.89964694815394,
      "learning_rate": 1.743367691209349e-07,
      "loss": 0.4176,
      "step": 7215,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5547445255474452,
      "success_rate.epoch.env.math": 0.9584775086505191,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.9402985074626866,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6524287990778999,
      "success_rate.epoch.global": 0.8306085376930064,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9954438250428816,
      "tokens_p.mean_in_band": 0.5691817434210527,
      "tokens_rate.above_band": 0.96843853820598,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03156146179401993
    },
    {
      "epoch": 1.2001329787234043,
      "grad_norm": 107.20550330360727,
      "learning_rate": 1.7431122064473036e-07,
      "loss": 0.2692,
      "step": 7220,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.8,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4727272727272727,
      "success_rate.epoch.env.logic": 0.5547445255474452,
      "success_rate.epoch.env.math": 0.9587628865979382,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.9405940594059405,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6524816108861429,
      "success_rate.epoch.global": 0.8312980551786522,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.990166083916084,
      "tokens_p.mean_in_band": 0.7708333333333334,
      "tokens_rate.above_band": 0.9794520547945206,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02054794520547945
    },
    {
      "epoch": 1.2009640957446808,
      "grad_norm": 861.2179674595136,
      "learning_rate": 1.742856822647155e-07,
      "loss": 0.3342,
      "step": 7225,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48214285714285715,
      "success_rate.epoch.env.logic": 0.5547445255474452,
      "success_rate.epoch.env.math": 0.9587628865979382,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.9408450704225352,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6412391801678562,
      "success_rate.epoch.global": 0.8314556106354214,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9916618329466357,
      "tokens_p.mean_in_band": 0.6695913461538462,
      "tokens_rate.above_band": 0.9298813376483279,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07011866235167206
    },
    {
      "epoch": 1.2017952127659575,
      "grad_norm": 43.7755808881625,
      "learning_rate": 1.7426015402621467e-07,
      "loss": 0.3397,
      "step": 7230,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48214285714285715,
      "success_rate.epoch.env.logic": 0.5563636363636364,
      "success_rate.epoch.env.math": 0.9590443686006825,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.9410526315789474,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6414308305292514,
      "success_rate.epoch.global": 0.8320610687022901,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.987300796812749,
      "tokens_p.mean_in_band": 0.84228515625,
      "tokens_rate.above_band": 0.9691119691119691,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03088803088803089
    },
    {
      "epoch": 1.202626329787234,
      "grad_norm": 44.13057072630015,
      "learning_rate": 1.7423463597453422e-07,
      "loss": 0.4113,
      "step": 7235,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48214285714285715,
      "success_rate.epoch.env.logic": 0.5563636363636364,
      "success_rate.epoch.env.math": 0.9593220338983051,
      "success_rate.epoch.env.sat": 0.056818181818181816,
      "success_rate.epoch.env.science": 0.9412997903563941,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6414785418088031,
      "success_rate.epoch.global": 0.8326621923937361,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9867869127516778,
      "tokens_p.mean_in_band": 0.79150390625,
      "tokens_rate.above_band": 0.9490445859872612,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050955414012738856
    },
    {
      "epoch": 1.2034574468085106,
      "grad_norm": 86.4276008076503,
      "learning_rate": 1.7420912815496246e-07,
      "loss": 0.3673,
      "step": 7240,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.453125,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48214285714285715,
      "success_rate.epoch.env.logic": 0.5563636363636364,
      "success_rate.epoch.env.math": 0.9593220338983051,
      "success_rate.epoch.env.sat": 0.056179775280898875,
      "success_rate.epoch.env.science": 0.941544885177453,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6407889261693772,
      "success_rate.epoch.global": 0.8323673651359786,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958333333333333,
      "tokens_p.mean_in_band": 0.661110101744186,
      "tokens_rate.above_band": 0.8847184986595175,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11528150134048257
    },
    {
      "epoch": 1.2042885638297873,
      "grad_norm": 42.279391788396666,
      "learning_rate": 1.7418363061276958e-07,
      "loss": 0.3394,
      "step": 7245,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48214285714285715,
      "success_rate.epoch.env.logic": 0.5579710144927537,
      "success_rate.epoch.env.math": 0.9594594594594594,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.9416666666666667,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6410310007147951,
      "success_rate.epoch.global": 0.8320746334962239,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.996510152284264,
      "tokens_p.mean_in_band": 0.70751953125,
      "tokens_rate.above_band": 0.9656862745098039,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03431372549019608
    },
    {
      "epoch": 1.2051196808510638,
      "grad_norm": 78.52708401960292,
      "learning_rate": 1.741581433932074e-07,
      "loss": 0.3322,
      "step": 7250,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48214285714285715,
      "success_rate.epoch.env.logic": 0.5539568345323741,
      "success_rate.epoch.env.math": 0.959866220735786,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.9418282548476454,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6407177433963338,
      "success_rate.epoch.global": 0.831858407079646,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0002920560747663,
      "tokens_p.mean_in_band": 0.5736736918604651,
      "tokens_rate.above_band": 0.9647540983606557,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03524590163934426
    },
    {
      "epoch": 1.2059507978723405,
      "grad_norm": 131.0447295822214,
      "learning_rate": 1.7413266654150945e-07,
      "loss": 0.2896,
      "step": 7255,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49122807017543857,
      "success_rate.epoch.env.logic": 0.5539568345323741,
      "success_rate.epoch.env.math": 0.96,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.9419889502762431,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6415149422249603,
      "success_rate.epoch.global": 0.8319364799294221,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943181818181818,
      "tokens_p.mean_below_band": 1.3869794202037156e-11,
      "tokens_p.mean_in_band": 0.61572265625,
      "tokens_rate.above_band": 0.9556737588652482,
      "tokens_rate.below_band": 0.0017730496453900709,
      "tokens_rate.in_band": 0.0425531914893617
    },
    {
      "epoch": 1.206781914893617,
      "grad_norm": 87.68702110098192,
      "learning_rate": 1.7410720010289102e-07,
      "loss": 0.2921,
      "step": 7260,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49122807017543857,
      "success_rate.epoch.env.logic": 0.5539568345323741,
      "success_rate.epoch.env.math": 0.9601328903654485,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.9416208791208791,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6414935621531499,
      "success_rate.epoch.global": 0.8321616871704746,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.985608552631579,
      "tokens_p.mean_below_band": 9.918585419654846e-08,
      "tokens_p.mean_in_band": 0.6337890625,
      "tokens_rate.above_band": 0.9440993788819876,
      "tokens_rate.below_band": 0.006211180124223602,
      "tokens_rate.in_band": 0.049689440993788817
    },
    {
      "epoch": 1.2076130319148937,
      "grad_norm": 175.50684701828033,
      "learning_rate": 1.740817441225487e-07,
      "loss": 0.2506,
      "step": 7265,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49122807017543857,
      "success_rate.epoch.env.logic": 0.5539568345323741,
      "success_rate.epoch.env.math": 0.9605263157894737,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.9411764705882353,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6414889273250937,
      "success_rate.epoch.global": 0.8323851203501094,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9948051948051948,
      "tokens_p.mean_below_band": 1.6079866327345371e-09,
      "tokens_p.mean_in_band": 0.736328125,
      "tokens_rate.above_band": 0.9871794871794872,
      "tokens_rate.below_band": 0.002564102564102564,
      "tokens_rate.in_band": 0.010256410256410256
    },
    {
      "epoch": 1.2084441489361701,
      "grad_norm": 28.995324676765556,
      "learning_rate": 1.7405629864566066e-07,
      "loss": 0.311,
      "step": 7270,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49122807017543857,
      "success_rate.epoch.env.logic": 0.5555555555555556,
      "success_rate.epoch.env.math": 0.9611650485436893,
      "success_rate.epoch.env.sat": 0.054945054945054944,
      "success_rate.epoch.env.science": 0.941296928327645,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6424433840646875,
      "success_rate.epoch.global": 0.8331154684095861,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9935154525386314,
      "tokens_p.mean_in_band": 0.7317708333333334,
      "tokens_rate.above_band": 0.993421052631579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006578947368421052
    },
    {
      "epoch": 1.2092752659574468,
      "grad_norm": 72.1276390026,
      "learning_rate": 1.740308637173864e-07,
      "loss": 0.2485,
      "step": 7275,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49122807017543857,
      "success_rate.epoch.env.logic": 0.5567375886524822,
      "success_rate.epoch.env.math": 0.9614147909967846,
      "success_rate.epoch.env.sat": 0.05434782608695652,
      "success_rate.epoch.env.science": 0.9414567733151804,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6425337833082746,
      "success_rate.epoch.global": 0.8329718004338394,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9969602609727165,
      "tokens_p.mean_in_band": 0.6417410714285714,
      "tokens_rate.above_band": 0.9601366742596811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03986332574031891
    },
    {
      "epoch": 1.2101063829787235,
      "grad_norm": 90.22251660236212,
      "learning_rate": 1.7400543938286668e-07,
      "loss": 0.4147,
      "step": 7280,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49122807017543857,
      "success_rate.epoch.env.logic": 0.5567375886524822,
      "success_rate.epoch.env.math": 0.9616613418530351,
      "success_rate.epoch.env.sat": 0.053763440860215055,
      "success_rate.epoch.env.science": 0.9416553595658074,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.642521124388287,
      "success_rate.epoch.global": 0.8331171638564635,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9881410256410257,
      "tokens_p.mean_in_band": 0.6795176630434783,
      "tokens_rate.above_band": 0.8944954128440367,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10550458715596331
    },
    {
      "epoch": 1.2109375,
      "grad_norm": 57.9272961121597,
      "learning_rate": 1.7398002568722344e-07,
      "loss": 0.3213,
      "step": 7285,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5567375886524822,
      "success_rate.epoch.env.math": 0.9619047619047619,
      "success_rate.epoch.env.sat": 0.053763440860215055,
      "success_rate.epoch.env.science": 0.9418918918918919,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6433622045885028,
      "success_rate.epoch.global": 0.8337639965546942,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9958832335329342,
      "tokens_p.mean_in_band": 0.828125,
      "tokens_rate.above_band": 0.9940476190476191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005952380952380952
    },
    {
      "epoch": 1.2117686170212765,
      "grad_norm": 85.92478016633245,
      "learning_rate": 1.7395462267555976e-07,
      "loss": 0.1761,
      "step": 7290,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5567375886524822,
      "success_rate.epoch.env.math": 0.9620253164556962,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.9421654337592468,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.643346035944846,
      "success_rate.epoch.global": 0.833976833976834,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9924107142857143,
      "tokens_p.mean_in_band": 0.7425986842105263,
      "tokens_rate.above_band": 0.9170305676855895,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08296943231441048
    },
    {
      "epoch": 1.2125997340425532,
      "grad_norm": 193.41476546345996,
      "learning_rate": 1.7392923039295982e-07,
      "loss": 0.4619,
      "step": 7295,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5567375886524822,
      "success_rate.epoch.env.math": 0.9622641509433962,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.942397856664434,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6433888775260176,
      "success_rate.epoch.global": 0.8345446772124839,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9955628803245437,
      "tokens_p.mean_in_band": 0.8763020833333334,
      "tokens_rate.above_band": 0.9939516129032258,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006048387096774193
    },
    {
      "epoch": 1.2134308510638299,
      "grad_norm": 31.936847658755845,
      "learning_rate": 1.739038488844886e-07,
      "loss": 0.3176,
      "step": 7300,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5578947368421052,
      "success_rate.epoch.env.math": 0.9625,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.9425517702070808,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6435295057795515,
      "success_rate.epoch.global": 0.8347529812606473,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.8222222222222223,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965625,
      "tokens_p.mean_in_band": 0.6397429435483871,
      "tokens_rate.above_band": 0.9626955475330926,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03730445246690734
    },
    {
      "epoch": 1.2142619680851063,
      "grad_norm": 77.57606503227909,
      "learning_rate": 1.7387847819519216e-07,
      "loss": 0.2923,
      "step": 7305,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4915254237288136,
      "success_rate.epoch.env.logic": 0.5578947368421052,
      "success_rate.epoch.env.math": 0.9629629629629629,
      "success_rate.epoch.env.sat": 0.05319148936170213,
      "success_rate.epoch.env.science": 0.9427048634243838,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6428150948621951,
      "success_rate.epoch.global": 0.8349596945269411,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9904157667386609,
      "tokens_p.mean_in_band": 0.7289635894495413,
      "tokens_rate.above_band": 0.8946859903381642,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10531400966183575
    },
    {
      "epoch": 1.215093085106383,
      "grad_norm": 81.84160403636776,
      "learning_rate": 1.7385311837009725e-07,
      "loss": 0.2625,
      "step": 7310,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5578947368421052,
      "success_rate.epoch.env.math": 0.963302752293578,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.9427811044577512,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6435724308822711,
      "success_rate.epoch.global": 0.8350253807106599,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.997244837172359,
      "tokens_p.mean_in_band": 0.6151815878378378,
      "tokens_rate.above_band": 0.9714506172839507,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02854938271604938
    },
    {
      "epoch": 1.2159242021276595,
      "grad_norm": 23.928531410931644,
      "learning_rate": 1.7382776945421128e-07,
      "loss": 0.3848,
      "step": 7315,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5578947368421052,
      "success_rate.epoch.env.math": 0.963302752293578,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.9417989417989417,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6434831433678339,
      "success_rate.epoch.global": 0.8348082595870207,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99235807860262,
      "tokens_p.mean_below_band": 4.1443854570388794e-08,
      "tokens_p.mean_in_band": 0.6575520833333334,
      "tokens_rate.above_band": 0.9703389830508474,
      "tokens_rate.below_band": 0.00423728813559322,
      "tokens_rate.in_band": 0.025423728813559324
    },
    {
      "epoch": 1.2167553191489362,
      "grad_norm": 85.70987555682437,
      "learning_rate": 1.7380243149252238e-07,
      "loss": 0.3901,
      "step": 7320,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5559440559440559,
      "success_rate.epoch.env.math": 0.9636363636363636,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.9419141914191419,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6432967737724612,
      "success_rate.epoch.global": 0.8345233095338094,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995127688172043,
      "tokens_p.mean_below_band": 1.1874362826347351e-08,
      "tokens_p.mean_in_band": 0.6556396484375,
      "tokens_rate.above_band": 0.916256157635468,
      "tokens_rate.below_band": 0.0049261083743842365,
      "tokens_rate.in_band": 0.07881773399014778
    },
    {
      "epoch": 1.2175864361702127,
      "grad_norm": 92.9236694079965,
      "learning_rate": 1.7377710452999928e-07,
      "loss": 0.2393,
      "step": 7325,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5559440559440559,
      "success_rate.epoch.env.math": 0.9637462235649547,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.9415627051871307,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6432748077448776,
      "success_rate.epoch.global": 0.8347280334728033,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9842557251908397,
      "tokens_p.mean_in_band": 0.7760416666666666,
      "tokens_rate.above_band": 0.9562043795620438,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043795620437956206
    },
    {
      "epoch": 1.2184175531914894,
      "grad_norm": 59.83939440072019,
      "learning_rate": 1.7375178861159107e-07,
      "loss": 0.3882,
      "step": 7330,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5590277777777778,
      "success_rate.epoch.env.math": 0.9637462235649547,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.9417920209287116,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.643575992978996,
      "success_rate.epoch.global": 0.835279399499583,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9936995967741935,
      "tokens_p.mean_in_band": 0.84765625,
      "tokens_rate.above_band": 0.9959839357429718,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004016064257028112
    },
    {
      "epoch": 1.219248670212766,
      "grad_norm": 243.97516346494928,
      "learning_rate": 1.7372648378222736e-07,
      "loss": 0.5224,
      "step": 7335,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5605536332179931,
      "success_rate.epoch.env.math": 0.9637462235649547,
      "success_rate.epoch.env.sat": 0.052083333333333336,
      "success_rate.epoch.env.science": 0.9414443721535458,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6436831026758187,
      "success_rate.epoch.global": 0.8354798504362276,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9871651785714286,
      "tokens_p.mean_in_band": 0.6995738636363636,
      "tokens_rate.above_band": 0.9531914893617022,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04680851063829787
    },
    {
      "epoch": 1.2200797872340425,
      "grad_norm": 225.05026430831384,
      "learning_rate": 1.73701190086818e-07,
      "loss": 0.2789,
      "step": 7340,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5605536332179931,
      "success_rate.epoch.env.math": 0.9610778443113772,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.9416342412451362,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6434089706992057,
      "success_rate.epoch.global": 0.8352649006622517,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.990625,
      "tokens_p.mean_below_band": 6.344635039567947e-09,
      "tokens_p.mean_in_band": 0.7288240131578947,
      "tokens_rate.above_band": 0.8823529411764706,
      "tokens_rate.below_band": 0.0058823529411764705,
      "tokens_rate.in_band": 0.11176470588235295
    },
    {
      "epoch": 1.2209109042553192,
      "grad_norm": 60.98321741520074,
      "learning_rate": 1.7367590757025308e-07,
      "loss": 0.398,
      "step": 7345,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5567010309278351,
      "success_rate.epoch.env.math": 0.9610778443113772,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.9418604651162791,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6430792999338407,
      "success_rate.epoch.global": 0.834983498349835,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981831395348837,
      "tokens_p.mean_in_band": 0.6392983490566038,
      "tokens_rate.above_band": 0.9578361177406524,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.042163882259347654
    },
    {
      "epoch": 1.2217420212765957,
      "grad_norm": 59.839232518173475,
      "learning_rate": 1.736506362774029e-07,
      "loss": 0.3146,
      "step": 7350,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5582191780821918,
      "success_rate.epoch.env.math": 0.9610778443113772,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.941972920696325,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6439726930289205,
      "success_rate.epoch.global": 0.8353231782626596,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9974731522425774,
      "tokens_p.mean_in_band": 0.7495561079545454,
      "tokens_rate.above_band": 0.9862928348909658,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013707165109034268
    },
    {
      "epoch": 1.2225731382978724,
      "grad_norm": 88.7350089943168,
      "learning_rate": 1.7362537625311778e-07,
      "loss": 0.2237,
      "step": 7355,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5612244897959183,
      "success_rate.epoch.env.math": 0.9610778443113772,
      "success_rate.epoch.env.sat": 0.05154639175257732,
      "success_rate.epoch.env.science": 0.9421593830334191,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6442628543062678,
      "success_rate.epoch.global": 0.8357963875205254,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9946808510638298,
      "tokens_p.mean_in_band": 0.7734375,
      "tokens_rate.above_band": 0.9915611814345991,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008438818565400843
    },
    {
      "epoch": 1.2234042553191489,
      "grad_norm": 95.5187307601354,
      "learning_rate": 1.736001275422281e-07,
      "loss": 0.2678,
      "step": 7360,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5612244897959183,
      "success_rate.epoch.env.math": 0.9613095238095238,
      "success_rate.epoch.env.sat": 0.05102040816326531,
      "success_rate.epoch.env.science": 0.942381562099872,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6442562974858395,
      "success_rate.epoch.global": 0.8359918200408998,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953218562874252,
      "tokens_p.mean_in_band": 0.7462890625,
      "tokens_rate.above_band": 0.893048128342246,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10695187165775401
    },
    {
      "epoch": 1.2242353723404256,
      "grad_norm": 54.862413313771825,
      "learning_rate": 1.7357489018954415e-07,
      "loss": 0.4193,
      "step": 7365,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5612244897959183,
      "success_rate.epoch.env.math": 0.9615384615384616,
      "success_rate.epoch.env.sat": 0.050505050505050504,
      "success_rate.epoch.env.science": 0.9426020408163265,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6442503028301283,
      "success_rate.epoch.global": 0.8361858190709046,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.991640127388535,
      "tokens_p.mean_in_band": 0.6,
      "tokens_rate.above_band": 0.9127906976744186,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0872093023255814
    },
    {
      "epoch": 1.225066489361702,
      "grad_norm": 56.44767446130195,
      "learning_rate": 1.7354966423985605e-07,
      "loss": 0.3954,
      "step": 7370,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.559322033898305,
      "success_rate.epoch.env.math": 0.961764705882353,
      "success_rate.epoch.env.sat": 0.050505050505050504,
      "success_rate.epoch.env.science": 0.9427480916030534,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6434926323764921,
      "success_rate.epoch.global": 0.8359057676685622,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9964012925969448,
      "tokens_p.mean_in_band": 0.6123046875,
      "tokens_rate.above_band": 0.9747995418098511,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025200458190148912
    },
    {
      "epoch": 1.2258976063829787,
      "grad_norm": 39.12242616722017,
      "learning_rate": 1.7352444973793362e-07,
      "loss": 0.2677,
      "step": 7375,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5604026845637584,
      "success_rate.epoch.env.math": 0.961764705882353,
      "success_rate.epoch.env.sat": 0.050505050505050504,
      "success_rate.epoch.env.science": 0.9429657794676806,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.643610663151954,
      "success_rate.epoch.global": 0.8360987454471873,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9993003731343284,
      "tokens_p.mean_in_band": 0.6050646551724138,
      "tokens_rate.above_band": 0.9651860744297719,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03481392557022809
    },
    {
      "epoch": 1.2267287234042552,
      "grad_norm": 109.84265599011383,
      "learning_rate": 1.734992467285265e-07,
      "loss": 0.432,
      "step": 7380,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5618729096989966,
      "success_rate.epoch.env.math": 0.961764705882353,
      "success_rate.epoch.env.sat": 0.05,
      "success_rate.epoch.env.science": 0.943217665615142,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403122141317403,
      "success_rate.epoch.global": 0.8359532446594116,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9902676399026764,
      "tokens_p.mean_in_band": 0.3748739919354839,
      "tokens_rate.above_band": 0.6236722306525038,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.37632776934749623
    },
    {
      "epoch": 1.227559840425532,
      "grad_norm": 1897.7888927282638,
      "learning_rate": 1.7347405525636384e-07,
      "loss": 0.4824,
      "step": 7385,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081967213114754,
      "success_rate.epoch.env.logic": 0.5618729096989966,
      "success_rate.epoch.env.math": 0.9618768328445748,
      "success_rate.epoch.env.sat": 0.05,
      "success_rate.epoch.env.science": 0.943502824858757,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403483310595436,
      "success_rate.epoch.global": 0.8365461847389558,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.984375,
      "tokens_p.mean_in_band": 0.76953125,
      "tokens_rate.above_band": 0.937799043062201,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06220095693779904
    },
    {
      "epoch": 1.2283909574468086,
      "grad_norm": 76.34445281624471,
      "learning_rate": 1.7344887536615427e-07,
      "loss": 0.3469,
      "step": 7390,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5161290322580645,
      "success_rate.epoch.env.logic": 0.56,
      "success_rate.epoch.env.math": 0.9619883040935673,
      "success_rate.epoch.env.sat": 0.04950495049504951,
      "success_rate.epoch.env.science": 0.943609022556391,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6408739693040226,
      "success_rate.epoch.global": 0.8362034441329596,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7777777777777778,
      "tokens_p.mean_above_band": 0.997297503045067,
      "tokens_p.mean_in_band": 0.5390625,
      "tokens_rate.above_band": 0.9624853458382181,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03751465416178194
    },
    {
      "epoch": 1.229222074468085,
      "grad_norm": 62.07374099914586,
      "learning_rate": 1.7342370710258601e-07,
      "loss": 0.3277,
      "step": 7395,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.6666666666666666,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.56,
      "success_rate.epoch.env.math": 0.9619883040935673,
      "success_rate.epoch.env.sat": 0.04950495049504951,
      "success_rate.epoch.env.science": 0.9438902743142145,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6401547627073196,
      "success_rate.epoch.global": 0.8363926576217079,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9921965948777648,
      "tokens_p.mean_in_band": 0.5486670020120724,
      "tokens_rate.above_band": 0.8736333587592169,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12636664124078312
    },
    {
      "epoch": 1.2300531914893618,
      "grad_norm": 351.29815142955675,
      "learning_rate": 1.733985505103265e-07,
      "loss": 0.3053,
      "step": 7400,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.56,
      "success_rate.epoch.env.math": 0.9622093023255814,
      "success_rate.epoch.env.sat": 0.04950495049504951,
      "success_rate.epoch.env.science": 0.9440298507462687,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6445165465512392,
      "success_rate.epoch.global": 0.8368483883804219,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.990234375,
      "tokens_p.mean_in_band": 0.820556640625,
      "tokens_rate.above_band": 0.9655172413793104,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034482758620689655
    },
    {
      "epoch": 1.2308843085106382,
      "grad_norm": 47.58568719033422,
      "learning_rate": 1.7337340563402254e-07,
      "loss": 0.2302,
      "step": 7405,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.56,
      "success_rate.epoch.env.math": 0.9623188405797102,
      "success_rate.epoch.env.sat": 0.04854368932038835,
      "success_rate.epoch.env.science": 0.9442033477991321,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6444548896541784,
      "success_rate.epoch.global": 0.836572788575962,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99300799086758,
      "tokens_p.mean_in_band": 0.6189516129032258,
      "tokens_rate.above_band": 0.876,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.124
    },
    {
      "epoch": 1.231715425531915,
      "grad_norm": 71.9789341886777,
      "learning_rate": 1.7334827251830018e-07,
      "loss": 0.3609,
      "step": 7410,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5079365079365079,
      "success_rate.epoch.env.logic": 0.5614617940199336,
      "success_rate.epoch.env.math": 0.962536023054755,
      "success_rate.epoch.env.sat": 0.05714285714285714,
      "success_rate.epoch.env.science": 0.9443413729128015,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6454018141479163,
      "success_rate.epoch.global": 0.8367588932806325,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9929748062015504,
      "tokens_p.mean_in_band": 0.6744791666666666,
      "tokens_rate.above_band": 0.9247311827956989,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07526881720430108
    },
    {
      "epoch": 1.2325465425531914,
      "grad_norm": 291.68875604555234,
      "learning_rate": 1.733231512077645e-07,
      "loss": 0.2239,
      "step": 7415,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.515625,
      "success_rate.epoch.env.logic": 0.5614617940199336,
      "success_rate.epoch.env.math": 0.962536023054755,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.9445129469790382,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6460192664517355,
      "success_rate.epoch.global": 0.8364854215918046,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9944661458333334,
      "tokens_p.mean_in_band": 0.6645833333333333,
      "tokens_rate.above_band": 0.927536231884058,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07246376811594203
    },
    {
      "epoch": 1.233377659574468,
      "grad_norm": 209.55077672755175,
      "learning_rate": 1.732980417469996e-07,
      "loss": 0.2544,
      "step": 7420,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.515625,
      "success_rate.epoch.env.logic": 0.5629139072847682,
      "success_rate.epoch.env.math": 0.9626436781609196,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.9447513812154696,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6461827394160474,
      "success_rate.epoch.global": 0.8370632116215155,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966299019607843,
      "tokens_p.mean_in_band": 0.603271484375,
      "tokens_rate.above_band": 0.9272727272727272,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07272727272727272
    },
    {
      "epoch": 1.2342087765957448,
      "grad_norm": 85.7948375372207,
      "learning_rate": 1.7327294418056876e-07,
      "loss": 0.4763,
      "step": 7425,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5657894736842105,
      "success_rate.epoch.env.math": 0.9627507163323782,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.944920440636475,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6457481004782486,
      "success_rate.epoch.global": 0.837245696400626,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953947368421052,
      "tokens_p.mean_below_band": 9.049472282640636e-11,
      "tokens_p.mean_in_band": 0.8459821428571429,
      "tokens_rate.above_band": 0.979381443298969,
      "tokens_rate.below_band": 0.002577319587628866,
      "tokens_rate.in_band": 0.01804123711340206
    },
    {
      "epoch": 1.2350398936170213,
      "grad_norm": 43.8859169989041,
      "learning_rate": 1.7324785855301395e-07,
      "loss": 0.2535,
      "step": 7430,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5657894736842105,
      "success_rate.epoch.env.math": 0.9628571428571429,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.9451553930530164,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6457791349274583,
      "success_rate.epoch.global": 0.8377535101404057,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9878318584070797,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9912280701754386,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008771929824561403
    },
    {
      "epoch": 1.235871010638298,
      "grad_norm": 90.09312044481688,
      "learning_rate": 1.7322278490885598e-07,
      "loss": 0.3369,
      "step": 7435,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5657894736842105,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.9447144592952612,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.645758235400484,
      "success_rate.epoch.global": 0.8378063010501751,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.5714285714285715,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9956896551724138,
      "tokens_p.mean_below_band": 4.377298878921465e-08,
      "tokens_p.mean_in_band": 0.5210129310344828,
      "tokens_rate.above_band": 0.9555873925501432,
      "tokens_rate.below_band": 0.0028653295128939827,
      "tokens_rate.in_band": 0.04154727793696275
    },
    {
      "epoch": 1.2367021276595744,
      "grad_norm": 50.87681601760614,
      "learning_rate": 1.7319772329259447e-07,
      "loss": 0.4331,
      "step": 7440,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5672131147540984,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.056074766355140186,
      "success_rate.epoch.env.science": 0.9443436176648518,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6458539444404366,
      "success_rate.epoch.global": 0.8379216750678558,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9953908554572272,
      "tokens_p.mean_in_band": 0.5479561941964286,
      "tokens_rate.above_band": 0.9603399433427762,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039660056657223795
    },
    {
      "epoch": 1.2375332446808511,
      "grad_norm": 25.949806146757872,
      "learning_rate": 1.731726737487076e-07,
      "loss": 0.1965,
      "step": 7445,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4492753623188406,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5686274509803921,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.9445114595898673,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6453499423249265,
      "success_rate.epoch.global": 0.8376497873985311,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9948586118251928,
      "tokens_p.mean_in_band": 0.7029296875,
      "tokens_rate.above_band": 0.9511002444987775,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0488997555012225
    },
    {
      "epoch": 1.2383643617021276,
      "grad_norm": 70.4545634397591,
      "learning_rate": 1.7314763632165225e-07,
      "loss": 0.3787,
      "step": 7450,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4492753623188406,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.564935064935065,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.05555555555555555,
      "success_rate.epoch.env.science": 0.9446782922429344,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6450294374710848,
      "success_rate.epoch.global": 0.8373168851195065,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.999290293040293,
      "tokens_p.mean_in_band": 0.631907393292683,
      "tokens_rate.above_band": 0.9708392603129445,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029160739687055477
    },
    {
      "epoch": 1.2391954787234043,
      "grad_norm": 25.7788781614811,
      "learning_rate": 1.7312261105586365e-07,
      "loss": 0.2402,
      "step": 7455,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4492753623188406,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5631067961165048,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.9443447037701975,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6447865700813376,
      "success_rate.epoch.global": 0.8367895545314901,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9933127572016461,
      "tokens_p.mean_in_band": 0.6124237804878049,
      "tokens_rate.above_band": 0.9467532467532468,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053246753246753244
    },
    {
      "epoch": 1.2400265957446808,
      "grad_norm": 590.1470970112662,
      "learning_rate": 1.7309759799575557e-07,
      "loss": 0.3905,
      "step": 7460,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4492753623188406,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5076923076923077,
      "success_rate.epoch.env.logic": 0.5612903225806452,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.9445107398568019,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6446365303132234,
      "success_rate.epoch.global": 0.8367816091954023,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.997577519379845,
      "tokens_p.mean_in_band": 0.6837993421052632,
      "tokens_rate.above_band": 0.9713855421686747,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0286144578313253
    },
    {
      "epoch": 1.2408577127659575,
      "grad_norm": 94.82940739419936,
      "learning_rate": 1.7307259718572e-07,
      "loss": 0.2434,
      "step": 7465,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44285714285714284,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.5641025641025641,
      "success_rate.epoch.env.math": 0.9630681818181818,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.9440809042236764,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.644947747939251,
      "success_rate.epoch.global": 0.8365788468881252,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9911085690515807,
      "tokens_p.mean_below_band": 1.755543053150177e-07,
      "tokens_p.mean_in_band": 0.7861328125,
      "tokens_rate.above_band": 0.9901153212520593,
      "tokens_rate.below_band": 0.0032948929159802307,
      "tokens_rate.in_band": 0.006589785831960461
    },
    {
      "epoch": 1.241688829787234,
      "grad_norm": 43.24476711455403,
      "learning_rate": 1.7304760867012732e-07,
      "loss": 0.3674,
      "step": 7470,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44285714285714284,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.5623003194888179,
      "success_rate.epoch.env.math": 0.9631728045325779,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.944279786603438,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6448114988920156,
      "success_rate.epoch.global": 0.8366958507803578,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9990208877284595,
      "tokens_p.mean_in_band": 0.6417534722222222,
      "tokens_rate.above_band": 0.9445129469790382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.055487053020961775
    },
    {
      "epoch": 1.2425199468085106,
      "grad_norm": 229.6832796178881,
      "learning_rate": 1.7302263249332598e-07,
      "loss": 0.2719,
      "step": 7475,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44285714285714284,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.5623003194888179,
      "success_rate.epoch.env.math": 0.9631728045325779,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.9444772593030124,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6448294509556134,
      "success_rate.epoch.global": 0.8370679832890239,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9898852657004831,
      "tokens_p.mean_below_band": 9.049472282640636e-11,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.971830985915493,
      "tokens_rate.below_band": 0.004694835680751174,
      "tokens_rate.in_band": 0.023474178403755867
    },
    {
      "epoch": 1.2433510638297873,
      "grad_norm": 248.54523507004134,
      "learning_rate": 1.7299766869964256e-07,
      "loss": 0.2548,
      "step": 7480,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.43661971830985913,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5151515151515151,
      "success_rate.epoch.env.logic": 0.5636942675159236,
      "success_rate.epoch.env.math": 0.963276836158192,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.9446733372572101,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6444164175973982,
      "success_rate.epoch.global": 0.8372445117335352,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9937177835051546,
      "tokens_p.mean_in_band": 0.59677734375,
      "tokens_rate.above_band": 0.9509803921568627,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049019607843137254
    },
    {
      "epoch": 1.2441821808510638,
      "grad_norm": 31.37462547237889,
      "learning_rate": 1.7297271733338174e-07,
      "loss": 0.4799,
      "step": 7485,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43661971830985913,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5632911392405063,
      "success_rate.epoch.env.math": 0.9633802816901409,
      "success_rate.epoch.env.sat": 0.05504587155963303,
      "success_rate.epoch.env.science": 0.9442160892542572,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6406405999042264,
      "success_rate.epoch.global": 0.8362881931346662,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45999999999999996,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.981434124386252,
      "tokens_p.mean_below_band": 2.0117568055866286e-07,
      "tokens_p.mean_in_band": 0.06185242674710122,
      "tokens_rate.above_band": 0.16036745406824146,
      "tokens_rate.below_band": 0.002099737532808399,
      "tokens_rate.in_band": 0.8375328083989502
    },
    {
      "epoch": 1.2450132978723405,
      "grad_norm": 124.82186128878911,
      "learning_rate": 1.7294777843882605e-07,
      "loss": 0.2841,
      "step": 7490,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43661971830985913,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5646687697160884,
      "success_rate.epoch.env.math": 0.9635854341736695,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.9443793911007026,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6407538424307153,
      "success_rate.epoch.global": 0.8364661654135338,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9924242424242424,
      "tokens_p.mean_in_band": 0.6579861111111112,
      "tokens_rate.above_band": 0.9428571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05714285714285714
    },
    {
      "epoch": 1.245844414893617,
      "grad_norm": 316.8585395516994,
      "learning_rate": 1.7292285206023589e-07,
      "loss": 0.3493,
      "step": 7495,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43661971830985913,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5642633228840125,
      "success_rate.epoch.env.math": 0.9635854341736695,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.9445740956826137,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6407346840443366,
      "success_rate.epoch.global": 0.8365817091454273,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.0000903179190752,
      "tokens_p.mean_in_band": 0.4714988425925926,
      "tokens_rate.above_band": 0.9624478442280946,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037552155771905425
    },
    {
      "epoch": 1.2466755319148937,
      "grad_norm": 0.9498932657786866,
      "learning_rate": 1.728979382418495e-07,
      "loss": 0.2038,
      "step": 7500,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43661971830985913,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.565625,
      "success_rate.epoch.env.math": 0.9637883008356546,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.9447674418604651,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6408944922221388,
      "success_rate.epoch.global": 0.8371311169219275,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9991258741258742,
      "tokens_p.mean_in_band": 0.5348557692307693,
      "tokens_rate.above_band": 0.9821428571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017857142857142856
    },
    {
      "epoch": 1.2475066489361701,
      "grad_norm": 235.16793673376912,
      "learning_rate": 1.7287303702788283e-07,
      "loss": 0.2561,
      "step": 7505,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4305555555555556,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.565625,
      "success_rate.epoch.env.math": 0.96398891966759,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.9449275362318841,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403759968084162,
      "success_rate.epoch.global": 0.837243947858473,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9990390528905289,
      "tokens_p.mean_in_band": 0.5276988636363636,
      "tokens_rate.above_band": 0.9866504854368932,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013349514563106795
    },
    {
      "epoch": 1.2483377659574468,
      "grad_norm": 884.4672010310525,
      "learning_rate": 1.728481484625294e-07,
      "loss": 0.4626,
      "step": 7510,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4305555555555556,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.565625,
      "success_rate.epoch.env.math": 0.96398891966759,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.9451817657241778,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403991085804429,
      "success_rate.epoch.global": 0.837727441515039,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9988086510263929,
      "tokens_p.mean_in_band": 0.694078947368421,
      "tokens_rate.above_band": 0.9728958630527818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02710413694721826
    },
    {
      "epoch": 1.2491688829787235,
      "grad_norm": 82.08050344934207,
      "learning_rate": 1.728232725899603e-07,
      "loss": 0.3161,
      "step": 7515,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4305555555555556,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.565625,
      "success_rate.epoch.env.math": 0.9640883977900553,
      "success_rate.epoch.env.sat": 0.05454545454545454,
      "success_rate.epoch.env.science": 0.9448909299655568,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403817124317015,
      "success_rate.epoch.global": 0.8379578246392897,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9823529411764705,
      "tokens_p.mean_in_band": 0.7098214285714286,
      "tokens_rate.above_band": 0.9239130434782609,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07608695652173914
    },
    {
      "epoch": 1.25,
      "grad_norm": 176.83054269338285,
      "learning_rate": 1.7279840945432416e-07,
      "loss": 0.3441,
      "step": 7520,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4305555555555556,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.565625,
      "success_rate.epoch.env.math": 0.9643835616438357,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.9445080091533181,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403290617544416,
      "success_rate.epoch.global": 0.8378179137486178,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9856601731601732,
      "tokens_p.mean_in_band": 0.6815185546875,
      "tokens_rate.above_band": 0.8783269961977186,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12167300380228137
    },
    {
      "epoch": 1.2508311170212765,
      "grad_norm": 86.48136312755608,
      "learning_rate": 1.7277355909974692e-07,
      "loss": 0.2084,
      "step": 7525,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4305555555555556,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5652173913043478,
      "success_rate.epoch.env.math": 0.9644808743169399,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.944634703196347,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403123706653944,
      "success_rate.epoch.global": 0.8378676470588236,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951463560334528,
      "tokens_p.mean_in_band": 0.7140625,
      "tokens_rate.above_band": 0.9766627771295215,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023337222870478413
    },
    {
      "epoch": 1.2516622340425532,
      "grad_norm": 54.12244428987018,
      "learning_rate": 1.7274872157033187e-07,
      "loss": 0.4196,
      "step": 7530,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4305555555555556,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5652173913043478,
      "success_rate.epoch.env.math": 0.9644808743169399,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.9443181818181818,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6402835959946521,
      "success_rate.epoch.global": 0.8379765395894428,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9833984375,
      "tokens_p.mean_below_band": 2.2851054382044822e-11,
      "tokens_p.mean_in_band": 0.86328125,
      "tokens_rate.above_band": 0.927536231884058,
      "tokens_rate.below_band": 0.007246376811594203,
      "tokens_rate.in_band": 0.06521739130434782
    },
    {
      "epoch": 1.2524933510638299,
      "grad_norm": 101.42877078453,
      "learning_rate": 1.7272389691015956e-07,
      "loss": 0.2857,
      "step": 7535,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4246575342465753,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5652173913043478,
      "success_rate.epoch.env.math": 0.9644808743169399,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.9445073612684032,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6397646103711285,
      "success_rate.epoch.global": 0.8380255941499086,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9935850439882697,
      "tokens_p.mean_in_band": 0.7666903409090909,
      "tokens_rate.above_band": 0.9393939393939394,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06060606060606061
    },
    {
      "epoch": 1.2533244680851063,
      "grad_norm": 88.0597909106569,
      "learning_rate": 1.7269908516328767e-07,
      "loss": 0.241,
      "step": 7540,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4246575342465753,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5652173913043478,
      "success_rate.epoch.env.math": 0.9646739130434783,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.9446952595936795,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6397992410122026,
      "success_rate.epoch.global": 0.8384979948960991,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9861111111111112,
      "tokens_p.mean_in_band": 0.7739955357142857,
      "tokens_rate.above_band": 0.9507042253521126,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04929577464788732
    },
    {
      "epoch": 1.254155585106383,
      "grad_norm": 82.27353593075074,
      "learning_rate": 1.72674286373751e-07,
      "loss": 0.2817,
      "step": 7545,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4246575342465753,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5652173913043478,
      "success_rate.epoch.env.math": 0.9646739130434783,
      "success_rate.epoch.env.sat": 0.05405405405405406,
      "success_rate.epoch.env.science": 0.9443194600674916,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6397650774189129,
      "success_rate.epoch.global": 0.8384867224445253,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.988030095759234,
      "tokens_p.mean_in_band": 0.6106627747252747,
      "tokens_rate.above_band": 0.80065717415115,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.19934282584884994
    },
    {
      "epoch": 1.2549867021276595,
      "grad_norm": 144.41834092786416,
      "learning_rate": 1.7264950058556127e-07,
      "loss": 0.3731,
      "step": 7550,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4246575342465753,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.56656346749226,
      "success_rate.epoch.env.math": 0.9648648648648649,
      "success_rate.epoch.env.sat": 0.05357142857142857,
      "success_rate.epoch.env.science": 0.9438832772166106,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6398212792076211,
      "success_rate.epoch.global": 0.8382299601015597,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9930921052631579,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_p.mean_in_band": 0.6282552083333334,
      "tokens_rate.above_band": 0.9193548387096774,
      "tokens_rate.below_band": 0.0032258064516129032,
      "tokens_rate.in_band": 0.07741935483870968
    },
    {
      "epoch": 1.2558178191489362,
      "grad_norm": 62.30315013495547,
      "learning_rate": 1.726247278427072e-07,
      "loss": 0.318,
      "step": 7555,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4246575342465753,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5679012345679012,
      "success_rate.epoch.env.math": 0.9650537634408602,
      "success_rate.epoch.env.sat": 0.05357142857142857,
      "success_rate.epoch.env.science": 0.9441028507546115,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.639980028224861,
      "success_rate.epoch.global": 0.838814600650524,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9947129909365559,
      "tokens_p.mean_in_band": 0.839111328125,
      "tokens_rate.above_band": 0.976401179941003,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02359882005899705
    },
    {
      "epoch": 1.2566489361702127,
      "grad_norm": 132.70108707197568,
      "learning_rate": 1.7259996818915436e-07,
      "loss": 0.4093,
      "step": 7560,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4189189189189189,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5661538461538461,
      "success_rate.epoch.env.math": 0.9651474530831099,
      "success_rate.epoch.env.sat": 0.05357142857142857,
      "success_rate.epoch.env.science": 0.9437012263099219,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6392714883572108,
      "success_rate.epoch.global": 0.8381981981981982,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9995865490628445,
      "tokens_p.mean_below_band": 9.255018085241318e-09,
      "tokens_p.mean_in_band": 0.6165114182692307,
      "tokens_rate.above_band": 0.9710920770877944,
      "tokens_rate.below_band": 0.0010706638115631692,
      "tokens_rate.in_band": 0.027837259100642397
    },
    {
      "epoch": 1.2574800531914894,
      "grad_norm": 79.06175651425075,
      "learning_rate": 1.7257522166884506e-07,
      "loss": 0.2467,
      "step": 7565,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.41333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5674846625766872,
      "success_rate.epoch.env.math": 0.9652406417112299,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.943301834352418,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6388137559998642,
      "success_rate.epoch.global": 0.8376436781609196,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.995434131736527,
      "tokens_p.mean_in_band": 0.6672623005319149,
      "tokens_rate.above_band": 0.9467120181405896,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05328798185941043
    },
    {
      "epoch": 1.258311170212766,
      "grad_norm": 144.34217262881566,
      "learning_rate": 1.725504883256983e-07,
      "loss": 0.6389,
      "step": 7570,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.41333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5074626865671642,
      "success_rate.epoch.env.logic": 0.5657492354740061,
      "success_rate.epoch.env.math": 0.9653333333333334,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.9434276206322796,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6386758515270718,
      "success_rate.epoch.global": 0.8376344086021505,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9971198156682027,
      "tokens_p.mean_in_band": 0.5610795454545454,
      "tokens_rate.above_band": 0.987485779294653,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012514220705346985
    },
    {
      "epoch": 1.2591422872340425,
      "grad_norm": 26.522834709665652,
      "learning_rate": 1.7252576820360972e-07,
      "loss": 0.2027,
      "step": 7575,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.41333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5657492354740061,
      "success_rate.epoch.env.math": 0.9654255319148937,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.9430624654505252,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6379726112391301,
      "success_rate.epoch.global": 0.8373838456040028,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9924933274021353,
      "tokens_p.mean_below_band": 5.400124791776761e-13,
      "tokens_p.mean_in_band": 0.8057914402173914,
      "tokens_rate.above_band": 0.9598633646456021,
      "tokens_rate.below_band": 0.0008539709649871904,
      "tokens_rate.in_band": 0.03928266438941076
    },
    {
      "epoch": 1.2599734042553192,
      "grad_norm": 108.90530153265249,
      "learning_rate": 1.7250106134645148e-07,
      "loss": 0.3732,
      "step": 7580,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.41333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5670731707317073,
      "success_rate.epoch.env.math": 0.9656992084432717,
      "success_rate.epoch.env.sat": 0.05309734513274336,
      "success_rate.epoch.env.science": 0.9431880860452289,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6381292687282922,
      "success_rate.epoch.global": 0.837847469707769,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.991875,
      "tokens_p.mean_in_band": 0.85546875,
      "tokens_rate.above_band": 0.9900990099009901,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009900990099009901
    },
    {
      "epoch": 1.2608045212765957,
      "grad_norm": 181.54067229850443,
      "learning_rate": 1.724763677980722e-07,
      "loss": 0.4089,
      "step": 7585,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.41333333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5670731707317073,
      "success_rate.epoch.env.math": 0.9657894736842105,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.942888522789676,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.638067899255566,
      "success_rate.epoch.global": 0.8377130681818182,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995,
      "tokens_p.mean_below_band": 2.7830537874251604e-10,
      "tokens_p.mean_in_band": 0.6794704861111112,
      "tokens_rate.above_band": 0.8875739644970414,
      "tokens_rate.below_band": 0.005917159763313609,
      "tokens_rate.in_band": 0.10650887573964497
    },
    {
      "epoch": 1.2616356382978724,
      "grad_norm": 87.58291830234873,
      "learning_rate": 1.7245168760229688e-07,
      "loss": 0.3688,
      "step": 7590,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5666666666666667,
      "success_rate.epoch.env.math": 0.9659685863874345,
      "success_rate.epoch.env.sat": 0.05263157894736842,
      "success_rate.epoch.env.science": 0.943013698630137,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6387603613214076,
      "success_rate.epoch.global": 0.8378761061946902,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9994077480490524,
      "tokens_p.mean_in_band": 0.5328125,
      "tokens_rate.above_band": 0.9781897491821155,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021810250817884406
    },
    {
      "epoch": 1.2624667553191489,
      "grad_norm": 313.01757503628585,
      "learning_rate": 1.7242702080292678e-07,
      "loss": 0.3031,
      "step": 7595,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5666666666666667,
      "success_rate.epoch.env.math": 0.9659685863874345,
      "success_rate.epoch.env.sat": 0.06086956521739131,
      "success_rate.epoch.env.science": 0.9426229508196722,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6394737466359128,
      "success_rate.epoch.global": 0.8378664782762275,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9914398923444976,
      "tokens_p.mean_below_band": 5.997717380523682e-07,
      "tokens_p.mean_in_band": 0.5068672558309038,
      "tokens_rate.above_band": 0.8293650793650794,
      "tokens_rate.below_band": 0.000496031746031746,
      "tokens_rate.in_band": 0.1701388888888889
    },
    {
      "epoch": 1.2632978723404256,
      "grad_norm": 88.11740418792925,
      "learning_rate": 1.7240236744373946e-07,
      "loss": 0.3213,
      "step": 7600,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5666666666666667,
      "success_rate.epoch.env.math": 0.9660574412532638,
      "success_rate.epoch.env.sat": 0.06779661016949153,
      "success_rate.epoch.env.science": 0.9417211328976035,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6400295722628093,
      "success_rate.epoch.global": 0.837029215065118,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.3333333333333333,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9955179282868526,
      "tokens_p.mean_below_band": 4.6798959374427795e-08,
      "tokens_p.mean_in_band": 0.6223958333333334,
      "tokens_rate.above_band": 0.8366666666666667,
      "tokens_rate.below_band": 0.0033333333333333335,
      "tokens_rate.in_band": 0.16
    },
    {
      "epoch": 1.2641289893617023,
      "grad_norm": 60.223873615188474,
      "learning_rate": 1.723777275684886e-07,
      "loss": 0.2599,
      "step": 7605,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5649546827794562,
      "success_rate.epoch.env.math": 0.9662337662337662,
      "success_rate.epoch.env.sat": 0.06779661016949153,
      "success_rate.epoch.env.science": 0.9418162044589451,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6398986097768669,
      "success_rate.epoch.global": 0.837021426062522,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9910416666666667,
      "tokens_p.mean_in_band": 0.525390625,
      "tokens_rate.above_band": 0.9868421052631579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013157894736842105
    },
    {
      "epoch": 1.2649601063829787,
      "grad_norm": 75.10334585640015,
      "learning_rate": 1.7235310122090397e-07,
      "loss": 0.2009,
      "step": 7610,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.42105263157894735,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5649546827794562,
      "success_rate.epoch.env.math": 0.9664082687338501,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.9420368364030336,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6398827384160473,
      "success_rate.epoch.global": 0.8372418620931047,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9904141104294478,
      "tokens_p.mean_in_band": 0.6107954545454546,
      "tokens_rate.above_band": 0.8810810810810811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11891891891891893
    },
    {
      "epoch": 1.2657912234042552,
      "grad_norm": 89.47123789519968,
      "learning_rate": 1.7232848844469122e-07,
      "loss": 0.2706,
      "step": 7615,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5615615615615616,
      "success_rate.epoch.env.math": 0.9665809768637532,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.9421308815575987,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6391014126044147,
      "success_rate.epoch.global": 0.8366492146596859,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.999929084720121,
      "tokens_p.mean_in_band": 0.62646484375,
      "tokens_rate.above_band": 0.9821693907875185,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017830609212481426
    },
    {
      "epoch": 1.266622340425532,
      "grad_norm": 134.08973388186456,
      "learning_rate": 1.7230388928353205e-07,
      "loss": 0.364,
      "step": 7620,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5611940298507463,
      "success_rate.epoch.env.math": 0.9666666666666667,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.9422869471413161,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6390899783931252,
      "success_rate.epoch.global": 0.8367560041768186,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9997344192634561,
      "tokens_p.mean_in_band": 0.7513020833333334,
      "tokens_rate.above_band": 0.9631650750341064,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.036834924965893585
    },
    {
      "epoch": 1.2674534574468086,
      "grad_norm": 39.52536572473698,
      "learning_rate": 1.7227930378108399e-07,
      "loss": 0.4201,
      "step": 7625,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5625,
      "success_rate.epoch.env.math": 0.9670050761421319,
      "success_rate.epoch.env.sat": 0.06722689075630252,
      "success_rate.epoch.env.science": 0.942380183091007,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6392479434453443,
      "success_rate.epoch.global": 0.8372093023255814,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9931175595238095,
      "tokens_p.mean_in_band": 0.859375,
      "tokens_rate.above_band": 0.9824561403508771,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017543859649122806
    },
    {
      "epoch": 1.268284574468085,
      "grad_norm": 67.08506398746117,
      "learning_rate": 1.7225473198098018e-07,
      "loss": 0.5256,
      "step": 7630,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.7142857142857143,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.5608308605341247,
      "success_rate.epoch.env.math": 0.9670886075949368,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9425040300913488,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6377654253191553,
      "success_rate.epoch.global": 0.8363321799307959,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9917110874200427,
      "tokens_p.mean_below_band": 3.9301812648773193e-07,
      "tokens_p.mean_in_band": 0.5827058232931727,
      "tokens_rate.above_band": 0.8245428973277075,
      "tokens_rate.below_band": 0.00035161744022503517,
      "tokens_rate.in_band": 0.1751054852320675
    },
    {
      "epoch": 1.2691156914893618,
      "grad_norm": 132.7669125484632,
      "learning_rate": 1.722301739268296e-07,
      "loss": 0.3246,
      "step": 7635,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.5608308605341247,
      "success_rate.epoch.env.math": 0.9671717171717171,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9426888055704339,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.629672895389169,
      "success_rate.epoch.global": 0.8364389233954451,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9898127753303965,
      "tokens_p.mean_in_band": 0.648046875,
      "tokens_rate.above_band": 0.850187265917603,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.149812734082397
    },
    {
      "epoch": 1.2699468085106382,
      "grad_norm": 39.39159648925311,
      "learning_rate": 1.7220562966221682e-07,
      "loss": 0.3642,
      "step": 7640,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.5591715976331361,
      "success_rate.epoch.env.math": 0.9671717171717171,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9429028815368197,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6295415147587506,
      "success_rate.epoch.global": 0.8365450791465933,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9973731884057971,
      "tokens_p.mean_in_band": 0.6219618055555556,
      "tokens_rate.above_band": 0.9745762711864406,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025423728813559324
    },
    {
      "epoch": 1.270777925531915,
      "grad_norm": 69.6753289548881,
      "learning_rate": 1.721810992307018e-07,
      "loss": 0.3274,
      "step": 7645,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.5591715976331361,
      "success_rate.epoch.env.math": 0.9672544080604534,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9430851063829787,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6295655980073774,
      "success_rate.epoch.global": 0.8369378647442499,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9916857798165137,
      "tokens_p.mean_in_band": 0.7927734375,
      "tokens_rate.above_band": 0.956140350877193,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043859649122807015
    },
    {
      "epoch": 1.2716090425531914,
      "grad_norm": 89.27030382498833,
      "learning_rate": 1.7215658267582013e-07,
      "loss": 0.3655,
      "step": 7650,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4857142857142857,
      "success_rate.epoch.env.logic": 0.56047197640118,
      "success_rate.epoch.env.math": 0.9675,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9431455897980872,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6297116392912593,
      "success_rate.epoch.global": 0.8372730387118876,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.9333333333333332,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9917553191489362,
      "tokens_p.mean_below_band": 2.648448571562767e-09,
      "tokens_p.mean_in_band": 0.5703125,
      "tokens_rate.above_band": 0.9873949579831933,
      "tokens_rate.below_band": 0.004201680672268907,
      "tokens_rate.in_band": 0.008403361344537815
    },
    {
      "epoch": 1.272440159574468,
      "grad_norm": 200.56429071306124,
      "learning_rate": 1.7213208004108268e-07,
      "loss": 0.5054,
      "step": 7655,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4788732394366197,
      "success_rate.epoch.env.logic": 0.56047197640118,
      "success_rate.epoch.env.math": 0.9675,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9433562731604024,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6291088790262273,
      "success_rate.epoch.global": 0.8373761530577383,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9961345665066366,
      "tokens_p.mean_in_band": 0.5514420503211992,
      "tokens_rate.above_band": 0.8834830339321357,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11651696606786427
    },
    {
      "epoch": 1.2732712765957448,
      "grad_norm": 92.1135032399493,
      "learning_rate": 1.7210759136997557e-07,
      "loss": 0.3051,
      "step": 7660,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5588235294117647,
      "success_rate.epoch.env.math": 0.9650872817955112,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9435058078141499,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6294112645838941,
      "success_rate.epoch.global": 0.8371379897785349,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9925431711145997,
      "tokens_p.mean_below_band": 2.8405338525772095e-08,
      "tokens_p.mean_in_band": 0.775,
      "tokens_rate.above_band": 0.9762452107279693,
      "tokens_rate.below_band": 0.0007662835249042146,
      "tokens_rate.in_band": 0.022988505747126436
    },
    {
      "epoch": 1.2741023936170213,
      "grad_norm": 65.59703990279134,
      "learning_rate": 1.7208311670596026e-07,
      "loss": 0.4438,
      "step": 7665,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5568513119533528,
      "success_rate.epoch.env.math": 0.9653465346534653,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9435951502372166,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6292636625677676,
      "success_rate.epoch.global": 0.8369565217391305,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982142857142857,
      "tokens_p.mean_in_band": 0.59442138671875,
      "tokens_rate.above_band": 0.9745425616547335,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02545743834526651
    },
    {
      "epoch": 1.2749335106382977,
      "grad_norm": 19.351340735188106,
      "learning_rate": 1.7205865609247322e-07,
      "loss": 0.2492,
      "step": 7670,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5568513119533528,
      "success_rate.epoch.env.math": 0.9654320987654321,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9437434279705573,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.629284920917341,
      "success_rate.epoch.global": 0.8372881355932204,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9947996918335902,
      "tokens_p.mean_in_band": 0.7075520833333333,
      "tokens_rate.above_band": 0.9774096385542169,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022590361445783132
    },
    {
      "epoch": 1.2757646276595744,
      "grad_norm": 17.405691056369445,
      "learning_rate": 1.720342095729261e-07,
      "loss": 0.2285,
      "step": 7675,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5594202898550724,
      "success_rate.epoch.env.math": 0.9656862745098039,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9438614900314796,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6295523041634332,
      "success_rate.epoch.global": 0.8377830348090571,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960477941176471,
      "tokens_p.mean_in_band": 0.7702414772727273,
      "tokens_rate.above_band": 0.9392265193370166,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06077348066298342
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 71.67340897541226,
      "learning_rate": 1.7200977719070542e-07,
      "loss": 0.2461,
      "step": 7680,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4155844155844156,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5578034682080925,
      "success_rate.epoch.env.math": 0.9656862745098039,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9435736677115988,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6293791547119004,
      "success_rate.epoch.global": 0.8376010781671159,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9964788732394366,
      "tokens_p.mean_below_band": 2.4158453015843406e-12,
      "tokens_p.mean_in_band": 0.6385216346153846,
      "tokens_rate.above_band": 0.9785604900459418,
      "tokens_rate.below_band": 0.0015313935681470138,
      "tokens_rate.in_band": 0.019908116385911178
    },
    {
      "epoch": 1.2774268617021276,
      "grad_norm": 124.24369516077107,
      "learning_rate": 1.7198535898917274e-07,
      "loss": 0.459,
      "step": 7685,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5578034682080925,
      "success_rate.epoch.env.math": 0.9658536585365853,
      "success_rate.epoch.env.sat": 0.06666666666666667,
      "success_rate.epoch.env.science": 0.9437206878582595,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6300888739542594,
      "success_rate.epoch.global": 0.8380376344086021,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9997616323417239,
      "tokens_p.mean_in_band": 0.5889269770408163,
      "tokens_rate.above_band": 0.9639705882352941,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03602941176470588
    },
    {
      "epoch": 1.2782579787234043,
      "grad_norm": 222.10974680153734,
      "learning_rate": 1.7196095501166434e-07,
      "loss": 0.2625,
      "step": 7690,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5590778097982709,
      "success_rate.epoch.env.math": 0.9658536585365853,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.9438961038961039,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.630170582448868,
      "success_rate.epoch.global": 0.8381367292225201,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9957170050761421,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_p.mean_in_band": 0.6052517361111112,
      "tokens_rate.above_band": 0.9120370370370371,
      "tokens_rate.below_band": 0.004629629629629629,
      "tokens_rate.in_band": 0.08333333333333333
    },
    {
      "epoch": 1.2790890957446808,
      "grad_norm": 49.216118031609234,
      "learning_rate": 1.7193656530149132e-07,
      "loss": 0.3442,
      "step": 7695,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4861111111111111,
      "success_rate.epoch.env.logic": 0.5590778097982709,
      "success_rate.epoch.env.math": 0.9659367396593674,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.944070429829104,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6301939830903028,
      "success_rate.epoch.global": 0.8385155466399198,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9903621495327103,
      "tokens_p.mean_in_band": 0.8419471153846154,
      "tokens_rate.above_band": 0.8916666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10833333333333334
    },
    {
      "epoch": 1.2799202127659575,
      "grad_norm": 157.99224406914018,
      "learning_rate": 1.7191218990193946e-07,
      "loss": 0.3083,
      "step": 7700,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.4230769230769231,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4931506849315068,
      "success_rate.epoch.env.logic": 0.5590778097982709,
      "success_rate.epoch.env.math": 0.9661016949152542,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.9442436757873,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6308646899116191,
      "success_rate.epoch.global": 0.839,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9886363636363636,
      "tokens_p.mean_in_band": 0.8642578125,
      "tokens_rate.above_band": 0.9929203539823008,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007079646017699115
    },
    {
      "epoch": 1.280751329787234,
      "grad_norm": 138.4902797807258,
      "learning_rate": 1.718878288562691e-07,
      "loss": 0.2881,
      "step": 7705,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4931506849315068,
      "success_rate.epoch.env.logic": 0.5574712643678161,
      "success_rate.epoch.env.math": 0.9661016949152542,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.94390118373649,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6313513977550058,
      "success_rate.epoch.global": 0.8387632978723404,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970034246575342,
      "tokens_p.mean_in_band": 0.58515625,
      "tokens_rate.above_band": 0.9776785714285714,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022321428571428572
    },
    {
      "epoch": 1.2815824468085106,
      "grad_norm": 85.17321046800986,
      "learning_rate": 1.718634822077151e-07,
      "loss": 0.3031,
      "step": 7710,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4931506849315068,
      "success_rate.epoch.env.logic": 0.5574712643678161,
      "success_rate.epoch.env.math": 0.9663461538461539,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.9440164355418593,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6313840987310303,
      "success_rate.epoch.global": 0.8391376451077943,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9956825657894737,
      "tokens_p.mean_in_band": 0.6919642857142857,
      "tokens_rate.above_band": 0.9156626506024096,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08433734939759036
    },
    {
      "epoch": 1.2824135638297873,
      "grad_norm": 51.72451180842357,
      "learning_rate": 1.7183914999948683e-07,
      "loss": 0.2251,
      "step": 7715,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5587392550143266,
      "success_rate.epoch.env.math": 0.9664268585131894,
      "success_rate.epoch.env.sat": 0.06611570247933884,
      "success_rate.epoch.env.science": 0.9441598360655737,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6321424088133716,
      "success_rate.epoch.global": 0.8395633476678795,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9919217687074829,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9932432432432432,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006756756756756757
    },
    {
      "epoch": 1.2832446808510638,
      "grad_norm": 104.89270597254156,
      "learning_rate": 1.7181483227476802e-07,
      "loss": 0.2516,
      "step": 7720,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5587392550143266,
      "success_rate.epoch.env.math": 0.9665871121718377,
      "success_rate.epoch.env.sat": 0.06504065040650407,
      "success_rate.epoch.env.science": 0.9442740286298569,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6320696264633804,
      "success_rate.epoch.global": 0.8393269548003959,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.992218875502008,
      "tokens_p.mean_in_band": 0.6833984375,
      "tokens_rate.above_band": 0.8615916955017301,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1384083044982699
    },
    {
      "epoch": 1.2840757978723405,
      "grad_norm": 116.62884366560398,
      "learning_rate": 1.717905290767166e-07,
      "loss": 0.3153,
      "step": 7725,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.56,
      "success_rate.epoch.env.math": 0.9643705463182898,
      "success_rate.epoch.env.sat": 0.06451612903225806,
      "success_rate.epoch.env.science": 0.9443593670239918,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6319428079317453,
      "success_rate.epoch.global": 0.8390388413429888,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.75,
      "tokens_p.mean_above_band": 0.9918870192307693,
      "tokens_p.mean_below_band": 3.0547380447387695e-07,
      "tokens_p.mean_in_band": 0.5863486842105263,
      "tokens_rate.above_band": 0.9122807017543859,
      "tokens_rate.below_band": 0.0043859649122807015,
      "tokens_rate.in_band": 0.08333333333333333
    },
    {
      "epoch": 1.284906914893617,
      "grad_norm": 61.1916645236904,
      "learning_rate": 1.7176624044846485e-07,
      "loss": 0.2892,
      "step": 7730,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5612535612535613,
      "success_rate.epoch.env.math": 0.964622641509434,
      "success_rate.epoch.env.sat": 0.06451612903225806,
      "success_rate.epoch.env.science": 0.9444444444444444,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.632087420101305,
      "success_rate.epoch.global": 0.8394088669950739,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964334239130435,
      "tokens_p.mean_in_band": 0.6231770833333333,
      "tokens_rate.above_band": 0.9608355091383812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0391644908616188
    },
    {
      "epoch": 1.2857380319148937,
      "grad_norm": 97.88755402057637,
      "learning_rate": 1.7174196643311917e-07,
      "loss": 0.3285,
      "step": 7735,
      "success_rate.epoch.env.abd": 0.5294117647058824,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5625,
      "success_rate.epoch.env.math": 0.964622641509434,
      "success_rate.epoch.env.sat": 0.06451612903225806,
      "success_rate.epoch.env.science": 0.9446138211382114,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6322161305958692,
      "success_rate.epoch.global": 0.8397771952817824,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9937169312169312,
      "tokens_p.mean_in_band": 0.7921875,
      "tokens_rate.above_band": 0.9742268041237113,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02577319587628866
    },
    {
      "epoch": 1.2865691489361701,
      "grad_norm": 84.25347909750369,
      "learning_rate": 1.7171770707375992e-07,
      "loss": 0.3818,
      "step": 7740,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5625,
      "success_rate.epoch.env.math": 0.9647887323943662,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.9446981227803145,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6294719998941383,
      "success_rate.epoch.global": 0.8392156862745098,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9901944294940797,
      "tokens_p.mean_in_band": 0.5656698258196722,
      "tokens_rate.above_band": 0.8839200761179828,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11607992388201713
    },
    {
      "epoch": 1.2874002659574468,
      "grad_norm": 34.29660852994889,
      "learning_rate": 1.7169346241344153e-07,
      "loss": 0.3328,
      "step": 7745,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5649717514124294,
      "success_rate.epoch.env.math": 0.9647887323943662,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.9447541814495691,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.629701800810655,
      "success_rate.epoch.global": 0.839425587467363,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9987560926076361,
      "tokens_p.mean_in_band": 0.6353125,
      "tokens_rate.above_band": 0.9800955414012739,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019904458598726114
    },
    {
      "epoch": 1.2882313829787235,
      "grad_norm": 33.844727744307455,
      "learning_rate": 1.7166923249519237e-07,
      "loss": 0.2749,
      "step": 7750,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5649717514124294,
      "success_rate.epoch.env.math": 0.9648711943793911,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.944949494949495,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6297270531274686,
      "success_rate.epoch.global": 0.83984375,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9987765089722676,
      "tokens_p.mean_in_band": 0.7222222222222222,
      "tokens_rate.above_band": 0.9855305466237942,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014469453376205787
    },
    {
      "epoch": 1.2890625,
      "grad_norm": 45.359782350325666,
      "learning_rate": 1.7164501736201456e-07,
      "loss": 0.2702,
      "step": 7755,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5633802816901409,
      "success_rate.epoch.env.math": 0.9649532710280374,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.9451158106747231,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6296049551867037,
      "success_rate.epoch.global": 0.839935064935065,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.999537037037037,
      "tokens_p.mean_in_band": 0.4560546875,
      "tokens_rate.above_band": 0.9768451519536903,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023154848046309694
    },
    {
      "epoch": 1.2898936170212765,
      "grad_norm": 74.988351784935,
      "learning_rate": 1.7162081705688406e-07,
      "loss": 0.2365,
      "step": 7760,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5646067415730337,
      "success_rate.epoch.env.math": 0.965034965034965,
      "success_rate.epoch.env.sat": 0.06349206349206349,
      "success_rate.epoch.env.science": 0.9451710261569416,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6297288978568891,
      "success_rate.epoch.global": 0.8401426718547341,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9925115207373272,
      "tokens_p.mean_in_band": 0.8139204545454546,
      "tokens_rate.above_band": 0.9517543859649122,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04824561403508772
    },
    {
      "epoch": 1.2907247340425532,
      "grad_norm": 56.988295766203706,
      "learning_rate": 1.715966316227505e-07,
      "loss": 0.3599,
      "step": 7765,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5646067415730337,
      "success_rate.epoch.env.math": 0.9651972157772621,
      "success_rate.epoch.env.sat": 0.06299212598425197,
      "success_rate.epoch.env.science": 0.9453634085213033,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6297156883658752,
      "success_rate.epoch.global": 0.8403361344537815,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940119760479041,
      "tokens_p.mean_in_band": 0.6,
      "tokens_rate.above_band": 0.9175824175824175,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08241758241758242
    },
    {
      "epoch": 1.2915558510638299,
      "grad_norm": 35.824128708039495,
      "learning_rate": 1.7157246110253704e-07,
      "loss": 0.2489,
      "step": 7770,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5630252100840336,
      "success_rate.epoch.env.math": 0.9651972157772621,
      "success_rate.epoch.env.sat": 0.06299212598425197,
      "success_rate.epoch.env.science": 0.945,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6295388756376658,
      "success_rate.epoch.global": 0.84,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9939577039274925,
      "tokens_p.mean_in_band": 0.6379024621212122,
      "tokens_rate.above_band": 0.9525179856115108,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04748201438848921
    },
    {
      "epoch": 1.2923869680851063,
      "grad_norm": 45.869845240653746,
      "learning_rate": 1.715483055391405e-07,
      "loss": 0.2914,
      "step": 7775,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.3333333333333333,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5654596100278552,
      "success_rate.epoch.env.math": 0.9652777777777778,
      "success_rate.epoch.env.sat": 0.0625,
      "success_rate.epoch.env.science": 0.945082376435347,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.629730258582705,
      "success_rate.epoch.global": 0.8400386224654007,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949383802816901,
      "tokens_p.mean_in_band": 0.7193667763157895,
      "tokens_rate.above_band": 0.9372937293729373,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0627062706270627
    },
    {
      "epoch": 1.293218085106383,
      "grad_norm": 45.28572513944938,
      "learning_rate": 1.7152416497543103e-07,
      "loss": 0.3758,
      "step": 7780,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5654596100278552,
      "success_rate.epoch.env.math": 0.9653579676674365,
      "success_rate.epoch.env.sat": 0.06201550387596899,
      "success_rate.epoch.env.science": 0.944748631159781,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6448146781424078,
      "success_rate.epoch.global": 0.8398587933247753,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9955654101995566,
      "tokens_p.mean_in_band": 0.7157118055555556,
      "tokens_rate.above_band": 0.9435146443514645,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056485355648535567
    },
    {
      "epoch": 1.2940492021276595,
      "grad_norm": 70.33801699162333,
      "learning_rate": 1.7150003945425226e-07,
      "loss": 0.2366,
      "step": 7785,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43037974683544306,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5666666666666667,
      "success_rate.epoch.env.math": 0.9655963302752294,
      "success_rate.epoch.env.sat": 0.06201550387596899,
      "success_rate.epoch.env.science": 0.9448857994041708,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6449585497324981,
      "success_rate.epoch.global": 0.84032,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9905092592592593,
      "tokens_p.mean_in_band": 0.896484375,
      "tokens_rate.above_band": 0.9926470588235294,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007352941176470588
    },
    {
      "epoch": 1.2948803191489362,
      "grad_norm": 40.558210758108984,
      "learning_rate": 1.7147592901842106e-07,
      "loss": 0.2904,
      "step": 7790,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5678670360110804,
      "success_rate.epoch.env.math": 0.9659863945578231,
      "success_rate.epoch.env.sat": 0.06201550387596899,
      "success_rate.epoch.env.science": 0.9449677739216659,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6457578825787762,
      "success_rate.epoch.global": 0.840829346092504,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9973958333333334,
      "tokens_p.mean_in_band": 0.697265625,
      "tokens_rate.above_band": 0.993103448275862,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006896551724137931
    },
    {
      "epoch": 1.2957114361702127,
      "grad_norm": 183.04553545185934,
      "learning_rate": 1.7145183371072755e-07,
      "loss": 0.2811,
      "step": 7795,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5686813186813187,
      "success_rate.epoch.env.math": 0.9659863945578231,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.9450766947055913,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6457984426802904,
      "success_rate.epoch.global": 0.8405981546293351,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971991037131882,
      "tokens_p.mean_in_band": 0.6282958984375,
      "tokens_rate.above_band": 0.9606396063960639,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03936039360393604
    },
    {
      "epoch": 1.2965425531914894,
      "grad_norm": 35.244866382635706,
      "learning_rate": 1.7142775357393502e-07,
      "loss": 0.4762,
      "step": 7800,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5683060109289617,
      "success_rate.epoch.env.math": 0.9659863945578231,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.9451581027667985,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6457717245265495,
      "success_rate.epoch.global": 0.8405336721728082,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4166666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9996878286014721,
      "tokens_p.mean_in_band": 0.5009581367924528,
      "tokens_rate.above_band": 0.9728900255754476,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02710997442455243
    },
    {
      "epoch": 1.297373670212766,
      "grad_norm": 18.618669521771686,
      "learning_rate": 1.7140368865077978e-07,
      "loss": 0.3719,
      "step": 7805,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5694822888283378,
      "success_rate.epoch.env.math": 0.9659863945578231,
      "success_rate.epoch.env.sat": 0.06153846153846154,
      "success_rate.epoch.env.science": 0.945320197044335,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6458933947244506,
      "success_rate.epoch.global": 0.8408874801901743,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9897119341563786,
      "tokens_p.mean_in_band": 0.7223074776785714,
      "tokens_rate.above_band": 0.8966789667896679,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1033210332103321
    },
    {
      "epoch": 1.2982047872340425,
      "grad_norm": 201.23196672066155,
      "learning_rate": 1.7137963898397115e-07,
      "loss": 0.2532,
      "step": 7810,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5694822888283378,
      "success_rate.epoch.env.math": 0.9662162162162162,
      "success_rate.epoch.env.sat": 0.061068702290076333,
      "success_rate.epoch.env.science": 0.9454813359528488,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6458862312079527,
      "success_rate.epoch.global": 0.8410742496050553,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9927147239263804,
      "tokens_p.mean_in_band": 0.6484375,
      "tokens_rate.above_band": 0.9106145251396648,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0893854748603352
    },
    {
      "epoch": 1.2990359042553192,
      "grad_norm": 54.528420854433485,
      "learning_rate": 1.7135560461619146e-07,
      "loss": 0.2778,
      "step": 7815,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5679347826086957,
      "success_rate.epoch.env.math": 0.9662162162162162,
      "success_rate.epoch.env.sat": 0.061068702290076333,
      "success_rate.epoch.env.science": 0.94564152791381,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6457601117298908,
      "success_rate.epoch.global": 0.8411097099621689,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9998310810810811,
      "tokens_p.mean_below_band": 1.0277290130034089e-10,
      "tokens_p.mean_in_band": 0.4642269736842105,
      "tokens_rate.above_band": 0.9736842105263158,
      "tokens_rate.below_band": 0.0013157894736842105,
      "tokens_rate.in_band": 0.025
    },
    {
      "epoch": 1.2998670212765957,
      "grad_norm": 103.26100128942463,
      "learning_rate": 1.713315855900958e-07,
      "loss": 0.3334,
      "step": 7820,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5702702702702702,
      "success_rate.epoch.env.math": 0.9662162162162162,
      "success_rate.epoch.env.sat": 0.07462686567164178,
      "success_rate.epoch.env.science": 0.9457478005865103,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6472146502495125,
      "success_rate.epoch.global": 0.8412448915435398,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936746987951808,
      "tokens_p.mean_in_band": 0.6223958333333334,
      "tokens_rate.above_band": 0.9518348623853211,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0481651376146789
    },
    {
      "epoch": 1.3006981382978724,
      "grad_norm": 71.61746023229394,
      "learning_rate": 1.7130758194831202e-07,
      "loss": 0.3164,
      "step": 7825,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.568733153638814,
      "success_rate.epoch.env.math": 0.9662162162162162,
      "success_rate.epoch.env.sat": 0.07407407407407407,
      "success_rate.epoch.env.science": 0.9458800585080449,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6470366820397409,
      "success_rate.epoch.global": 0.8409661229611042,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9961166471277842,
      "tokens_p.mean_in_band": 0.5823863636363636,
      "tokens_rate.above_band": 0.9627539503386005,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03724604966139955
    },
    {
      "epoch": 1.3015292553191489,
      "grad_norm": 136.2477937279116,
      "learning_rate": 1.7128359373344077e-07,
      "loss": 0.4513,
      "step": 7830,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5710455764075067,
      "success_rate.epoch.env.math": 0.9662162162162162,
      "success_rate.epoch.env.sat": 0.07407407407407407,
      "success_rate.epoch.env.science": 0.9454722492697176,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.647235081249572,
      "success_rate.epoch.global": 0.8406885758998435,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986328591919675,
      "tokens_p.mean_below_band": 2.7120113372802733e-07,
      "tokens_p.mean_in_band": 0.48908617424242423,
      "tokens_rate.above_band": 0.9609464736963014,
      "tokens_rate.below_band": 0.0011486331265793705,
      "tokens_rate.in_band": 0.03790489317711923
    },
    {
      "epoch": 1.3023603723404256,
      "grad_norm": 43.5416123814797,
      "learning_rate": 1.712596209880552e-07,
      "loss": 0.3195,
      "step": 7835,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5721925133689839,
      "success_rate.epoch.env.math": 0.9662921348314607,
      "success_rate.epoch.env.sat": 0.07407407407407407,
      "success_rate.epoch.env.science": 0.9456574478408539,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6473630861721046,
      "success_rate.epoch.global": 0.8411360799001248,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9994688385269122,
      "tokens_p.mean_in_band": 0.6610054347826086,
      "tokens_rate.above_band": 0.9684499314128944,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03155006858710562
    },
    {
      "epoch": 1.3031914893617023,
      "grad_norm": 124.36568743877578,
      "learning_rate": 1.712356637547011e-07,
      "loss": 0.3671,
      "step": 7840,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5706666666666667,
      "success_rate.epoch.env.math": 0.9662921348314607,
      "success_rate.epoch.env.sat": 0.07352941176470588,
      "success_rate.epoch.env.science": 0.94581519109821,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6471891983762564,
      "success_rate.epoch.global": 0.8409090909090909,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974850968703428,
      "tokens_p.mean_in_band": 0.5109375,
      "tokens_rate.above_band": 0.9437412095639943,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05625879043600562
    },
    {
      "epoch": 1.3040226063829787,
      "grad_norm": 83.12046904820303,
      "learning_rate": 1.7121172207589668e-07,
      "loss": 0.2877,
      "step": 7845,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5740740740740741,
      "success_rate.epoch.env.math": 0.9662921348314607,
      "success_rate.epoch.env.sat": 0.07971014492753623,
      "success_rate.epoch.env.science": 0.9454106280193236,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6480240690572884,
      "success_rate.epoch.global": 0.8406832298136646,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9936061381074168,
      "tokens_p.mean_in_band": 0.6761363636363636,
      "tokens_rate.above_band": 0.9467312348668281,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.053268765133171914
    },
    {
      "epoch": 1.3048537234042552,
      "grad_norm": 564.5812448606076,
      "learning_rate": 1.7118779599413248e-07,
      "loss": 0.2138,
      "step": 7850,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5740740740740741,
      "success_rate.epoch.env.math": 0.9663677130044843,
      "success_rate.epoch.env.sat": 0.07971014492753623,
      "success_rate.epoch.env.science": 0.9455684007707129,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6480452827776896,
      "success_rate.epoch.global": 0.8410288193368454,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978693181818182,
      "tokens_p.mean_in_band": 0.68359375,
      "tokens_rate.above_band": 0.9806835066864784,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019316493313521546
    },
    {
      "epoch": 1.305684840425532,
      "grad_norm": 70.87256434077706,
      "learning_rate": 1.7116388555187155e-07,
      "loss": 0.1972,
      "step": 7855,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.575197889182058,
      "success_rate.epoch.env.math": 0.9663677130044843,
      "success_rate.epoch.env.sat": 0.07913669064748201,
      "success_rate.epoch.env.science": 0.9456730769230769,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6481048315940799,
      "success_rate.epoch.global": 0.8410145375811939,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9939350328947368,
      "tokens_p.mean_in_band": 0.6740056818181818,
      "tokens_rate.above_band": 0.9325153374233128,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06748466257668712
    },
    {
      "epoch": 1.3065159574468086,
      "grad_norm": 119.48117115616687,
      "learning_rate": 1.71139990791549e-07,
      "loss": 0.3086,
      "step": 7860,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5774278215223098,
      "success_rate.epoch.env.math": 0.9663677130044843,
      "success_rate.epoch.env.sat": 0.07857142857142857,
      "success_rate.epoch.env.science": 0.9457773512476008,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6482656447385092,
      "success_rate.epoch.global": 0.8410493827160493,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936868686868687,
      "tokens_p.mean_in_band": 0.728125,
      "tokens_rate.above_band": 0.9369085173501577,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06309148264984227
    },
    {
      "epoch": 1.307347074468085,
      "grad_norm": 42.676069946877085,
      "learning_rate": 1.7111611175557222e-07,
      "loss": 0.3076,
      "step": 7865,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5774278215223098,
      "success_rate.epoch.env.math": 0.9663677130044843,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.945933014354067,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6481791923082757,
      "success_rate.epoch.global": 0.8408251231527094,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9925176056338029,
      "tokens_p.mean_in_band": 0.5514508928571429,
      "tokens_rate.above_band": 0.8588709677419355,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14112903225806453
    },
    {
      "epoch": 1.3081781914893618,
      "grad_norm": 0.0,
      "learning_rate": 1.710922484863206e-07,
      "loss": 0.266,
      "step": 7870,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.43902439024390244,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5785340314136126,
      "success_rate.epoch.env.math": 0.9664429530201343,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9460877862595419,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6478079348184472,
      "success_rate.epoch.global": 0.8409579367516119,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9928925992779783,
      "tokens_p.mean_in_band": 0.580078125,
      "tokens_rate.above_band": 0.992831541218638,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007168458781362007
    },
    {
      "epoch": 1.3090093085106382,
      "grad_norm": 116.18762386106206,
      "learning_rate": 1.710684010261456e-07,
      "loss": 0.194,
      "step": 7875,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4457831325301205,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.577023498694517,
      "success_rate.epoch.env.math": 0.9664429530201343,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9462160875773441,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6482967085352584,
      "success_rate.epoch.global": 0.8409926470588235,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976461038961039,
      "tokens_p.mean_in_band": 0.5659375,
      "tokens_rate.above_band": 0.9685534591194969,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.031446540880503145
    },
    {
      "epoch": 1.309840425531915,
      "grad_norm": 160.8591830017501,
      "learning_rate": 1.7104456941737065e-07,
      "loss": 0.4221,
      "step": 7880,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4457831325301205,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.577023498694517,
      "success_rate.epoch.env.math": 0.9666666666666667,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9463946869070209,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6483332824421866,
      "success_rate.epoch.global": 0.8414783139890043,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9870495495495496,
      "tokens_p.mean_in_band": 0.8779296875,
      "tokens_rate.above_band": 0.9652173913043478,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034782608695652174
    },
    {
      "epoch": 1.3106715425531914,
      "grad_norm": 65.3715205302918,
      "learning_rate": 1.7102075370229101e-07,
      "loss": 0.2971,
      "step": 7885,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4457831325301205,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5755208333333334,
      "success_rate.epoch.env.math": 0.9666666666666667,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9464962121212122,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6482059060651874,
      "success_rate.epoch.global": 0.841415065568771,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9926362297496318,
      "tokens_p.mean_in_band": 0.6958912037037037,
      "tokens_rate.above_band": 0.9617563739376771,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03824362606232295
    },
    {
      "epoch": 1.311502659574468,
      "grad_norm": 68.79483226085244,
      "learning_rate": 1.7099695392317374e-07,
      "loss": 0.296,
      "step": 7890,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5755208333333334,
      "success_rate.epoch.env.math": 0.9667405764966741,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9466225791213982,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6483400849587769,
      "success_rate.epoch.global": 0.8414968055978096,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.995846313603323,
      "tokens_p.mean_in_band": 0.557421875,
      "tokens_rate.above_band": 0.9948347107438017,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005165289256198347
    },
    {
      "epoch": 1.3123337765957448,
      "grad_norm": 92.85074060125947,
      "learning_rate": 1.7097317012225757e-07,
      "loss": 0.2929,
      "step": 7895,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5755208333333334,
      "success_rate.epoch.env.math": 0.9668141592920354,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.946773433820066,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.648360488367325,
      "success_rate.epoch.global": 0.8418336369156041,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988155976676385,
      "tokens_p.mean_in_band": 0.5561810661764706,
      "tokens_rate.above_band": 0.9527777777777777,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04722222222222222
    },
    {
      "epoch": 1.3131648936170213,
      "grad_norm": 52.05855833697158,
      "learning_rate": 1.70949402341753e-07,
      "loss": 0.3807,
      "step": 7900,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49333333333333335,
      "success_rate.epoch.env.logic": 0.5755208333333334,
      "success_rate.epoch.env.math": 0.9668874172185431,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9468984962406015,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6483785174897835,
      "success_rate.epoch.global": 0.8421212121212122,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9873991935483871,
      "tokens_p.mean_in_band": 0.8671875,
      "tokens_rate.above_band": 0.992,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008
    },
    {
      "epoch": 1.3139960106382977,
      "grad_norm": 127.58702723849014,
      "learning_rate": 1.7092565062384197e-07,
      "loss": 0.2928,
      "step": 7905,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5755208333333334,
      "success_rate.epoch.env.math": 0.967032967032967,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9469981238273921,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.647810694701696,
      "success_rate.epoch.global": 0.8421530087692773,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9993508026440038,
      "tokens_p.mean_in_band": 0.6882512019230769,
      "tokens_rate.above_band": 0.9878731343283582,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012126865671641791
    },
    {
      "epoch": 1.3148271276595744,
      "grad_norm": 98.7251028939823,
      "learning_rate": 1.7090191501067795e-07,
      "loss": 0.28,
      "step": 7910,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.574025974025974,
      "success_rate.epoch.env.math": 0.9672489082969432,
      "success_rate.epoch.env.sat": 0.07746478873239436,
      "success_rate.epoch.env.science": 0.9471221338324755,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6477057030618506,
      "success_rate.epoch.global": 0.8422798552472859,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9946205007824727,
      "tokens_p.mean_in_band": 0.5904947916666666,
      "tokens_rate.above_band": 0.9726027397260274,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0273972602739726
    },
    {
      "epoch": 1.3156582446808511,
      "grad_norm": 1014.5527849798041,
      "learning_rate": 1.7087819554438587e-07,
      "loss": 0.3109,
      "step": 7915,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.574025974025974,
      "success_rate.epoch.env.math": 0.9673202614379085,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.947196261682243,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6471971040407855,
      "success_rate.epoch.global": 0.8419626730885009,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9945469798657718,
      "tokens_p.mean_in_band": 0.6200086805555556,
      "tokens_rate.above_band": 0.9430379746835443,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056962025316455694
    },
    {
      "epoch": 1.3164893617021276,
      "grad_norm": 41.45903796314505,
      "learning_rate": 1.7085449226706193e-07,
      "loss": 0.3286,
      "step": 7920,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.625,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4805194805194805,
      "success_rate.epoch.env.logic": 0.5736434108527132,
      "success_rate.epoch.env.math": 0.9674620390455532,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9472947761194029,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6466093862342278,
      "success_rate.epoch.global": 0.8417892524767338,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975282485875706,
      "tokens_p.mean_below_band": 1.6916601452976465e-10,
      "tokens_p.mean_in_band": 0.7094907407407407,
      "tokens_rate.above_band": 0.9827267119062307,
      "tokens_rate.below_band": 0.0006169031462060457,
      "tokens_rate.in_band": 0.016656384947563233
    },
    {
      "epoch": 1.3173204787234043,
      "grad_norm": 133.09126217363126,
      "learning_rate": 1.7083080522077372e-07,
      "loss": 0.3157,
      "step": 7925,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.5747422680412371,
      "success_rate.epoch.env.math": 0.9675324675324676,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9469026548672567,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6409723613832146,
      "success_rate.epoch.global": 0.841521869382864,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7666666666666667,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9980181747873164,
      "tokens_p.mean_below_band": 4.1443854570388794e-08,
      "tokens_p.mean_in_band": 0.5224358974358975,
      "tokens_rate.above_band": 0.8917241379310344,
      "tokens_rate.below_band": 0.000689655172413793,
      "tokens_rate.in_band": 0.10758620689655173
    },
    {
      "epoch": 1.3181515957446808,
      "grad_norm": 33.978257926965945,
      "learning_rate": 1.7080713444755986e-07,
      "loss": 0.2957,
      "step": 7930,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4482758620689655,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.5732647814910026,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.07692307692307693,
      "success_rate.epoch.env.science": 0.9469767441860465,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.641447040262546,
      "success_rate.epoch.global": 0.8416019127316199,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9969063845050216,
      "tokens_p.mean_below_band": 5.3085386753082275e-08,
      "tokens_p.mean_in_band": 0.589599609375,
      "tokens_rate.above_band": 0.9761904761904762,
      "tokens_rate.below_band": 0.0014005602240896359,
      "tokens_rate.in_band": 0.022408963585434174
    },
    {
      "epoch": 1.3189827127659575,
      "grad_norm": 144.45895246177582,
      "learning_rate": 1.7078347998943022e-07,
      "loss": 0.2749,
      "step": 7935,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4482758620689655,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.5732647814910026,
      "success_rate.epoch.env.math": 0.9678111587982833,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9471243042671614,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6444418429243157,
      "success_rate.epoch.global": 0.842026825633383,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9920280612244898,
      "tokens_p.mean_in_band": 0.651875,
      "tokens_rate.above_band": 0.9216300940438872,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07836990595611286
    },
    {
      "epoch": 1.319813829787234,
      "grad_norm": 60.51122395493921,
      "learning_rate": 1.7075984188836562e-07,
      "loss": 0.3397,
      "step": 7940,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4431818181818182,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48717948717948717,
      "success_rate.epoch.env.logic": 0.5743589743589743,
      "success_rate.epoch.env.math": 0.9680170575692963,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9471733086190918,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6441013931155674,
      "success_rate.epoch.global": 0.8420582986317668,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9939769553072626,
      "tokens_p.mean_in_band": 0.73095703125,
      "tokens_rate.above_band": 0.988950276243094,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011049723756906077
    },
    {
      "epoch": 1.3206449468085106,
      "grad_norm": 62.699437822293184,
      "learning_rate": 1.7073622018631798e-07,
      "loss": 0.321,
      "step": 7945,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4431818181818182,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4936708860759494,
      "success_rate.epoch.env.logic": 0.5739795918367347,
      "success_rate.epoch.env.math": 0.9680851063829787,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9472954230235784,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6446743185330575,
      "success_rate.epoch.global": 0.8421833283892021,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9946737683089214,
      "tokens_p.mean_in_band": 0.7052017405063291,
      "tokens_rate.above_band": 0.9048192771084337,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09518072289156626
    },
    {
      "epoch": 1.3214760638297873,
      "grad_norm": 103.37139911912308,
      "learning_rate": 1.7071261492520996e-07,
      "loss": 0.3286,
      "step": 7950,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4431818181818182,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4936708860759494,
      "success_rate.epoch.env.logic": 0.5739795918367347,
      "success_rate.epoch.env.math": 0.9681528662420382,
      "success_rate.epoch.env.sat": 0.08275862068965517,
      "success_rate.epoch.env.science": 0.9474412171507607,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.644641485927836,
      "success_rate.epoch.global": 0.8422610239715892,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944957386363636,
      "tokens_p.mean_in_band": 0.6982421875,
      "tokens_rate.above_band": 0.9565217391304348,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043478260869565216
    },
    {
      "epoch": 1.3223071808510638,
      "grad_norm": 53.50656227034014,
      "learning_rate": 1.7068902614693514e-07,
      "loss": 0.4684,
      "step": 7955,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4431818181818182,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5750636132315522,
      "success_rate.epoch.env.math": 0.9682875264270613,
      "success_rate.epoch.env.sat": 0.0821917808219178,
      "success_rate.epoch.env.science": 0.9474654377880184,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6441419564981461,
      "success_rate.epoch.global": 0.8419497784342689,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9950044404973357,
      "tokens_p.mean_in_band": 0.6307641006097561,
      "tokens_rate.above_band": 0.9321192052980133,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06788079470198675
    },
    {
      "epoch": 1.3231382978723405,
      "grad_norm": 78.7339542445413,
      "learning_rate": 1.7066545389335782e-07,
      "loss": 0.4022,
      "step": 7960,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4431818181818182,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5750636132315522,
      "success_rate.epoch.env.math": 0.9682875264270613,
      "success_rate.epoch.env.sat": 0.0821917808219178,
      "success_rate.epoch.env.science": 0.9471507352941176,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6441133471805188,
      "success_rate.epoch.global": 0.8419345325862577,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941056910569106,
      "tokens_p.mean_in_band": 0.2910070586622807,
      "tokens_rate.above_band": 0.7295373665480427,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2704626334519573
    },
    {
      "epoch": 1.323969414893617,
      "grad_norm": 32.7728521523835,
      "learning_rate": 1.7064189820631298e-07,
      "loss": 0.325,
      "step": 7965,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4431818181818182,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5761421319796954,
      "success_rate.epoch.env.math": 0.9683544303797469,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.9473202015574896,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.644182052744474,
      "success_rate.epoch.global": 0.8421052631578947,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9933712121212122,
      "tokens_p.mean_in_band": 0.7447916666666666,
      "tokens_rate.above_band": 0.9041095890410958,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0958904109589041
    },
    {
      "epoch": 1.3248005319148937,
      "grad_norm": 39.58354034681417,
      "learning_rate": 1.706183591276062e-07,
      "loss": 0.3829,
      "step": 7970,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5746835443037974,
      "success_rate.epoch.env.math": 0.9683544303797469,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.9474885844748858,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6446335235905531,
      "success_rate.epoch.global": 0.8422287390029326,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992529880478087,
      "tokens_p.mean_in_band": 0.670703125,
      "tokens_rate.above_band": 0.9741267787839586,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0258732212160414
    },
    {
      "epoch": 1.3256316489361701,
      "grad_norm": 147.88389160321034,
      "learning_rate": 1.7059483669901358e-07,
      "loss": 0.2915,
      "step": 7975,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5757575757575758,
      "success_rate.epoch.env.math": 0.9683544303797469,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.947632058287796,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6447442058875249,
      "success_rate.epoch.global": 0.842551946151595,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9907738095238096,
      "tokens_p.mean_in_band": 0.828515625,
      "tokens_rate.above_band": 0.9692307692307692,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03076923076923077
    },
    {
      "epoch": 1.3264627659574468,
      "grad_norm": 25.526319341458443,
      "learning_rate": 1.7057133096228166e-07,
      "loss": 0.2057,
      "step": 7980,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5757575757575758,
      "success_rate.epoch.env.math": 0.9684873949579832,
      "success_rate.epoch.env.sat": 0.08163265306122448,
      "success_rate.epoch.env.science": 0.9477272727272728,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6447649494345897,
      "success_rate.epoch.global": 0.8428279287174992,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944267515923567,
      "tokens_p.mean_in_band": 0.5390888342696629,
      "tokens_rate.above_band": 0.8858681713259811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11413182867401898
    },
    {
      "epoch": 1.3272938829787235,
      "grad_norm": 126.87769291316708,
      "learning_rate": 1.7054784195912733e-07,
      "loss": 0.1923,
      "step": 7985,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5743073047858942,
      "success_rate.epoch.env.math": 0.9684873949579832,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.9478221415607986,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6452058387653585,
      "success_rate.epoch.global": 0.8428113152522602,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9984817813765182,
      "tokens_p.mean_below_band": 1.6079866327345371e-09,
      "tokens_p.mean_in_band": 0.565625,
      "tokens_rate.above_band": 0.9755134281200631,
      "tokens_rate.below_band": 0.0007898894154818325,
      "tokens_rate.in_band": 0.023696682464454975
    },
    {
      "epoch": 1.328125,
      "grad_norm": 243.32881266861213,
      "learning_rate": 1.7052436973123787e-07,
      "loss": 0.2514,
      "step": 7990,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5753768844221105,
      "success_rate.epoch.env.math": 0.9684873949579832,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.9479402444545043,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6453138099044424,
      "success_rate.epoch.global": 0.8430858806404657,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951265389876881,
      "tokens_p.mean_in_band": 0.5965401785714286,
      "tokens_rate.above_band": 0.9812080536912752,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01879194630872483
    },
    {
      "epoch": 1.3289561170212765,
      "grad_norm": 125.78788675640281,
      "learning_rate": 1.705009143202707e-07,
      "loss": 0.3716,
      "step": 7995,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5753768844221105,
      "success_rate.epoch.env.math": 0.9684873949579832,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.9481514878268711,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6453330138473848,
      "success_rate.epoch.global": 0.8434959349593496,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963450292397661,
      "tokens_p.mean_in_band": 0.6463913690476191,
      "tokens_rate.above_band": 0.9702127659574468,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029787234042553193
    },
    {
      "epoch": 1.3297872340425532,
      "grad_norm": 49.26032274536303,
      "learning_rate": 1.7047747576785347e-07,
      "loss": 0.1993,
      "step": 8000,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49382716049382713,
      "success_rate.epoch.env.logic": 0.5753768844221105,
      "success_rate.epoch.env.math": 0.9686192468619247,
      "success_rate.epoch.env.sat": 0.08783783783783784,
      "success_rate.epoch.env.science": 0.9481981981981982,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.64592444319003,
      "success_rate.epoch.global": 0.8437228182081763,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9932795698924731,
      "tokens_p.mean_in_band": 0.558203125,
      "tokens_rate.above_band": 0.9903194578896418,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00968054211035818
    },
    {
      "epoch": 1.3306183510638299,
      "grad_norm": 110.32576412481902,
      "learning_rate": 1.7045405411558382e-07,
      "loss": 0.2353,
      "step": 8005,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49382716049382713,
      "success_rate.epoch.env.logic": 0.5753768844221105,
      "success_rate.epoch.env.math": 0.9686847599164927,
      "success_rate.epoch.env.sat": 0.087248322147651,
      "success_rate.epoch.env.science": 0.9483610237988325,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6458916089141222,
      "success_rate.epoch.global": 0.8438403701561596,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9926697530864198,
      "tokens_p.mean_in_band": 0.6223958333333334,
      "tokens_rate.above_band": 0.9,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1
    },
    {
      "epoch": 1.3314494680851063,
      "grad_norm": 184.91759656046762,
      "learning_rate": 1.7043064940502947e-07,
      "loss": 0.3444,
      "step": 8010,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49382716049382713,
      "success_rate.epoch.env.logic": 0.5764411027568922,
      "success_rate.epoch.env.math": 0.9686847599164927,
      "success_rate.epoch.env.sat": 0.087248322147651,
      "success_rate.epoch.env.science": 0.948051948051948,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6459602582402947,
      "success_rate.epoch.global": 0.8438672438672439,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.997774092178771,
      "tokens_p.mean_below_band": 3.1650415621697903e-10,
      "tokens_p.mean_in_band": 0.7172475961538461,
      "tokens_rate.above_band": 0.9808219178082191,
      "tokens_rate.below_band": 0.0013698630136986301,
      "tokens_rate.in_band": 0.01780821917808219
    },
    {
      "epoch": 1.332280585106383,
      "grad_norm": 57.22127420728385,
      "learning_rate": 1.7040726167772802e-07,
      "loss": 0.3172,
      "step": 8015,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5775,
      "success_rate.epoch.env.math": 0.9686847599164927,
      "success_rate.epoch.env.sat": 0.08666666666666667,
      "success_rate.epoch.env.science": 0.9481911567664135,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6454688189704348,
      "success_rate.epoch.global": 0.8436960276338514,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9951657458563536,
      "tokens_p.mean_below_band": 2.2470914018413168e-13,
      "tokens_p.mean_in_band": 0.6779513888888888,
      "tokens_rate.above_band": 0.9501312335958005,
      "tokens_rate.below_band": 0.0026246719160104987,
      "tokens_rate.in_band": 0.047244094488188976
    },
    {
      "epoch": 1.3331117021276595,
      "grad_norm": 83.76120591697925,
      "learning_rate": 1.7038389097518702e-07,
      "loss": 0.1957,
      "step": 8020,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5775,
      "success_rate.epoch.env.math": 0.9688149688149689,
      "success_rate.epoch.env.sat": 0.08666666666666667,
      "success_rate.epoch.env.science": 0.9483526268922529,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6454953352453726,
      "success_rate.epoch.global": 0.8440999138673557,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9866935483870968,
      "tokens_p.mean_in_band": 0.8458806818181818,
      "tokens_rate.above_band": 0.9337349397590361,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06626506024096386
    },
    {
      "epoch": 1.3339428191489362,
      "grad_norm": 116.76877475560637,
      "learning_rate": 1.7036053733888368e-07,
      "loss": 0.377,
      "step": 8025,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.449438202247191,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5781637717121588,
      "success_rate.epoch.env.math": 0.9688796680497925,
      "success_rate.epoch.env.sat": 0.08609271523178808,
      "success_rate.epoch.env.science": 0.948421520675856,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6455156455449823,
      "success_rate.epoch.global": 0.8438842738470352,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9946826660600546,
      "tokens_p.mean_in_band": 0.6218428938356164,
      "tokens_rate.above_band": 0.8338391502276176,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1661608497723824
    },
    {
      "epoch": 1.3347739361702127,
      "grad_norm": 80.86425458268842,
      "learning_rate": 1.7033720081026498e-07,
      "loss": 0.2547,
      "step": 8030,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5792079207920792,
      "success_rate.epoch.env.math": 0.968944099378882,
      "success_rate.epoch.env.sat": 0.08552631578947369,
      "success_rate.epoch.env.science": 0.9485130936529073,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6461293825679016,
      "success_rate.epoch.global": 0.8439554158330952,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.997878590078329,
      "tokens_p.mean_in_band": 0.6351102941176471,
      "tokens_rate.above_band": 0.9575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0425
    },
    {
      "epoch": 1.3356050531914894,
      "grad_norm": 51.291575262262754,
      "learning_rate": 1.7031388143074758e-07,
      "loss": 0.4153,
      "step": 8035,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5792079207920792,
      "success_rate.epoch.env.math": 0.968944099378882,
      "success_rate.epoch.env.sat": 0.08552631578947369,
      "success_rate.epoch.env.science": 0.947787610619469,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6456083291097614,
      "success_rate.epoch.global": 0.8434559452523525,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.3888888888888889,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9935581140350878,
      "tokens_p.mean_in_band": 0.63984375,
      "tokens_rate.above_band": 0.9785407725321889,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02145922746781116
    },
    {
      "epoch": 1.336436170212766,
      "grad_norm": 120.25845189976242,
      "learning_rate": 1.7029057924171767e-07,
      "loss": 0.3245,
      "step": 8040,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5792079207920792,
      "success_rate.epoch.env.math": 0.968944099378882,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.9479028697571744,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6455679894379132,
      "success_rate.epoch.global": 0.843438656419015,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9990646258503402,
      "tokens_p.mean_in_band": 0.6140802556818182,
      "tokens_rate.above_band": 0.9435173299101413,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05648267008985879
    },
    {
      "epoch": 1.3372672872340425,
      "grad_norm": 49.072460945603204,
      "learning_rate": 1.7026729428453087e-07,
      "loss": 0.2834,
      "step": 8045,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5777777777777777,
      "success_rate.epoch.env.math": 0.9690721649484536,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.9479947113265755,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6454579679947015,
      "success_rate.epoch.global": 0.8434659090909091,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9908364661654135,
      "tokens_p.mean_in_band": 0.7002467105263158,
      "tokens_rate.above_band": 0.9333333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06666666666666667
    },
    {
      "epoch": 1.3380984042553192,
      "grad_norm": 39.61924425235563,
      "learning_rate": 1.702440266005123e-07,
      "loss": 0.3767,
      "step": 8050,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4878048780487805,
      "success_rate.epoch.env.logic": 0.5763546798029556,
      "success_rate.epoch.env.math": 0.9691991786447639,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.9480633802816901,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6453463847834835,
      "success_rate.epoch.global": 0.84344866704481,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9961988304093568,
      "tokens_p.mean_in_band": 0.68359375,
      "tokens_rate.above_band": 0.981630309988519,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018369690011481057
    },
    {
      "epoch": 1.3389295212765957,
      "grad_norm": 69.17395267168801,
      "learning_rate": 1.7022077623095643e-07,
      "loss": 0.2954,
      "step": 8055,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5763546798029556,
      "success_rate.epoch.env.math": 0.9693251533742331,
      "success_rate.epoch.env.sat": 0.08496732026143791,
      "success_rate.epoch.env.science": 0.9481318681318681,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6459250655239676,
      "success_rate.epoch.global": 0.8437146092865232,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9938033681214421,
      "tokens_p.mean_in_band": 0.7822779605263158,
      "tokens_rate.above_band": 0.9652014652014652,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0347985347985348
    },
    {
      "epoch": 1.3397606382978724,
      "grad_norm": 51.05556502055433,
      "learning_rate": 1.7019754321712695e-07,
      "loss": 0.392,
      "step": 8060,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5763546798029556,
      "success_rate.epoch.env.math": 0.9693877551020408,
      "success_rate.epoch.env.sat": 0.08441558441558442,
      "success_rate.epoch.env.science": 0.9478070175438597,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6458510669143261,
      "success_rate.epoch.global": 0.8434586041254591,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9905857740585774,
      "tokens_p.mean_below_band": 1.126900315284729e-07,
      "tokens_p.mean_in_band": 0.7066865808823529,
      "tokens_rate.above_band": 0.8722627737226277,
      "tokens_rate.below_band": 0.0036496350364963502,
      "tokens_rate.in_band": 0.12408759124087591
    },
    {
      "epoch": 1.3405917553191489,
      "grad_norm": 38.75034963762497,
      "learning_rate": 1.7017432760025677e-07,
      "loss": 0.3619,
      "step": 8065,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44565217391304346,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5763546798029556,
      "success_rate.epoch.env.math": 0.9694501018329938,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.9478527607361963,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6453661756973474,
      "success_rate.epoch.global": 0.8431151241534989,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9965744570837642,
      "tokens_p.mean_in_band": 0.6471354166666666,
      "tokens_rate.above_band": 0.9757820383451059,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024217961654894045
    },
    {
      "epoch": 1.3414228723404256,
      "grad_norm": 130.59590338037611,
      "learning_rate": 1.7015112942154793e-07,
      "loss": 0.4773,
      "step": 8070,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44565217391304346,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5749385749385749,
      "success_rate.epoch.env.math": 0.967479674796748,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.9479440069991251,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.645614249401697,
      "success_rate.epoch.global": 0.8428611658687694,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9945293942992874,
      "tokens_p.mean_below_band": 2.1047890186309814e-07,
      "tokens_p.mean_in_band": 0.5278463084795322,
      "tokens_rate.above_band": 0.8911939034716342,
      "tokens_rate.below_band": 0.00021168501270110075,
      "tokens_rate.in_band": 0.1085944115156647
    },
    {
      "epoch": 1.3422539893617023,
      "grad_norm": 141.17121286279115,
      "learning_rate": 1.701279487221715e-07,
      "loss": 0.2639,
      "step": 8075,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44565217391304346,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5749385749385749,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.9475982532751092,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6456066591256158,
      "success_rate.epoch.global": 0.8429334082607474,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9166666666666667,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9922445255474452,
      "tokens_p.mean_below_band": 4.6798959374427795e-08,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9856115107913669,
      "tokens_rate.below_band": 0.007194244604316547,
      "tokens_rate.in_band": 0.007194244604316547
    },
    {
      "epoch": 1.3430851063829787,
      "grad_norm": 96.49923872240176,
      "learning_rate": 1.7010478554326752e-07,
      "loss": 0.3327,
      "step": 8080,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5749385749385749,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.9468641114982579,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6460818034470623,
      "success_rate.epoch.global": 0.8426808749298934,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9948949824970829,
      "tokens_p.mean_in_band": 0.6080078125,
      "tokens_rate.above_band": 0.9345692475463467,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06543075245365322
    },
    {
      "epoch": 1.3439162234042552,
      "grad_norm": 86.9066090915904,
      "learning_rate": 1.7008163992594499e-07,
      "loss": 0.3098,
      "step": 8085,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5745721271393643,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.9469565217391305,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6460568909417589,
      "success_rate.epoch.global": 0.8427092079485027,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9970649171270718,
      "tokens_p.mean_below_band": 2.7830537874251604e-10,
      "tokens_p.mean_in_band": 0.6667668269230769,
      "tokens_rate.above_band": 0.9890710382513661,
      "tokens_rate.below_band": 0.00078064012490242,
      "tokens_rate.in_band": 0.01014832162373146
    },
    {
      "epoch": 1.344747340425532,
      "grad_norm": 106.02571468541893,
      "learning_rate": 1.7005851191128172e-07,
      "loss": 0.2359,
      "step": 8090,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5745721271393643,
      "success_rate.epoch.env.math": 0.9678068410462777,
      "success_rate.epoch.env.sat": 0.08387096774193549,
      "success_rate.epoch.env.science": 0.9470945359930616,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6460753381977896,
      "success_rate.epoch.global": 0.8430167597765363,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940476190476191,
      "tokens_p.mean_in_band": 0.7249540441176471,
      "tokens_rate.above_band": 0.9081081081081082,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0918918918918919
    },
    {
      "epoch": 1.3455784574468086,
      "grad_norm": 89.48001110103597,
      "learning_rate": 1.7003540154032425e-07,
      "loss": 0.2883,
      "step": 8095,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058823529411764,
      "success_rate.epoch.env.logic": 0.5745721271393643,
      "success_rate.epoch.env.math": 0.9678068410462777,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9471632741446514,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6461307076611219,
      "success_rate.epoch.global": 0.8427216954824317,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9901859504132231,
      "tokens_p.mean_in_band": 0.7865323153409091,
      "tokens_rate.above_band": 0.9428571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05714285714285714
    },
    {
      "epoch": 1.346409574468085,
      "grad_norm": 131.98335158202892,
      "learning_rate": 1.700123088540878e-07,
      "loss": 0.3112,
      "step": 8100,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058823529411764,
      "success_rate.epoch.env.logic": 0.5745721271393643,
      "success_rate.epoch.env.math": 0.9659318637274549,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9473002159827214,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.645972704435599,
      "success_rate.epoch.global": 0.8427935447968837,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99075,
      "tokens_p.mean_below_band": 3.4051481634378433e-09,
      "tokens_rate.above_band": 0.9920634920634921,
      "tokens_rate.below_band": 0.007936507936507936,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.3472406914893618,
      "grad_norm": 87.18761372198222,
      "learning_rate": 1.699892338935563e-07,
      "loss": 0.1673,
      "step": 8105,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058823529411764,
      "success_rate.epoch.env.logic": 0.5766423357664233,
      "success_rate.epoch.env.math": 0.9659318637274549,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9473911168607159,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6461691689360584,
      "success_rate.epoch.global": 0.8430555555555556,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9876143292682927,
      "tokens_p.mean_in_band": 0.7359227594339622,
      "tokens_rate.above_band": 0.8608923884514436,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13910761154855644
    },
    {
      "epoch": 1.3480718085106382,
      "grad_norm": 134.4144077412549,
      "learning_rate": 1.699661766996821e-07,
      "loss": 0.3375,
      "step": 8110,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058823529411764,
      "success_rate.epoch.env.logic": 0.5766423357664233,
      "success_rate.epoch.env.math": 0.9659318637274549,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9475494411006019,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6461835620487753,
      "success_rate.epoch.global": 0.8433601330745772,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.0003379783693844,
      "tokens_p.mean_in_band": 0.6365740740740741,
      "tokens_rate.above_band": 0.9780309194467046,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021969080553295363
    },
    {
      "epoch": 1.348902925531915,
      "grad_norm": 223.12720514740883,
      "learning_rate": 1.6994313731338607e-07,
      "loss": 0.4122,
      "step": 8115,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058823529411764,
      "success_rate.epoch.env.logic": 0.5748792270531401,
      "success_rate.epoch.env.math": 0.966,
      "success_rate.epoch.env.sat": 0.08333333333333333,
      "success_rate.epoch.env.science": 0.9476619476619477,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.646039701514285,
      "success_rate.epoch.global": 0.8431969026548672,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.996791074249605,
      "tokens_p.mean_in_band": 0.4778645833333333,
      "tokens_rate.above_band": 0.965675057208238,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034324942791762014
    },
    {
      "epoch": 1.3497340425531914,
      "grad_norm": 44.49840690034461,
      "learning_rate": 1.6992011577555752e-07,
      "loss": 0.3307,
      "step": 8120,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5748792270531401,
      "success_rate.epoch.env.math": 0.9660678642714571,
      "success_rate.epoch.env.sat": 0.08280254777070063,
      "success_rate.epoch.env.science": 0.9477739726027398,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6454730424877796,
      "success_rate.epoch.global": 0.8429911699779249,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.985316265060241,
      "tokens_p.mean_in_band": 0.76171875,
      "tokens_rate.above_band": 0.8767605633802817,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12323943661971831
    },
    {
      "epoch": 1.350565159574468,
      "grad_norm": 47.988907313821656,
      "learning_rate": 1.6989711212705395e-07,
      "loss": 0.317,
      "step": 8125,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.44680851063829785,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5734939759036145,
      "success_rate.epoch.env.math": 0.9662698412698413,
      "success_rate.epoch.env.sat": 0.08227848101265822,
      "success_rate.epoch.env.science": 0.9478409576742197,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6453239192298065,
      "success_rate.epoch.global": 0.8427863436123348,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947558459422283,
      "tokens_p.mean_in_band": 0.6508413461538461,
      "tokens_rate.above_band": 0.9654714475431607,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034528552456839307
    },
    {
      "epoch": 1.3513962765957448,
      "grad_norm": 133.8318294727147,
      "learning_rate": 1.6987412640870132e-07,
      "loss": 0.3788,
      "step": 8130,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4421052631578947,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5721153846153846,
      "success_rate.epoch.env.math": 0.9664031620553359,
      "success_rate.epoch.env.sat": 0.08227848101265822,
      "success_rate.epoch.env.science": 0.9479522184300341,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6447932594818679,
      "success_rate.epoch.global": 0.842625652293326,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9972993827160493,
      "tokens_p.mean_in_band": 0.3767903645833333,
      "tokens_rate.above_band": 0.9908256880733946,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009174311926605505
    },
    {
      "epoch": 1.3522273936170213,
      "grad_norm": 118.77883537195326,
      "learning_rate": 1.6985115866129357e-07,
      "loss": 0.1919,
      "step": 8135,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4421052631578947,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5721153846153846,
      "success_rate.epoch.env.math": 0.9664694280078896,
      "success_rate.epoch.env.sat": 0.08176100628930817,
      "success_rate.epoch.env.science": 0.948018747337026,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6447582885851584,
      "success_rate.epoch.global": 0.8425671969281404,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9917953667953668,
      "tokens_p.mean_in_band": 0.7801724137931034,
      "tokens_rate.above_band": 0.8993055555555556,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10069444444444445
    },
    {
      "epoch": 1.3530585106382977,
      "grad_norm": 348.231295807114,
      "learning_rate": 1.698282089255928e-07,
      "loss": 0.2543,
      "step": 8140,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4421052631578947,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5721153846153846,
      "success_rate.epoch.env.math": 0.9666011787819253,
      "success_rate.epoch.env.sat": 0.08176100628930817,
      "success_rate.epoch.env.science": 0.9481292517006803,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6447803117794939,
      "success_rate.epoch.global": 0.8428688748973446,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9898200757575758,
      "tokens_p.mean_in_band": 0.75341796875,
      "tokens_rate.above_band": 0.9924812030075187,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007518796992481203
    },
    {
      "epoch": 1.3538896276595744,
      "grad_norm": 0.0,
      "learning_rate": 1.6980527724232927e-07,
      "loss": 0.2454,
      "step": 8145,
      "success_rate.epoch.env.abd": 0.5263157894736842,
      "success_rate.epoch.env.agentgym:alfworld": 0.4421052631578947,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5707434052757794,
      "success_rate.epoch.env.math": 0.9666666666666667,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.9473907509546033,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6445479482803803,
      "success_rate.epoch.global": 0.8421196394427752,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9978362183754993,
      "tokens_p.mean_in_band": 0.6311910377358491,
      "tokens_rate.above_band": 0.9340796019900498,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06592039800995025
    },
    {
      "epoch": 1.3547207446808511,
      "grad_norm": 10.303336966261215,
      "learning_rate": 1.6978236365220102e-07,
      "loss": 0.3853,
      "step": 8150,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4479166666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5717703349282297,
      "success_rate.epoch.env.math": 0.9666666666666667,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.947011445527766,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6427427881222623,
      "success_rate.epoch.global": 0.8417894162575014,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.43333333333333335,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9938186813186813,
      "tokens_p.mean_below_band": 4.6293280320242047e-10,
      "tokens_p.mean_in_band": 0.6172930743243243,
      "tokens_rate.above_band": 0.9210526315789473,
      "tokens_rate.below_band": 0.004048582995951417,
      "tokens_rate.in_band": 0.07489878542510121
    },
    {
      "epoch": 1.3555518617021276,
      "grad_norm": 77.38340136478867,
      "learning_rate": 1.6975946819587407e-07,
      "loss": 0.3095,
      "step": 8155,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4479166666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4942528735632184,
      "success_rate.epoch.env.logic": 0.5717703349282297,
      "success_rate.epoch.env.math": 0.9667318982387475,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.9470787468247248,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6422323705251948,
      "success_rate.epoch.global": 0.8417324979569599,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9848977695167286,
      "tokens_p.mean_in_band": 0.81234375,
      "tokens_rate.above_band": 0.9149659863945578,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08503401360544217
    },
    {
      "epoch": 1.3563829787234043,
      "grad_norm": 26.713054797983926,
      "learning_rate": 1.6973659091398227e-07,
      "loss": 0.2446,
      "step": 8160,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4479166666666667,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5717703349282297,
      "success_rate.epoch.env.math": 0.9667318982387475,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.9472351203039258,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.641735994484499,
      "success_rate.epoch.global": 0.8418048382712694,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9961436909394108,
      "tokens_p.mean_below_band": 1.3597309589385986e-07,
      "tokens_p.mean_in_band": 0.5226629849137931,
      "tokens_rate.above_band": 0.9115784139853053,
      "tokens_rate.below_band": 0.0002533569799847986,
      "tokens_rate.in_band": 0.0881682290347099
    },
    {
      "epoch": 1.3572140957446808,
      "grad_norm": 44.70321260397381,
      "learning_rate": 1.6971373184712716e-07,
      "loss": 0.2363,
      "step": 8165,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.4536082474226804,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5727923627684964,
      "success_rate.epoch.env.math": 0.9668615984405458,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.9473240623683101,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6423661991083592,
      "success_rate.epoch.global": 0.8421480878763222,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9956113801452785,
      "tokens_p.mean_in_band": 0.70068359375,
      "tokens_rate.above_band": 0.9627039627039627,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037296037296037296
    },
    {
      "epoch": 1.3580452127659575,
      "grad_norm": 64.2790938183128,
      "learning_rate": 1.6969089103587802e-07,
      "loss": 0.2348,
      "step": 8170,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.45918367346938777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5727923627684964,
      "success_rate.epoch.env.math": 0.9668615984405458,
      "success_rate.epoch.env.sat": 0.08125,
      "success_rate.epoch.env.science": 0.9470142977291842,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6428448955999575,
      "success_rate.epoch.global": 0.8421337665854319,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9958920187793427,
      "tokens_p.mean_in_band": 0.6438802083333334,
      "tokens_rate.above_band": 0.9659863945578231,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034013605442176874
    },
    {
      "epoch": 1.358876329787234,
      "grad_norm": 55.08817867861605,
      "learning_rate": 1.6966806852077167e-07,
      "loss": 0.2433,
      "step": 8175,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.45918367346938777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5738095238095238,
      "success_rate.epoch.env.math": 0.9669260700389105,
      "success_rate.epoch.env.sat": 0.08074534161490683,
      "success_rate.epoch.env.science": 0.947103274559194,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.642905436607622,
      "success_rate.epoch.global": 0.8421621621621621,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9941479400749064,
      "tokens_p.mean_in_band": 0.5859375,
      "tokens_rate.above_band": 0.9434628975265018,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05653710247349823
    },
    {
      "epoch": 1.3597074468085106,
      "grad_norm": 71.34830114272714,
      "learning_rate": 1.6964526434231247e-07,
      "loss": 0.3126,
      "step": 8180,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.45918367346938777,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5758293838862559,
      "success_rate.epoch.env.math": 0.9669902912621359,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9467728415758592,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6430195475423459,
      "success_rate.epoch.global": 0.8419633225458468,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9924045138888888,
      "tokens_p.mean_in_band": 0.6516544117647058,
      "tokens_rate.above_band": 0.9442622950819672,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05573770491803279
    },
    {
      "epoch": 1.3605385638297873,
      "grad_norm": 208.77030032587822,
      "learning_rate": 1.6962247854097228e-07,
      "loss": 0.3752,
      "step": 8185,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5731132075471698,
      "success_rate.epoch.env.math": 0.9670542635658915,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9468619246861925,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6432831539288986,
      "success_rate.epoch.global": 0.8417653390742734,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976071975497703,
      "tokens_p.mean_in_band": 0.5317708333333333,
      "tokens_rate.above_band": 0.9666913397483345,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033308660251665435
    },
    {
      "epoch": 1.3613696808510638,
      "grad_norm": 27.360320610012824,
      "learning_rate": 1.695997111571903e-07,
      "loss": 0.3352,
      "step": 8190,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5727699530516432,
      "success_rate.epoch.env.math": 0.9671179883945842,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9469063545150501,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6432617812163554,
      "success_rate.epoch.global": 0.8417092179521634,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9971072931276297,
      "tokens_p.mean_in_band": 0.48214285714285715,
      "tokens_rate.above_band": 0.9807427785419532,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01925722145804677
    },
    {
      "epoch": 1.3622007978723405,
      "grad_norm": 0.0,
      "learning_rate": 1.6957696223137306e-07,
      "loss": 0.2413,
      "step": 8195,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5727699530516432,
      "success_rate.epoch.env.math": 0.9671814671814671,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9470391993327774,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6432796288167745,
      "success_rate.epoch.global": 0.8420064377682404,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9849806201550387,
      "tokens_p.mean_in_band": 0.8196614583333334,
      "tokens_rate.above_band": 0.9555555555555556,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044444444444444446
    },
    {
      "epoch": 1.363031914893617,
      "grad_norm": 52.32346758828354,
      "learning_rate": 1.6955423180389433e-07,
      "loss": 0.3667,
      "step": 8200,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5710955710955711,
      "success_rate.epoch.env.math": 0.9672447013487476,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9471273938384679,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6431411785183107,
      "success_rate.epoch.global": 0.8418094218415417,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9966820987654321,
      "tokens_p.mean_in_band": 0.5223214285714286,
      "tokens_rate.above_band": 0.9774738535800482,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02252614641995173
    },
    {
      "epoch": 1.3638630319148937,
      "grad_norm": 61.841807043450736,
      "learning_rate": 1.6953151991509505e-07,
      "loss": 0.2597,
      "step": 8205,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5710955710955711,
      "success_rate.epoch.env.math": 0.9673076923076923,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9472591362126246,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6431588815485926,
      "success_rate.epoch.global": 0.8421052631578947,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9967603668261563,
      "tokens_p.mean_in_band": 0.5926339285714286,
      "tokens_rate.above_band": 0.9889589905362776,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011041009463722398
    },
    {
      "epoch": 1.3646941489361701,
      "grad_norm": 43.16026661712374,
      "learning_rate": 1.6950882660528325e-07,
      "loss": 0.4053,
      "step": 8210,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48863636363636365,
      "success_rate.epoch.env.logic": 0.5720930232558139,
      "success_rate.epoch.env.math": 0.9673076923076923,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9469759734879868,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6432238169518295,
      "success_rate.epoch.global": 0.8421333333333333,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.7777777777777778,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9933035714285714,
      "tokens_p.mean_below_band": 7.566995918750763e-10,
      "tokens_p.mean_in_band": 0.584375,
      "tokens_rate.above_band": 0.9680851063829787,
      "tokens_rate.below_band": 0.005319148936170213,
      "tokens_rate.in_band": 0.026595744680851064
    },
    {
      "epoch": 1.3655252659574468,
      "grad_norm": 195.18112815856313,
      "learning_rate": 1.6948615191473402e-07,
      "loss": 0.2825,
      "step": 8215,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48314606741573035,
      "success_rate.epoch.env.logic": 0.5720930232558139,
      "success_rate.epoch.env.math": 0.9674329501915708,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9470417873396773,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.642742069271369,
      "success_rate.epoch.global": 0.8421192758253461,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9914638269100744,
      "tokens_p.mean_below_band": 6.845220923423767e-08,
      "tokens_p.mean_in_band": 0.6799232219827587,
      "tokens_rate.above_band": 0.8639018691588785,
      "tokens_rate.below_band": 0.0005841121495327102,
      "tokens_rate.in_band": 0.13551401869158877
    },
    {
      "epoch": 1.3663563829787235,
      "grad_norm": 61.03500435577016,
      "learning_rate": 1.6946349588368937e-07,
      "loss": 0.2848,
      "step": 8220,
      "success_rate.epoch.env.abd": 0.5,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48314606741573035,
      "success_rate.epoch.env.logic": 0.5707656612529002,
      "success_rate.epoch.env.math": 0.9674329501915708,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9471947194719472,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6426353029194923,
      "success_rate.epoch.global": 0.8421891604675876,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0004284490145672,
      "tokens_p.mean_in_band": 0.4954769736842105,
      "tokens_rate.above_band": 0.9684647302904564,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03153526970954357
    },
    {
      "epoch": 1.3671875,
      "grad_norm": 101.80055787478545,
      "learning_rate": 1.6944085855235816e-07,
      "loss": 0.2511,
      "step": 8225,
      "success_rate.epoch.env.abd": 0.5238095238095238,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48314606741573035,
      "success_rate.epoch.env.logic": 0.5704387990762124,
      "success_rate.epoch.env.math": 0.9674952198852772,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9472817133443163,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.644783659755757,
      "success_rate.epoch.global": 0.8422587486744433,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992133867276888,
      "tokens_p.mean_in_band": 0.56640625,
      "tokens_rate.above_band": 0.9820224719101124,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017977528089887642
    },
    {
      "epoch": 1.3680186170212765,
      "grad_norm": 98.99828634082701,
      "learning_rate": 1.694182399609162e-07,
      "loss": 0.3233,
      "step": 8230,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48314606741573035,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9674952198852772,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.947000821692687,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.64681583269628,
      "success_rate.epoch.global": 0.8423280423280424,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9917346014492754,
      "tokens_p.mean_in_band": 0.62890625,
      "tokens_rate.above_band": 0.9616724738675958,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03832752613240418
    },
    {
      "epoch": 1.3688497340425532,
      "grad_norm": 83.78584689142346,
      "learning_rate": 1.6939564014950588e-07,
      "loss": 0.2912,
      "step": 8235,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48314606741573035,
      "success_rate.epoch.env.logic": 0.5711009174311926,
      "success_rate.epoch.env.math": 0.9676190476190476,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9470877768662839,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6468052080517332,
      "success_rate.epoch.global": 0.8423970432946146,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9884969325153374,
      "tokens_p.mean_in_band": 0.7466145833333333,
      "tokens_rate.above_band": 0.9560117302052786,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04398826979472141
    },
    {
      "epoch": 1.3696808510638299,
      "grad_norm": 124.54686648700506,
      "learning_rate": 1.6937305915823634e-07,
      "loss": 0.2057,
      "step": 8240,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5711009174311926,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.08024691358024691,
      "success_rate.epoch.env.science": 0.9471744471744472,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6473463334741102,
      "success_rate.epoch.global": 0.8426877470355731,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951923076923077,
      "tokens_p.mean_in_band": 0.52734375,
      "tokens_rate.above_band": 0.9933554817275747,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006644518272425249
    },
    {
      "epoch": 1.3705119680851063,
      "grad_norm": 43.62444350218963,
      "learning_rate": 1.693504970271833e-07,
      "loss": 0.2965,
      "step": 8245,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46464646464646464,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5707762557077626,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.07926829268292683,
      "success_rate.epoch.env.science": 0.947260834014718,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6472357065849756,
      "success_rate.epoch.global": 0.8422298185642914,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9977490996398559,
      "tokens_p.mean_in_band": 0.6370849609375,
      "tokens_rate.above_band": 0.9286510590858417,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0713489409141583
    },
    {
      "epoch": 1.371343085106383,
      "grad_norm": 51.00846567410458,
      "learning_rate": 1.6932795379638901e-07,
      "loss": 0.5359,
      "step": 8250,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5555555555555556,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5694760820045558,
      "success_rate.epoch.env.math": 0.967741935483871,
      "success_rate.epoch.env.sat": 0.07878787878787878,
      "success_rate.epoch.env.science": 0.9473684210526315,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6466612097479932,
      "success_rate.epoch.global": 0.8417738126475991,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9987186788154897,
      "tokens_p.mean_in_band": 0.5801205842391305,
      "tokens_rate.above_band": 0.9502164502164502,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049783549783549784
    },
    {
      "epoch": 1.3721742021276595,
      "grad_norm": 80.15349101983222,
      "learning_rate": 1.6930542950586225e-07,
      "loss": 0.2597,
      "step": 8255,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5704545454545454,
      "success_rate.epoch.env.math": 0.9678030303030303,
      "success_rate.epoch.env.sat": 0.07878787878787878,
      "success_rate.epoch.env.science": 0.9474969474969475,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6417168942168942,
      "success_rate.epoch.global": 0.8418848167539267,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983513189448441,
      "tokens_p.mean_in_band": 0.6172902960526315,
      "tokens_rate.above_band": 0.9705197827773467,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02948021722265322
    },
    {
      "epoch": 1.3730053191489362,
      "grad_norm": 70.0812423905079,
      "learning_rate": 1.6928292419557804e-07,
      "loss": 0.2137,
      "step": 8260,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.45544554455445546,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5704545454545454,
      "success_rate.epoch.env.math": 0.9678638941398866,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9476248477466505,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6418245105124147,
      "success_rate.epoch.global": 0.8419952990336903,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951121794871794,
      "tokens_p.mean_in_band": 0.7487980769230769,
      "tokens_rate.above_band": 0.967741935483871,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03225806451612903
    },
    {
      "epoch": 1.3738364361702127,
      "grad_norm": 157.4674575578166,
      "learning_rate": 1.6926043790547782e-07,
      "loss": 0.263,
      "step": 8265,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.45544554455445546,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5704545454545454,
      "success_rate.epoch.env.math": 0.9679245283018868,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9477309562398704,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6418396689356165,
      "success_rate.epoch.global": 0.8422425032594524,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9986861861861862,
      "tokens_p.mean_in_band": 0.75390625,
      "tokens_rate.above_band": 0.9940298507462687,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005970149253731343
    },
    {
      "epoch": 1.3746675531914894,
      "grad_norm": 127.5671503534398,
      "learning_rate": 1.6923797067546922e-07,
      "loss": 0.3876,
      "step": 8270,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.45544554455445546,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9680451127819549,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9478155339805825,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6419468678624173,
      "success_rate.epoch.global": 0.8425299323269131,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972345132743363,
      "tokens_p.mean_in_band": 0.5993303571428571,
      "tokens_rate.above_band": 0.9797687861271677,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02023121387283237
    },
    {
      "epoch": 1.375498670212766,
      "grad_norm": 108.84975969558603,
      "learning_rate": 1.6921552254542613e-07,
      "loss": 0.1988,
      "step": 8275,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.45544554455445546,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9680451127819549,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9479628882613957,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6419602637061275,
      "success_rate.epoch.global": 0.8428163159262146,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9851371951219512,
      "tokens_p.mean_in_band": 0.8268229166666666,
      "tokens_rate.above_band": 0.9647058823529412,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03529411764705882
    },
    {
      "epoch": 1.3763297872340425,
      "grad_norm": 159.07076061506493,
      "learning_rate": 1.6919309355518843e-07,
      "loss": 0.2876,
      "step": 8280,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.46078431372549017,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9680451127819549,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9481094127111827,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6424589267625659,
      "success_rate.epoch.global": 0.8431423386051335,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9957256838905775,
      "tokens_p.mean_in_band": 0.63671875,
      "tokens_rate.above_band": 0.9909638554216867,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009036144578313253
    },
    {
      "epoch": 1.3771609042553192,
      "grad_norm": 48.778187610501774,
      "learning_rate": 1.691706837445621e-07,
      "loss": 0.3073,
      "step": 8285,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563106796116505,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5723981900452488,
      "success_rate.epoch.env.math": 0.9680451127819549,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9482135688478522,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6421498486388846,
      "success_rate.epoch.global": 0.843167701863354,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9956395348837209,
      "tokens_p.mean_in_band": 0.746484375,
      "tokens_rate.above_band": 0.9748110831234257,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02518891687657431
    },
    {
      "epoch": 1.3779920212765957,
      "grad_norm": 69.05478907883565,
      "learning_rate": 1.6914829315331906e-07,
      "loss": 0.1656,
      "step": 8290,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563106796116505,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5733634311512416,
      "success_rate.epoch.env.math": 0.9682242990654205,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9483173076923077,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6422633182965132,
      "success_rate.epoch.global": 0.8435321456235476,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917127071823204,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.9945054945054945,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005494505494505495
    },
    {
      "epoch": 1.3788231382978724,
      "grad_norm": 74.68886340671088,
      "learning_rate": 1.6912592182119713e-07,
      "loss": 0.333,
      "step": 8295,
      "success_rate.epoch.env.abd": 0.5652173913043478,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563106796116505,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5733634311512416,
      "success_rate.epoch.env.math": 0.9682835820895522,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9483793517406963,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6440709703803607,
      "success_rate.epoch.global": 0.8437338834450748,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986064659977704,
      "tokens_p.mean_in_band": 0.6478074596774194,
      "tokens_rate.above_band": 0.9665948275862069,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0334051724137931
    },
    {
      "epoch": 1.3796542553191489,
      "grad_norm": 120.32190112944522,
      "learning_rate": 1.6910356978789994e-07,
      "loss": 0.3921,
      "step": 8300,
      "success_rate.epoch.env.abd": 0.5652173913043478,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563106796116505,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5752808988764045,
      "success_rate.epoch.env.math": 0.9683426443202979,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9484412470023981,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6442562817637798,
      "success_rate.epoch.global": 0.8439752832131823,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960416666666667,
      "tokens_p.mean_in_band": 0.6607572115384616,
      "tokens_rate.above_band": 0.9877704609595485,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012229539040451553
    },
    {
      "epoch": 1.3804853723404256,
      "grad_norm": 65.6684037208593,
      "learning_rate": 1.6908123709309683e-07,
      "loss": 0.372,
      "step": 8305,
      "success_rate.epoch.env.abd": 0.5652173913043478,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563106796116505,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5762331838565022,
      "success_rate.epoch.env.math": 0.9685185185185186,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9477045908183632,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6442918729450784,
      "success_rate.epoch.global": 0.8437419686455924,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9908494475138122,
      "tokens_p.mean_below_band": 5.115907697472721e-12,
      "tokens_p.mean_in_band": 0.4409950657894737,
      "tokens_rate.above_band": 0.900497512437811,
      "tokens_rate.below_band": 0.004975124378109453,
      "tokens_rate.in_band": 0.0945273631840796
    },
    {
      "epoch": 1.3813164893617023,
      "grad_norm": 114.16992487162783,
      "learning_rate": 1.6905892377642295e-07,
      "loss": 0.4041,
      "step": 8310,
      "success_rate.epoch.env.abd": 0.5652173913043478,
      "success_rate.epoch.env.agentgym:alfworld": 0.4519230769230769,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5762331838565022,
      "success_rate.epoch.env.math": 0.9686346863468634,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9477671451355661,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.643909247441167,
      "success_rate.epoch.global": 0.8437259430331023,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981730769230769,
      "tokens_p.mean_in_band": 0.6603618421052632,
      "tokens_rate.above_band": 0.9715994020926756,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028400597907324365
    },
    {
      "epoch": 1.3821476063829787,
      "grad_norm": 153.63807539239286,
      "learning_rate": 1.6903662987747892e-07,
      "loss": 0.174,
      "step": 8315,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44761904761904764,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5762331838565022,
      "success_rate.epoch.env.math": 0.96875,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9478503184713376,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6451829201424273,
      "success_rate.epoch.global": 0.8437900128040973,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9918382352941176,
      "tokens_p.mean_in_band": 0.8151041666666666,
      "tokens_rate.above_band": 0.9860788863109049,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013921113689095127
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 42.72788035331363,
      "learning_rate": 1.6901435543583093e-07,
      "loss": 0.1334,
      "step": 8320,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44761904761904764,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4888888888888889,
      "success_rate.epoch.env.logic": 0.5746102449888641,
      "success_rate.epoch.env.math": 0.9688644688644689,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9479332273449921,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6409210922711491,
      "success_rate.epoch.global": 0.8434227330779055,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975706713780919,
      "tokens_p.mean_in_band": 0.5389344262295082,
      "tokens_rate.above_band": 0.9586720867208672,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041327913279132794
    },
    {
      "epoch": 1.383809840425532,
      "grad_norm": 100.76000031026607,
      "learning_rate": 1.6899210049101068e-07,
      "loss": 0.4322,
      "step": 8325,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44761904761904764,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4835164835164835,
      "success_rate.epoch.env.logic": 0.5746102449888641,
      "success_rate.epoch.env.math": 0.968978102189781,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9480570975416336,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6404542830120171,
      "success_rate.epoch.global": 0.8435270132517839,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9869981751824818,
      "tokens_p.mean_in_band": 0.20414624183006536,
      "tokens_rate.above_band": 0.4724137931034483,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.5275862068965518
    },
    {
      "epoch": 1.3846409574468086,
      "grad_norm": 50.39568366541492,
      "learning_rate": 1.6896986508251527e-07,
      "loss": 0.3325,
      "step": 8330,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4835164835164835,
      "success_rate.epoch.env.logic": 0.5746102449888641,
      "success_rate.epoch.env.math": 0.968978102189781,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9482008699090549,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6400834603905142,
      "success_rate.epoch.global": 0.8435910478128179,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930555555555556,
      "tokens_p.mean_in_band": 0.71875,
      "tokens_rate.above_band": 0.9924812030075187,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007518796992481203
    },
    {
      "epoch": 1.385472074468085,
      "grad_norm": 77.04914310728238,
      "learning_rate": 1.689476492498071e-07,
      "loss": 0.4162,
      "step": 8335,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4782608695652174,
      "success_rate.epoch.env.logic": 0.5733333333333334,
      "success_rate.epoch.env.math": 0.968978102189781,
      "success_rate.epoch.env.sat": 0.08433734939759036,
      "success_rate.epoch.env.science": 0.9482826687722069,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6394970306865465,
      "success_rate.epoch.global": 0.8433214829862875,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971677623855365,
      "tokens_p.mean_in_band": 0.5416254940711462,
      "tokens_rate.above_band": 0.943927304964539,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056072695035460994
    },
    {
      "epoch": 1.3863031914893618,
      "grad_norm": 97.20778958939513,
      "learning_rate": 1.6892545303231377e-07,
      "loss": 0.2281,
      "step": 8340,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4782608695652174,
      "success_rate.epoch.env.logic": 0.5752212389380531,
      "success_rate.epoch.env.math": 0.9690346083788707,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9483845547675335,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6401815132022721,
      "success_rate.epoch.global": 0.8436787433493793,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9935405027932961,
      "tokens_p.mean_in_band": 0.8046875,
      "tokens_rate.above_band": 0.9808219178082191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019178082191780823
    },
    {
      "epoch": 1.3871343085106382,
      "grad_norm": 61.70549035738112,
      "learning_rate": 1.6890327646942816e-07,
      "loss": 0.3042,
      "step": 8345,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4782608695652174,
      "success_rate.epoch.env.logic": 0.5748898678414097,
      "success_rate.epoch.env.math": 0.9690346083788707,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9485062893081762,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6401624553335448,
      "success_rate.epoch.global": 0.8437420986093552,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951923076923077,
      "tokens_p.mean_in_band": 0.5275493421052632,
      "tokens_rate.above_band": 0.9766009852216748,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023399014778325122
    },
    {
      "epoch": 1.387965425531915,
      "grad_norm": 100.48262737084313,
      "learning_rate": 1.6888111960050827e-07,
      "loss": 0.3931,
      "step": 8350,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4782608695652174,
      "success_rate.epoch.env.logic": 0.5758241758241758,
      "success_rate.epoch.env.math": 0.9690909090909091,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9485871271585558,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6402598595649253,
      "success_rate.epoch.global": 0.8439787932340318,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9903381642512077,
      "tokens_p.mean_in_band": 0.708984375,
      "tokens_rate.above_band": 0.9627906976744186,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.037209302325581395
    },
    {
      "epoch": 1.3887965425531914,
      "grad_norm": 199.91981455687412,
      "learning_rate": 1.6885898246487707e-07,
      "loss": 0.3211,
      "step": 8355,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4782608695652174,
      "success_rate.epoch.env.logic": 0.5767543859649122,
      "success_rate.epoch.env.math": 0.969147005444646,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9487079091620987,
      "success_rate.epoch.env.webshop": 1.0,
      "success_rate.epoch.env_macro_mean": 0.6403605039738358,
      "success_rate.epoch.global": 0.8442932728647015,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9914647577092511,
      "tokens_p.mean_in_band": 0.8815104166666666,
      "tokens_rate.above_band": 0.9869565217391304,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013043478260869565
    },
    {
      "epoch": 1.389627659574468,
      "grad_norm": 298.52706127773706,
      "learning_rate": 1.6883686510182255e-07,
      "loss": 0.2553,
      "step": 8360,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4782608695652174,
      "success_rate.epoch.env.logic": 0.5776805251641138,
      "success_rate.epoch.env.math": 0.9692028985507246,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9487881157154027,
      "success_rate.epoch.env.webshop": 0.6666666666666666,
      "success_rate.epoch.env_macro_mean": 0.6101540408397678,
      "success_rate.epoch.global": 0.8443158953722334,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9892761394101877,
      "tokens_p.mean_in_band": 0.4809229651162791,
      "tokens_rate.above_band": 0.6844036697247706,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.3155963302752294
    },
    {
      "epoch": 1.3904587765957448,
      "grad_norm": 48.18066271543616,
      "learning_rate": 1.6881476755059767e-07,
      "loss": 0.3036,
      "step": 8365,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.5764192139737991,
      "success_rate.epoch.env.math": 0.9692028985507246,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9488481062085123,
      "success_rate.epoch.env.webshop": 0.6666666666666666,
      "success_rate.epoch.env_macro_mean": 0.6100868784754856,
      "success_rate.epoch.global": 0.8440482169763938,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952848344880677,
      "tokens_p.mean_in_band": 0.7495349702380952,
      "tokens_rate.above_band": 0.9840909090909091,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015909090909090907
    },
    {
      "epoch": 1.3912898936170213,
      "grad_norm": 57.08815032106201,
      "learning_rate": 1.687926898504201e-07,
      "loss": 0.2079,
      "step": 8370,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.5760869565217391,
      "success_rate.epoch.env.math": 0.9692028985507246,
      "success_rate.epoch.env.sat": 0.08982035928143713,
      "success_rate.epoch.env.science": 0.9489676665368134,
      "success_rate.epoch.env.webshop": 0.6666666666666666,
      "success_rate.epoch.env_macro_mean": 0.6100675423733257,
      "success_rate.epoch.global": 0.844110275689223,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951862373737373,
      "tokens_p.mean_in_band": 0.6171875,
      "tokens_rate.above_band": 0.9826302729528535,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017369727047146403
    },
    {
      "epoch": 1.3921210106382977,
      "grad_norm": 77.09650797301903,
      "learning_rate": 1.6877063204047238e-07,
      "loss": 0.3386,
      "step": 8375,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.5760869565217391,
      "success_rate.epoch.env.math": 0.9692028985507246,
      "success_rate.epoch.env.sat": 0.08928571428571429,
      "success_rate.epoch.env.science": 0.9490668740279938,
      "success_rate.epoch.env.webshop": 0.6666666666666666,
      "success_rate.epoch.env_macro_mean": 0.6100279571456401,
      "success_rate.epoch.global": 0.8440940940940941,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9902895480225988,
      "tokens_p.mean_in_band": 0.6481370192307693,
      "tokens_rate.above_band": 0.8719211822660099,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12807881773399016
    },
    {
      "epoch": 1.3929521276595744,
      "grad_norm": 110.09370402287995,
      "learning_rate": 1.6874859415990175e-07,
      "loss": 0.5582,
      "step": 8380,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.5770065075921909,
      "success_rate.epoch.env.math": 0.969258589511754,
      "success_rate.epoch.env.sat": 0.08875739644970414,
      "success_rate.epoch.env.science": 0.9491656965463717,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5949260553317475,
      "success_rate.epoch.global": 0.8439450686641697,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950358072916666,
      "tokens_p.mean_in_band": 0.646484375,
      "tokens_rate.above_band": 0.8135593220338984,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1864406779661017
    },
    {
      "epoch": 1.3937832446808511,
      "grad_norm": 154.69772930804822,
      "learning_rate": 1.6872657624781997e-07,
      "loss": 0.4721,
      "step": 8385,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.5770065075921909,
      "success_rate.epoch.env.math": 0.969258589511754,
      "success_rate.epoch.env.sat": 0.08823529411764706,
      "success_rate.epoch.env.science": 0.9492641363284275,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5948875405544747,
      "success_rate.epoch.global": 0.843929194714535,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9989436619718309,
      "tokens_p.mean_in_band": 0.6216856060606061,
      "tokens_rate.above_band": 0.955585464333782,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04441453566621804
    },
    {
      "epoch": 1.3946143617021276,
      "grad_norm": 91.78758005607338,
      "learning_rate": 1.6870457834330354e-07,
      "loss": 0.323,
      "step": 8390,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.577922077922078,
      "success_rate.epoch.env.math": 0.969258589511754,
      "success_rate.epoch.env.sat": 0.08823529411764706,
      "success_rate.epoch.env.science": 0.9493817619783617,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5949814674617312,
      "success_rate.epoch.global": 0.8442010950721752,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9880998452012384,
      "tokens_p.mean_in_band": 0.7905649038461539,
      "tokens_rate.above_band": 0.9613095238095238,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03869047619047619
    },
    {
      "epoch": 1.3954454787234043,
      "grad_norm": 51.38050078813915,
      "learning_rate": 1.6868260048539327e-07,
      "loss": 0.3091,
      "step": 8395,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.577922077922078,
      "success_rate.epoch.env.math": 0.969258589511754,
      "success_rate.epoch.env.sat": 0.08823529411764706,
      "success_rate.epoch.env.science": 0.9494988434849653,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5949921112350588,
      "success_rate.epoch.global": 0.8444333996023857,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9886924342105263,
      "tokens_p.mean_in_band": 0.7584635416666666,
      "tokens_rate.above_band": 0.9620253164556962,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0379746835443038
    },
    {
      "epoch": 1.3962765957446808,
      "grad_norm": 131.16956759583073,
      "learning_rate": 1.686606427130945e-07,
      "loss": 0.2383,
      "step": 8400,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4787234042553192,
      "success_rate.epoch.env.logic": 0.5788336933045356,
      "success_rate.epoch.env.math": 0.9693693693693693,
      "success_rate.epoch.env.sat": 0.0872093023255814,
      "success_rate.epoch.env.science": 0.9495571813631113,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5949970877192544,
      "success_rate.epoch.global": 0.8442460317460317,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9978210034013606,
      "tokens_p.mean_in_band": 0.6898311491935484,
      "tokens_rate.above_band": 0.9499192245557351,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050080775444264945
    },
    {
      "epoch": 1.3971077127659575,
      "grad_norm": 20.40932897875633,
      "learning_rate": 1.686387050653769e-07,
      "loss": 0.2054,
      "step": 8405,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47368421052631576,
      "success_rate.epoch.env.logic": 0.575107296137339,
      "success_rate.epoch.env.math": 0.9694244604316546,
      "success_rate.epoch.env.sat": 0.0872093023255814,
      "success_rate.epoch.env.science": 0.9496153846153846,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5942105153027417,
      "success_rate.epoch.global": 0.8435643564356435,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9946627850557982,
      "tokens_p.mean_in_band": 0.6571691176470589,
      "tokens_rate.above_band": 0.9758522727272727,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.024147727272727272
    },
    {
      "epoch": 1.397938829787234,
      "grad_norm": 65.5731791262289,
      "learning_rate": 1.686167875811744e-07,
      "loss": 0.3979,
      "step": 8410,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.575107296137339,
      "success_rate.epoch.env.math": 0.9694793536804309,
      "success_rate.epoch.env.sat": 0.0872093023255814,
      "success_rate.epoch.env.science": 0.9497120921305182,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5937757325970684,
      "success_rate.epoch.global": 0.843587842846553,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9869473189087489,
      "tokens_p.mean_in_band": 0.5395791997354498,
      "tokens_rate.above_band": 0.7376821651630812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2623178348369188
    },
    {
      "epoch": 1.3987699468085106,
      "grad_norm": 46.34687494719824,
      "learning_rate": 1.685948902993852e-07,
      "loss": 0.3938,
      "step": 8415,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.5738758029978587,
      "success_rate.epoch.env.math": 0.9695340501792115,
      "success_rate.epoch.env.sat": 0.08670520231213873,
      "success_rate.epoch.env.science": 0.9497506712696586,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5936264310047954,
      "success_rate.epoch.global": 0.8432872655478776,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9919225481209899,
      "tokens_p.mean_in_band": 0.760670731707317,
      "tokens_rate.above_band": 0.9637809187279152,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.036219081272084806
    },
    {
      "epoch": 1.3996010638297873,
      "grad_norm": 41.00890655977667,
      "learning_rate": 1.685730132588716e-07,
      "loss": 0.2116,
      "step": 8420,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.5765957446808511,
      "success_rate.epoch.env.math": 0.9695885509838998,
      "success_rate.epoch.env.sat": 0.08670520231213873,
      "success_rate.epoch.env.science": 0.9498660543436663,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5938891424194944,
      "success_rate.epoch.global": 0.8436730674544559,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9959054388133498,
      "tokens_p.mean_in_band": 0.7634548611111112,
      "tokens_rate.above_band": 0.988997555012225,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011002444987775062
    },
    {
      "epoch": 1.4004321808510638,
      "grad_norm": 52.45351729152351,
      "learning_rate": 1.6855115649845993e-07,
      "loss": 0.2796,
      "step": 8425,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46875,
      "success_rate.epoch.env.logic": 0.5774946921443737,
      "success_rate.epoch.env.math": 0.9697508896797153,
      "success_rate.epoch.env.sat": 0.08620689655172414,
      "success_rate.epoch.env.science": 0.9499235474006116,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5939455490973007,
      "success_rate.epoch.global": 0.8437346437346437,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9896864686468647,
      "tokens_p.mean_in_band": 0.6438802083333334,
      "tokens_rate.above_band": 0.9099099099099099,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09009009009009009
    },
    {
      "epoch": 1.4012632978723405,
      "grad_norm": 57.910756304430734,
      "learning_rate": 1.6852932005694071e-07,
      "loss": 0.3465,
      "step": 8430,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4639175257731959,
      "success_rate.epoch.env.logic": 0.5774946921443737,
      "success_rate.epoch.env.math": 0.9698581560283688,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.95,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5934781521776461,
      "success_rate.epoch.global": 0.8435507601765572,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9904442148760331,
      "tokens_p.mean_below_band": 1.6079866327345371e-09,
      "tokens_p.mean_in_band": 0.6223021582733813,
      "tokens_rate.above_band": 0.8383371824480369,
      "tokens_rate.below_band": 0.0011547344110854503,
      "tokens_rate.in_band": 0.1605080831408776
    },
    {
      "epoch": 1.402094414893617,
      "grad_norm": 41.27371947077507,
      "learning_rate": 1.6850750397306815e-07,
      "loss": 0.2101,
      "step": 8435,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.44339622641509435,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4639175257731959,
      "success_rate.epoch.env.logic": 0.5774946921443737,
      "success_rate.epoch.env.math": 0.9699115044247788,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.950152207001522,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5934968390320035,
      "success_rate.epoch.global": 0.8438952777098117,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.991869918699187,
      "tokens_p.mean_in_band": 0.8763020833333334,
      "tokens_rate.above_band": 0.9761904761904762,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023809523809523808
    },
    {
      "epoch": 1.4029255319148937,
      "grad_norm": 74.19727213794278,
      "learning_rate": 1.6848570828556055e-07,
      "loss": 0.2465,
      "step": 8440,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4639175257731959,
      "success_rate.epoch.env.logic": 0.5792811839323467,
      "success_rate.epoch.env.math": 0.9700704225352113,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.9502090459901178,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5933021443884131,
      "success_rate.epoch.global": 0.843994140625,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9975253222836096,
      "tokens_p.mean_in_band": 0.755859375,
      "tokens_rate.above_band": 0.9945054945054945,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005494505494505495
    },
    {
      "epoch": 1.4037566489361701,
      "grad_norm": 293.395395615618,
      "learning_rate": 1.6846393303309984e-07,
      "loss": 0.3409,
      "step": 8445,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46938775510204084,
      "success_rate.epoch.env.logic": 0.580168776371308,
      "success_rate.epoch.env.math": 0.9702276707530648,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.9502090459901178,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5938944234780185,
      "success_rate.epoch.global": 0.8441843452816387,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9935379644588045,
      "tokens_p.mean_in_band": 0.6997282608695652,
      "tokens_rate.above_band": 0.9641744548286605,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03582554517133956
    },
    {
      "epoch": 1.4045877659574468,
      "grad_norm": 33.23971138607381,
      "learning_rate": 1.6844217825433176e-07,
      "loss": 0.3046,
      "step": 8450,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9703315881326352,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.9503034901365706,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5933703928525813,
      "success_rate.epoch.global": 0.8440389294403893,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942249568221071,
      "tokens_p.mean_in_band": 0.7004504504504504,
      "tokens_rate.above_band": 0.9125295508274232,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08747044917257683
    },
    {
      "epoch": 1.4054188829787235,
      "grad_norm": 101.36408097169931,
      "learning_rate": 1.6842044398786577e-07,
      "loss": 0.2966,
      "step": 8455,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5798319327731093,
      "success_rate.epoch.env.math": 0.9703832752613241,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.9504538577912254,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5934691764103449,
      "success_rate.epoch.global": 0.8444174757281553,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9913091715976331,
      "tokens_p.mean_in_band": 0.746875,
      "tokens_rate.above_band": 0.9712643678160919,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028735632183908046
    },
    {
      "epoch": 1.40625,
      "grad_norm": 71.99968433828516,
      "learning_rate": 1.6839873027227485e-07,
      "loss": 0.3234,
      "step": 8460,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5815899581589958,
      "success_rate.epoch.env.math": 0.9703832752613241,
      "success_rate.epoch.env.sat": 0.08571428571428572,
      "success_rate.epoch.env.science": 0.950566037735849,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.593639195076755,
      "success_rate.epoch.global": 0.844718992248062,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9908854166666666,
      "tokens_p.mean_in_band": 0.4971751412429379,
      "tokens_rate.above_band": 0.730593607305936,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2694063926940639
    },
    {
      "epoch": 1.4070811170212765,
      "grad_norm": 57.62338551044947,
      "learning_rate": 1.683770371460955e-07,
      "loss": 0.4822,
      "step": 8465,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58125,
      "success_rate.epoch.env.math": 0.9703832752613241,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.950640542577242,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5935707890490627,
      "success_rate.epoch.global": 0.8444981862152358,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986001317523057,
      "tokens_p.mean_in_band": 0.6627155172413793,
      "tokens_rate.above_band": 0.9631979695431472,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03680203045685279
    },
    {
      "epoch": 1.4079122340425532,
      "grad_norm": 85.41164953714559,
      "learning_rate": 1.683553646478277e-07,
      "loss": 0.2966,
      "step": 8470,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58125,
      "success_rate.epoch.env.math": 0.9705372616984402,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.9507148231753197,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5935915405977167,
      "success_rate.epoch.global": 0.8447609850313859,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9958118556701031,
      "tokens_p.mean_in_band": 0.498046875,
      "tokens_rate.above_band": 0.9974293059125964,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.002570694087403599
    },
    {
      "epoch": 1.4087433510638299,
      "grad_norm": 94.69942747018248,
      "learning_rate": 1.6833371281593487e-07,
      "loss": 0.2865,
      "step": 8475,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58125,
      "success_rate.epoch.env.math": 0.9705882352941176,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.950844277673546,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5936079431517078,
      "success_rate.epoch.global": 0.8450602409638555,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994873395149786,
      "tokens_p.mean_in_band": 0.5691105769230769,
      "tokens_rate.above_band": 0.9642365887207703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03576341127922971
    },
    {
      "epoch": 1.4095744680851063,
      "grad_norm": 622.6886392493246,
      "learning_rate": 1.6831208168884368e-07,
      "loss": 0.235,
      "step": 8480,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4392523364485981,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58125,
      "success_rate.epoch.env.math": 0.9706390328151986,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.950954698614751,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5936225993755522,
      "success_rate.epoch.global": 0.8453211450565311,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.989448051948052,
      "tokens_p.mean_in_band": 0.439453125,
      "tokens_rate.above_band": 0.9935483870967742,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0064516129032258064
    },
    {
      "epoch": 1.410405585106383,
      "grad_norm": 29.6230016642961,
      "learning_rate": 1.6829047130494406e-07,
      "loss": 0.2267,
      "step": 8485,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58125,
      "success_rate.epoch.env.math": 0.9707401032702238,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.9510463378176383,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5941121282531665,
      "success_rate.epoch.global": 0.8456182472989195,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9979729729729729,
      "tokens_p.mean_below_band": 1.7497114868092467e-13,
      "tokens_p.mean_in_band": 0.6658653846153846,
      "tokens_rate.above_band": 0.9850905218317358,
      "tokens_rate.below_band": 0.0010649627263045794,
      "tokens_rate.in_band": 0.013844515441959531
    },
    {
      "epoch": 1.4112367021276595,
      "grad_norm": 227.04022765890267,
      "learning_rate": 1.682688817025892e-07,
      "loss": 0.3032,
      "step": 8490,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58125,
      "success_rate.epoch.env.math": 0.9707401032702238,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.9512104283054004,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5850361364793267,
      "success_rate.epoch.global": 0.8457485029940119,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9943110972568578,
      "tokens_p.mean_in_band": 0.634765625,
      "tokens_rate.above_band": 0.9950372208436724,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004962779156327543
    },
    {
      "epoch": 1.4120678191489362,
      "grad_norm": 64.9213150845803,
      "learning_rate": 1.6824731292009531e-07,
      "loss": 0.3299,
      "step": 8495,
      "success_rate.epoch.env.abd": 0.5833333333333334,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58298755186722,
      "success_rate.epoch.env.math": 0.9707903780068728,
      "success_rate.epoch.env.sat": 0.08522727272727272,
      "success_rate.epoch.env.science": 0.9508928571428571,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5851697960649018,
      "success_rate.epoch.global": 0.845730686438651,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942434210526315,
      "tokens_p.mean_in_band": 0.7126736111111112,
      "tokens_rate.above_band": 0.9547738693467337,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04522613065326633
    },
    {
      "epoch": 1.4128989361702127,
      "grad_norm": 54.897691443447165,
      "learning_rate": 1.682257649957417e-07,
      "loss": 0.1865,
      "step": 8500,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.58298755186722,
      "success_rate.epoch.env.math": 0.9707903780068728,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.9509840326773116,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5871630733103416,
      "success_rate.epoch.global": 0.8459885386819485,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9833409926470589,
      "tokens_p.mean_in_band": 0.8663194444444444,
      "tokens_rate.above_band": 0.9679715302491103,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03202846975088968
    },
    {
      "epoch": 1.4137300531914894,
      "grad_norm": 102.09243416471436,
      "learning_rate": 1.6820423796777067e-07,
      "loss": 0.3828,
      "step": 8505,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5838509316770186,
      "success_rate.epoch.env.math": 0.9708904109589042,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.9510748702742773,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5872589142520502,
      "success_rate.epoch.global": 0.84628217349857,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9931006493506493,
      "tokens_p.mean_in_band": 0.8671875,
      "tokens_rate.above_band": 0.9871794871794872,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01282051282051282
    },
    {
      "epoch": 1.414561170212766,
      "grad_norm": 87.87693699337014,
      "learning_rate": 1.6818273187438742e-07,
      "loss": 0.2531,
      "step": 8510,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5826446280991735,
      "success_rate.epoch.env.math": 0.9709401709401709,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.9511472982975574,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5871603582908413,
      "success_rate.epoch.global": 0.846263683960019,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9940318302387268,
      "tokens_p.mean_in_band": 0.6069444444444444,
      "tokens_rate.above_band": 0.9436795994993742,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056320400500625784
    },
    {
      "epoch": 1.4153922872340425,
      "grad_norm": 46.8815807390635,
      "learning_rate": 1.6816124675376e-07,
      "loss": 0.3642,
      "step": 8515,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5823045267489712,
      "success_rate.epoch.env.math": 0.9710391822827938,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.9512195121951219,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5871450059172036,
      "success_rate.epoch.global": 0.8463182897862233,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9989406779661016,
      "tokens_p.mean_in_band": 0.74765625,
      "tokens_rate.above_band": 0.9860724233983287,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013927576601671309
    },
    {
      "epoch": 1.4162234042553192,
      "grad_norm": 59.774205281413664,
      "learning_rate": 1.681397826440192e-07,
      "loss": 0.3651,
      "step": 8520,
      "success_rate.epoch.env.abd": 0.6153846153846154,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46464646464646464,
      "success_rate.epoch.env.logic": 0.5823045267489712,
      "success_rate.epoch.env.math": 0.9710391822827938,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.9509587020648967,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5885198973039664,
      "success_rate.epoch.global": 0.8463362580033199,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9909147869674185,
      "tokens_p.mean_in_band": 0.52734375,
      "tokens_rate.above_band": 0.869281045751634,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13071895424836602
    },
    {
      "epoch": 1.4170545212765957,
      "grad_norm": 57.75438079059562,
      "learning_rate": 1.6811833958325864e-07,
      "loss": 0.3606,
      "step": 8525,
      "success_rate.epoch.env.abd": 0.6153846153846154,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46,
      "success_rate.epoch.env.logic": 0.5823045267489712,
      "success_rate.epoch.env.math": 0.9711375212224108,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.951048951048951,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5881146357837124,
      "success_rate.epoch.global": 0.8463905325443787,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9887704174228675,
      "tokens_p.mean_in_band": 0.6736111111111112,
      "tokens_rate.above_band": 0.859594383775351,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14040561622464898
    },
    {
      "epoch": 1.4178856382978724,
      "grad_norm": 54.146553604113556,
      "learning_rate": 1.6809691760953443e-07,
      "loss": 0.2784,
      "step": 8530,
      "success_rate.epoch.env.abd": 0.6153846153846154,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5831622176591376,
      "success_rate.epoch.env.math": 0.9711375212224108,
      "success_rate.epoch.env.sat": 0.0903954802259887,
      "success_rate.epoch.env.science": 0.9507533994854833,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5877516979565446,
      "success_rate.epoch.global": 0.8461356653273457,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.989856429463171,
      "tokens_p.mean_below_band": 1.0277290130034089e-10,
      "tokens_p.mean_in_band": 0.6682091346153847,
      "tokens_rate.above_band": 0.8594420600858369,
      "tokens_rate.below_band": 0.001072961373390558,
      "tokens_rate.in_band": 0.13948497854077252
    },
    {
      "epoch": 1.4187167553191489,
      "grad_norm": 47.83464306540245,
      "learning_rate": 1.680755167608653e-07,
      "loss": 0.2885,
      "step": 8535,
      "success_rate.epoch.env.abd": 0.6153846153846154,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5831622176591376,
      "success_rate.epoch.env.math": 0.9712351945854484,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.9508076358296622,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5877193406775142,
      "success_rate.epoch.global": 0.8461175359924474,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9926927860696517,
      "tokens_p.mean_in_band": 0.6770582932692307,
      "tokens_rate.above_band": 0.8854625550660793,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1145374449339207
    },
    {
      "epoch": 1.4195478723404256,
      "grad_norm": 248.32031368998727,
      "learning_rate": 1.6805413707523256e-07,
      "loss": 0.4229,
      "step": 8540,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5831622176591376,
      "success_rate.epoch.env.math": 0.9712837837837838,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.9505131964809385,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5856249885918405,
      "success_rate.epoch.global": 0.8458637756304501,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9804817275747508,
      "tokens_p.mean_in_band": 0.6345419847328244,
      "tokens_rate.above_band": 0.6967592592592593,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.30324074074074076
    },
    {
      "epoch": 1.4203789893617023,
      "grad_norm": 28.831742212183467,
      "learning_rate": 1.6803277859057993e-07,
      "loss": 0.1909,
      "step": 8545,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5804480651731161,
      "success_rate.epoch.env.math": 0.9713322091062394,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.9505675576711827,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5853875916851748,
      "success_rate.epoch.global": 0.8454481298517996,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9991362631288004,
      "tokens_p.mean_in_band": 0.6020107581967213,
      "tokens_rate.above_band": 0.967379679144385,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.032620320855614976
    },
    {
      "epoch": 1.4212101063829787,
      "grad_norm": 113.12793535026168,
      "learning_rate": 1.6801144134481347e-07,
      "loss": 0.2344,
      "step": 8550,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5804480651731161,
      "success_rate.epoch.env.math": 0.9713322091062394,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.9507119386637459,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854007172299535,
      "success_rate.epoch.global": 0.8457384362526414,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951149425287357,
      "tokens_p.mean_in_band": 0.6796875,
      "tokens_rate.above_band": 0.9954233409610984,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004576659038901602
    },
    {
      "epoch": 1.4220412234042552,
      "grad_norm": 97.25920413395448,
      "learning_rate": 1.6799012537580156e-07,
      "loss": 0.2869,
      "step": 8555,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5813008130081301,
      "success_rate.epoch.env.math": 0.9713322091062394,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.9507838133430551,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854847738221646,
      "success_rate.epoch.global": 0.8459193245778611,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978054775280899,
      "tokens_p.mean_in_band": 0.76171875,
      "tokens_rate.above_band": 0.9888888888888889,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011111111111111112
    },
    {
      "epoch": 1.422872340425532,
      "grad_norm": 133.72499691704502,
      "learning_rate": 1.679688307213748e-07,
      "loss": 0.3424,
      "step": 8560,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5826612903225806,
      "success_rate.epoch.env.math": 0.9713322091062394,
      "success_rate.epoch.env.sat": 0.0898876404494382,
      "success_rate.epoch.env.science": 0.9508733624454149,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.585616594405511,
      "success_rate.epoch.global": 0.8460098291598409,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9975429975429976,
      "tokens_p.mean_in_band": 0.5405016447368421,
      "tokens_rate.above_band": 0.9771908763505402,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022809123649459785
    },
    {
      "epoch": 1.4237034574468086,
      "grad_norm": 93.43347688320038,
      "learning_rate": 1.6794755741932601e-07,
      "loss": 0.3283,
      "step": 8565,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5826612903225806,
      "success_rate.epoch.env.math": 0.9713804713804713,
      "success_rate.epoch.env.sat": 0.0893854748603352,
      "success_rate.epoch.env.science": 0.9509803921568627,
      "success_rate.epoch.env.webshop": 0.4,
      "success_rate.epoch.env_macro_mean": 0.5764941513506543,
      "success_rate.epoch.global": 0.845866417561887,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9921518264840182,
      "tokens_p.mean_in_band": 0.6305803571428571,
      "tokens_rate.above_band": 0.8866396761133604,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11336032388663968
    },
    {
      "epoch": 1.424534574468085,
      "grad_norm": 30.845878216754365,
      "learning_rate": 1.679263055074101e-07,
      "loss": 0.2865,
      "step": 8570,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45544554455445546,
      "success_rate.epoch.env.logic": 0.5826612903225806,
      "success_rate.epoch.env.math": 0.9715242881072027,
      "success_rate.epoch.env.sat": 0.0893854748603352,
      "success_rate.epoch.env.science": 0.9510514865844815,
      "success_rate.epoch.env.webshop": 0.4,
      "success_rate.epoch.env_macro_mean": 0.5765136887283225,
      "success_rate.epoch.global": 0.8461179762182327,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9976851851851852,
      "tokens_p.mean_in_band": 0.44503348214285715,
      "tokens_rate.above_band": 0.9665871121718377,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03341288782816229
    },
    {
      "epoch": 1.4253656914893618,
      "grad_norm": 68.72044706609415,
      "learning_rate": 1.6790507502334396e-07,
      "loss": 0.2513,
      "step": 8575,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.5814889336016097,
      "success_rate.epoch.env.math": 0.9715242881072027,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.9511400651465798,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5859462710047513,
      "success_rate.epoch.global": 0.845974872033504,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9924175126903553,
      "tokens_p.mean_in_band": 0.6511182598039216,
      "tokens_rate.above_band": 0.9507722007722008,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04922779922779923
    },
    {
      "epoch": 1.4261968085106382,
      "grad_norm": 44.67211750077507,
      "learning_rate": 1.6788386600480658e-07,
      "loss": 0.2824,
      "step": 8580,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.5803212851405622,
      "success_rate.epoch.env.math": 0.9715242881072027,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.9512459371614301,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858497458732788,
      "success_rate.epoch.global": 0.845993031358885,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9945693597560976,
      "tokens_p.mean_in_band": 0.5940290178571429,
      "tokens_rate.above_band": 0.9590643274853801,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04093567251461988
    },
    {
      "epoch": 1.427027925531915,
      "grad_norm": 80.3944084089916,
      "learning_rate": 1.678626784894387e-07,
      "loss": 0.2373,
      "step": 8585,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.5803212851405622,
      "success_rate.epoch.env.math": 0.9715242881072027,
      "success_rate.epoch.env.sat": 0.08888888888888889,
      "success_rate.epoch.env.science": 0.9513513513513514,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858593289814533,
      "success_rate.epoch.global": 0.8462073764787752,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9902573529411764,
      "tokens_p.mean_in_band": 0.8372395833333334,
      "tokens_rate.above_band": 0.9826589595375722,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017341040462427744
    },
    {
      "epoch": 1.4278590425531914,
      "grad_norm": 122.8034342934403,
      "learning_rate": 1.67841512514843e-07,
      "loss": 0.2955,
      "step": 8590,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.5811623246492986,
      "success_rate.epoch.env.math": 0.9716193656093489,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.9514038876889849,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.586406821380847,
      "success_rate.epoch.global": 0.8464566929133859,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.994410569105691,
      "tokens_p.mean_in_band": 0.76953125,
      "tokens_rate.above_band": 0.9879518072289156,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012048192771084338
    },
    {
      "epoch": 1.428690159574468,
      "grad_norm": 104.24034106569569,
      "learning_rate": 1.6782036811858386e-07,
      "loss": 0.3699,
      "step": 8595,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.582,
      "success_rate.epoch.env.math": 0.9716193656093489,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.9514563106796117,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5864877394118768,
      "success_rate.epoch.global": 0.8465987968533086,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9903645833333333,
      "tokens_p.mean_below_band": 1.4915713109076023e-10,
      "tokens_p.mean_in_band": 0.8546875,
      "tokens_rate.above_band": 0.975609756097561,
      "tokens_rate.below_band": 0.0040650406504065045,
      "tokens_rate.in_band": 0.02032520325203252
    },
    {
      "epoch": 1.4295212765957448,
      "grad_norm": 39.72259975094303,
      "learning_rate": 1.6779924533818745e-07,
      "loss": 0.2195,
      "step": 8600,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46078431372549017,
      "success_rate.epoch.env.logic": 0.582,
      "success_rate.epoch.env.math": 0.9716666666666667,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.9515781922525107,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5865031196509874,
      "success_rate.epoch.global": 0.8468822170900693,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9849837662337663,
      "tokens_p.mean_in_band": 0.8463541666666666,
      "tokens_rate.above_band": 0.9808917197452229,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01910828025477707
    },
    {
      "epoch": 1.4303523936170213,
      "grad_norm": 100.07232165750263,
      "learning_rate": 1.6777814421114155e-07,
      "loss": 0.3136,
      "step": 8605,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4563106796116505,
      "success_rate.epoch.env.logic": 0.5808383233532934,
      "success_rate.epoch.env.math": 0.9717607973421927,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.951647564469914,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860056825721132,
      "success_rate.epoch.global": 0.8467035500230521,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977895480225989,
      "tokens_p.mean_in_band": 0.5431937172774869,
      "tokens_rate.above_band": 0.9586221837088388,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.041377816291161176
    },
    {
      "epoch": 1.4311835106382977,
      "grad_norm": 88.49918466277656,
      "learning_rate": 1.6775706477489542e-07,
      "loss": 0.1981,
      "step": 8610,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4563106796116505,
      "success_rate.epoch.env.logic": 0.5808383233532934,
      "success_rate.epoch.env.math": 0.971947194719472,
      "success_rate.epoch.env.sat": 0.09392265193370165,
      "success_rate.epoch.env.science": 0.9517340007150519,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860304856286965,
      "success_rate.epoch.global": 0.8470209339774557,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9852642276422764,
      "tokens_p.mean_in_band": 0.88125,
      "tokens_rate.above_band": 0.9609375,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0390625
    },
    {
      "epoch": 1.4320146276595744,
      "grad_norm": 17.35600566267856,
      "learning_rate": 1.6773600706685992e-07,
      "loss": 0.3189,
      "step": 8615,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.44954128440366975,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5808383233532934,
      "success_rate.epoch.env.math": 0.9720394736842105,
      "success_rate.epoch.env.sat": 0.09340659340659341,
      "success_rate.epoch.env.science": 0.9517857142857142,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.586061137563146,
      "success_rate.epoch.global": 0.8468427095292766,
      "success_rate.window.env.agentgym:alfworld": 0.6666666666666666,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9923309682804674,
      "tokens_p.mean_in_band": 0.6994392641129032,
      "tokens_rate.above_band": 0.9062027231467473,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09379727685325265
    },
    {
      "epoch": 1.4328457446808511,
      "grad_norm": 63.43731999211111,
      "learning_rate": 1.6771497112440735e-07,
      "loss": 0.2726,
      "step": 8620,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.44954128440366975,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5808383233532934,
      "success_rate.epoch.env.math": 0.9720394736842105,
      "success_rate.epoch.env.sat": 0.09340659340659341,
      "success_rate.epoch.env.science": 0.9512455516014234,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860120318645742,
      "success_rate.epoch.global": 0.8467353951890034,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9913194444444444,
      "tokens_p.mean_in_band": 0.6731770833333334,
      "tokens_rate.above_band": 0.9473684210526315,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05263157894736842
    },
    {
      "epoch": 1.4336768617021276,
      "grad_norm": 54.61369506875519,
      "learning_rate": 1.6769395698487138e-07,
      "loss": 0.4171,
      "step": 8625,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5808383233532934,
      "success_rate.epoch.env.math": 0.9721311475409836,
      "success_rate.epoch.env.sat": 0.09340659340659341,
      "success_rate.epoch.env.science": 0.9513321492007105,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5861108898193778,
      "success_rate.epoch.global": 0.846822130772748,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9977897838899804,
      "tokens_p.mean_in_band": 0.7161458333333334,
      "tokens_rate.above_band": 0.9883495145631068,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011650485436893204
    },
    {
      "epoch": 1.4345079787234043,
      "grad_norm": 304.3190549004163,
      "learning_rate": 1.6767296468554685e-07,
      "loss": 0.2495,
      "step": 8630,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5816733067729084,
      "success_rate.epoch.env.math": 0.9722222222222222,
      "success_rate.epoch.env.sat": 0.09289617486338798,
      "success_rate.epoch.env.science": 0.951418439716312,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5861565198260369,
      "success_rate.epoch.global": 0.8469085101528633,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959177927927928,
      "tokens_p.mean_in_band": 0.6796875,
      "tokens_rate.above_band": 0.9652173913043478,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034782608695652174
    },
    {
      "epoch": 1.4353390957446808,
      "grad_norm": 312.434319232639,
      "learning_rate": 1.6765199426369007e-07,
      "loss": 0.2669,
      "step": 8635,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5816733067729084,
      "success_rate.epoch.env.math": 0.9722675367047309,
      "success_rate.epoch.env.sat": 0.09289617486338798,
      "success_rate.epoch.env.science": 0.9515729939908095,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5861746897130374,
      "success_rate.epoch.global": 0.8472569997723651,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9910102739726028,
      "tokens_p.mean_in_band": 0.8854166666666666,
      "tokens_rate.above_band": 0.9798657718120806,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020134228187919462
    },
    {
      "epoch": 1.4361702127659575,
      "grad_norm": 424.42794893225584,
      "learning_rate": 1.676310457565183e-07,
      "loss": 0.2701,
      "step": 8640,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5816733067729084,
      "success_rate.epoch.env.math": 0.9723127035830619,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.9516413695728909,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5861391144352965,
      "success_rate.epoch.global": 0.8472380086383269,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9874625748502994,
      "tokens_p.mean_below_band": 3.0547380447387695e-07,
      "tokens_p.mean_in_band": 0.669677734375,
      "tokens_rate.above_band": 0.907608695652174,
      "tokens_rate.below_band": 0.005434782608695652,
      "tokens_rate.in_band": 0.08695652173913043
    },
    {
      "epoch": 1.437001329787234,
      "grad_norm": 46.119291957804386,
      "learning_rate": 1.676101192012101e-07,
      "loss": 0.3312,
      "step": 8645,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5816733067729084,
      "success_rate.epoch.env.math": 0.9723127035830619,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.9516925246826516,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5861437648998202,
      "success_rate.epoch.global": 0.8473421172194457,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9958314167433303,
      "tokens_p.mean_in_band": 0.6761762640449438,
      "tokens_rate.above_band": 0.9243197278911565,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07568027210884354
    },
    {
      "epoch": 1.4378324468085106,
      "grad_norm": 255.95866811533935,
      "learning_rate": 1.675892146349049e-07,
      "loss": 0.2728,
      "step": 8650,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5813492063492064,
      "success_rate.epoch.env.math": 0.9723127035830619,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.9518114667604644,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.586125114141103,
      "success_rate.epoch.global": 0.8474268873271367,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966023489932886,
      "tokens_p.mean_in_band": 0.6751302083333334,
      "tokens_rate.above_band": 0.9841479524438573,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015852047556142668
    },
    {
      "epoch": 1.4386635638297873,
      "grad_norm": 29.06535848688785,
      "learning_rate": 1.6756833209470323e-07,
      "loss": 0.2309,
      "step": 8655,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5798816568047337,
      "success_rate.epoch.env.math": 0.9724473257698542,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.9518453427065027,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860070185582266,
      "success_rate.epoch.global": 0.8472505091649695,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9978480538922155,
      "tokens_p.mean_in_band": 0.5659327651515151,
      "tokens_rate.above_band": 0.9758948137326515,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02410518626734843
    },
    {
      "epoch": 1.4394946808510638,
      "grad_norm": 240.5160701591656,
      "learning_rate": 1.6754747161766648e-07,
      "loss": 0.2569,
      "step": 8660,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5798816568047337,
      "success_rate.epoch.env.math": 0.9724473257698542,
      "success_rate.epoch.env.sat": 0.09239130434782608,
      "success_rate.epoch.env.science": 0.9519298245614035,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860146987268539,
      "success_rate.epoch.global": 0.8474231464737794,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9938063063063063,
      "tokens_p.mean_in_band": 0.6397758152173914,
      "tokens_rate.above_band": 0.9666182873730044,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033381712626995644
    },
    {
      "epoch": 1.4403257978723405,
      "grad_norm": 39.62803208176381,
      "learning_rate": 1.6752663324081687e-07,
      "loss": 0.2168,
      "step": 8665,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5807086614173228,
      "success_rate.epoch.env.math": 0.9725363489499192,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.9519971969166082,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860586976079379,
      "success_rate.epoch.global": 0.8474729241877257,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9920528017241379,
      "tokens_p.mean_in_band": 0.6429227941176471,
      "tokens_rate.above_band": 0.9317269076305221,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06827309236947791
    },
    {
      "epoch": 1.441156914893617,
      "grad_norm": 61.07512049302331,
      "learning_rate": 1.6750581700113742e-07,
      "loss": 0.2246,
      "step": 8670,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5803921568627451,
      "success_rate.epoch.env.math": 0.9725806451612903,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.952047602380119,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860385337097838,
      "success_rate.epoch.global": 0.8474538080216314,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9962631406044679,
      "tokens_p.mean_in_band": 0.6515066964285714,
      "tokens_rate.above_band": 0.9819354838709677,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01806451612903226
    },
    {
      "epoch": 1.4419880319148937,
      "grad_norm": 67.94565280718675,
      "learning_rate": 1.6748502293557184e-07,
      "loss": 0.1965,
      "step": 8675,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5803921568627451,
      "success_rate.epoch.env.math": 0.9726247987117552,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.9517988124345093,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5860199304011342,
      "success_rate.epoch.global": 0.8474690663667042,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9913321167883211,
      "tokens_p.mean_below_band": 1.955777406692505e-08,
      "tokens_p.mean_in_band": 0.75,
      "tokens_rate.above_band": 0.9647887323943662,
      "tokens_rate.below_band": 0.007042253521126761,
      "tokens_rate.in_band": 0.028169014084507043
    },
    {
      "epoch": 1.4428191489361701,
      "grad_norm": 164.19239948795624,
      "learning_rate": 1.6746425108102456e-07,
      "loss": 0.2735,
      "step": 8680,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5792563600782779,
      "success_rate.epoch.env.math": 0.9726688102893891,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.9519163763066202,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5859313648252503,
      "success_rate.epoch.global": 0.8475527615626404,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964849768875192,
      "tokens_p.mean_in_band": 0.6681385869565217,
      "tokens_rate.above_band": 0.9657738095238095,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03422619047619048
    },
    {
      "epoch": 1.4436502659574468,
      "grad_norm": 55.10663821114271,
      "learning_rate": 1.6744350147436046e-07,
      "loss": 0.2592,
      "step": 8685,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9726688102893891,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.9516689847009736,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858807845286257,
      "success_rate.epoch.global": 0.8473778574630211,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9973628691983122,
      "tokens_p.mean_in_band": 0.65625,
      "tokens_rate.above_band": 0.9875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0125
    },
    {
      "epoch": 1.4444813829787235,
      "grad_norm": 29.708229339774526,
      "learning_rate": 1.6742277415240505e-07,
      "loss": 0.2786,
      "step": 8690,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9726688102893891,
      "success_rate.epoch.env.sat": 0.0918918918918919,
      "success_rate.epoch.env.science": 0.9518197573656846,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858944911345084,
      "success_rate.epoch.global": 0.8476850816372177,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9902673545966229,
      "tokens_p.mean_in_band": 0.6785714285714286,
      "tokens_rate.above_band": 0.8541666666666666,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14583333333333334
    },
    {
      "epoch": 1.4453125,
      "grad_norm": 39.03621860273987,
      "learning_rate": 1.6740206915194423e-07,
      "loss": 0.3147,
      "step": 8695,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.45045045045045046,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5766990291262136,
      "success_rate.epoch.env.math": 0.9728,
      "success_rate.epoch.env.sat": 0.0913978494623656,
      "success_rate.epoch.env.science": 0.9518531347419467,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5856601443492818,
      "success_rate.epoch.global": 0.8472873409243135,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9974712323682257,
      "tokens_p.mean_in_band": 0.65078125,
      "tokens_rate.above_band": 0.9573560767590619,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.042643923240938165
    },
    {
      "epoch": 1.4461436170212765,
      "grad_norm": 225.77303993765307,
      "learning_rate": 1.6738138650972434e-07,
      "loss": 0.2559,
      "step": 8700,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5775193798449613,
      "success_rate.epoch.env.math": 0.9728867623604466,
      "success_rate.epoch.env.sat": 0.0913978494623656,
      "success_rate.epoch.env.science": 0.9518864659051575,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5853800139147842,
      "success_rate.epoch.global": 0.8472686733556298,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967648678414097,
      "tokens_p.mean_in_band": 0.7265625,
      "tokens_rate.above_band": 0.9826839826839827,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017316017316017316
    },
    {
      "epoch": 1.4469747340425532,
      "grad_norm": 680.9468878174185,
      "learning_rate": 1.6736072626245194e-07,
      "loss": 0.3047,
      "step": 8705,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5775193798449613,
      "success_rate.epoch.env.math": 0.972972972972973,
      "success_rate.epoch.env.sat": 0.09090909090909091,
      "success_rate.epoch.env.science": 0.951969592259848,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5853509755887791,
      "success_rate.epoch.global": 0.8473180503004674,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9914596273291926,
      "tokens_p.mean_below_band": 8.149072527885437e-09,
      "tokens_p.mean_in_band": 0.5965073529411765,
      "tokens_rate.above_band": 0.8994413407821229,
      "tokens_rate.below_band": 0.00558659217877095,
      "tokens_rate.in_band": 0.09497206703910614
    },
    {
      "epoch": 1.4478058510638299,
      "grad_norm": 62.860235008006676,
      "learning_rate": 1.6734008844679396e-07,
      "loss": 0.4091,
      "step": 8710,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.4424778761061947,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5783365570599613,
      "success_rate.epoch.env.math": 0.972972972972973,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.951986183074266,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854611644102378,
      "success_rate.epoch.global": 0.8470431302801245,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9972527472527473,
      "tokens_p.mean_in_band": 0.6467578125,
      "tokens_rate.above_band": 0.9667994687915007,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033200531208499334
    },
    {
      "epoch": 1.4486369680851063,
      "grad_norm": 55.9695147997463,
      "learning_rate": 1.6731947309937744e-07,
      "loss": 0.2228,
      "step": 8715,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5772200772200772,
      "success_rate.epoch.env.math": 0.972972972972973,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.9520358868184955,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5850113315944395,
      "success_rate.epoch.global": 0.8467688207861426,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952417695473251,
      "tokens_p.mean_in_band": 0.6136067708333334,
      "tokens_rate.above_band": 0.9818181818181818,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01818181818181818
    },
    {
      "epoch": 1.449468085106383,
      "grad_norm": 45.446571894704654,
      "learning_rate": 1.672988802567896e-07,
      "loss": 0.1526,
      "step": 8720,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4519230769230769,
      "success_rate.epoch.env.logic": 0.5761078998073218,
      "success_rate.epoch.env.math": 0.973015873015873,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.9521349862258953,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5849231335978528,
      "success_rate.epoch.global": 0.8468188871647085,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963672969187675,
      "tokens_p.mean_in_band": 0.6397372159090909,
      "tokens_rate.above_band": 0.9848275862068966,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015172413793103448
    },
    {
      "epoch": 1.4502992021276595,
      "grad_norm": 47.457035107552926,
      "learning_rate": 1.6727830995557766e-07,
      "loss": 0.3986,
      "step": 8725,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.5769230769230769,
      "success_rate.epoch.env.math": 0.9731012658227848,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.952200825309491,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854855144365839,
      "success_rate.epoch.global": 0.8470900641734898,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99609375,
      "tokens_p.mean_below_band": 5.893525667488575e-10,
      "tokens_p.mean_in_band": 0.8854166666666666,
      "tokens_rate.above_band": 0.9959654178674352,
      "tokens_rate.below_band": 0.0005763688760806917,
      "tokens_rate.in_band": 0.00345821325648415
    },
    {
      "epoch": 1.4511303191489362,
      "grad_norm": 91.4597482139096,
      "learning_rate": 1.6725776223224885e-07,
      "loss": 0.2718,
      "step": 8730,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.5769230769230769,
      "success_rate.epoch.env.math": 0.9731012658227848,
      "success_rate.epoch.env.sat": 0.09523809523809523,
      "success_rate.epoch.env.science": 0.9519395811877789,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854617649709737,
      "success_rate.epoch.global": 0.8470380194518126,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9868683510638298,
      "tokens_p.mean_below_band": 1.8416358216200024e-08,
      "tokens_p.mean_in_band": 0.5908203125,
      "tokens_rate.above_band": 0.912621359223301,
      "tokens_rate.below_band": 0.009708737864077669,
      "tokens_rate.in_band": 0.07766990291262135
    },
    {
      "epoch": 1.4519614361702127,
      "grad_norm": 22.796198905348415,
      "learning_rate": 1.6723723712327042e-07,
      "loss": 0.2272,
      "step": 8735,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.5769230769230769,
      "success_rate.epoch.env.math": 0.9731012658227848,
      "success_rate.epoch.env.sat": 0.09473684210526316,
      "success_rate.epoch.env.science": 0.9520219328307059,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854236830173459,
      "success_rate.epoch.global": 0.8470198675496688,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9911111111111112,
      "tokens_p.mean_in_band": 0.72216796875,
      "tokens_rate.above_band": 0.8754863813229572,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1245136186770428
    },
    {
      "epoch": 1.4527925531914894,
      "grad_norm": 54.05771872340115,
      "learning_rate": 1.672167346650693e-07,
      "loss": 0.3134,
      "step": 8740,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45714285714285713,
      "success_rate.epoch.env.logic": 0.5769230769230769,
      "success_rate.epoch.env.math": 0.973186119873817,
      "success_rate.epoch.env.sat": 0.09473684210526316,
      "success_rate.epoch.env.science": 0.9521040027369141,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854388579225497,
      "success_rate.epoch.global": 0.8472558959664976,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9901889534883721,
      "tokens_p.mean_in_band": 0.8776041666666666,
      "tokens_rate.above_band": 0.9662921348314607,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033707865168539325
    },
    {
      "epoch": 1.453623670212766,
      "grad_norm": 120.17919160073394,
      "learning_rate": 1.6719625489403243e-07,
      "loss": 0.2402,
      "step": 8745,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4528301886792453,
      "success_rate.epoch.env.logic": 0.5777351247600768,
      "success_rate.epoch.env.math": 0.973186119873817,
      "success_rate.epoch.env.sat": 0.09473684210526316,
      "success_rate.epoch.env.science": 0.9521857923497268,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5851280551031134,
      "success_rate.epoch.global": 0.8472711267605634,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9925246891002194,
      "tokens_p.mean_in_band": 0.5591957885304659,
      "tokens_rate.above_band": 0.830498177399757,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16950182260024302
    },
    {
      "epoch": 1.4544547872340425,
      "grad_norm": 100.65369323379176,
      "learning_rate": 1.6717579784650635e-07,
      "loss": 0.1957,
      "step": 8750,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.578544061302682,
      "success_rate.epoch.env.math": 0.973186119873817,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9522184300341296,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.585579734073672,
      "success_rate.epoch.global": 0.847032967032967,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9948308270676691,
      "tokens_p.mean_in_band": 0.697985197368421,
      "tokens_rate.above_band": 0.9130434782608695,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08695652173913043
    },
    {
      "epoch": 1.4552859042553192,
      "grad_norm": 63.25419099890285,
      "learning_rate": 1.671553635587973e-07,
      "loss": 0.3672,
      "step": 8755,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.578544061302682,
      "success_rate.epoch.env.math": 0.973186119873817,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9523323118828737,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5855900869690124,
      "success_rate.epoch.global": 0.847267939433838,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9884982638888888,
      "tokens_p.mean_in_band": 0.802734375,
      "tokens_rate.above_band": 0.9473684210526315,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05263157894736842
    },
    {
      "epoch": 1.4561170212765957,
      "grad_norm": 67.16979030932264,
      "learning_rate": 1.6713495206717115e-07,
      "loss": 0.2948,
      "step": 8760,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.578544061302682,
      "success_rate.epoch.env.math": 0.97339593114241,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9524133242692047,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5856165254830963,
      "success_rate.epoch.global": 0.8476023647908911,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9909957627118644,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.4569481382978724,
      "grad_norm": 49.82950088176118,
      "learning_rate": 1.6711456340785325e-07,
      "loss": 0.1949,
      "step": 8765,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45794392523364486,
      "success_rate.epoch.env.logic": 0.578544061302682,
      "success_rate.epoch.env.math": 0.9734789391575663,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9525101763907734,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5856328764046168,
      "success_rate.epoch.global": 0.8478688524590164,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9852941176470589,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.4577792553191489,
      "grad_norm": 1.2199100707662283,
      "learning_rate": 1.6709419761702856e-07,
      "loss": 0.2266,
      "step": 8770,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4537037037037037,
      "success_rate.epoch.env.logic": 0.578544061302682,
      "success_rate.epoch.env.math": 0.973561430793157,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9525262800949474,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5852563649327825,
      "success_rate.epoch.global": 0.8477833588119676,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9914198234121333,
      "tokens_p.mean_below_band": 3.0547380447387695e-07,
      "tokens_p.mean_in_band": 0.49826959978070173,
      "tokens_rate.above_band": 0.793625678119349,
      "tokens_rate.below_band": 0.0002260397830018083,
      "tokens_rate.in_band": 0.20614828209764918
    },
    {
      "epoch": 1.4586103723404256,
      "grad_norm": 125.04770250388152,
      "learning_rate": 1.670738547308413e-07,
      "loss": 0.3216,
      "step": 8775,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45871559633027525,
      "success_rate.epoch.env.logic": 0.578544061302682,
      "success_rate.epoch.env.math": 0.9736024844720497,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9525745257452575,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5857201096560347,
      "success_rate.epoch.global": 0.8479493891797557,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9985160013764625,
      "tokens_p.mean_in_band": 0.23349216331269348,
      "tokens_rate.above_band": 0.8181306306306306,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18186936936936937
    },
    {
      "epoch": 1.4594414893617023,
      "grad_norm": 37.293791066211455,
      "learning_rate": 1.670535347853951e-07,
      "loss": 0.2724,
      "step": 8780,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45871559633027525,
      "success_rate.epoch.env.logic": 0.5801526717557252,
      "success_rate.epoch.env.math": 0.9736434108527132,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.952638700947226,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858759016592779,
      "success_rate.epoch.global": 0.8481812241341755,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917763157894737,
      "tokens_p.mean_in_band": 0.8169642857142857,
      "tokens_rate.above_band": 0.976027397260274,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023972602739726026
    },
    {
      "epoch": 1.4602726063829787,
      "grad_norm": 38.87283598834505,
      "learning_rate": 1.6703323781675297e-07,
      "loss": 0.3142,
      "step": 8785,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45871559633027525,
      "success_rate.epoch.env.logic": 0.5798479087452472,
      "success_rate.epoch.env.math": 0.9736434108527132,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.952686718485975,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.585852561161848,
      "success_rate.epoch.global": 0.8481288076588338,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941100303183426,
      "tokens_p.mean_below_band": 7.003545761108398e-07,
      "tokens_p.mean_in_band": 0.4973266786798179,
      "tokens_rate.above_band": 0.8568954319116692,
      "tokens_rate.below_band": 0.00043299415457891317,
      "tokens_rate.in_band": 0.1426715739337519
    },
    {
      "epoch": 1.4611037234042552,
      "grad_norm": 54.46552396007076,
      "learning_rate": 1.6701296386093698e-07,
      "loss": 0.4159,
      "step": 8790,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5798479087452472,
      "success_rate.epoch.env.math": 0.9736434108527132,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9527824620573356,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854821613242608,
      "success_rate.epoch.global": 0.8481425157505974,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944903581267218,
      "tokens_p.mean_below_band": 1.3535221417744955e-07,
      "tokens_p.mean_in_band": 0.48112277809633025,
      "tokens_rate.above_band": 0.9009476534296029,
      "tokens_rate.below_band": 0.0006768953068592057,
      "tokens_rate.in_band": 0.0983754512635379
    },
    {
      "epoch": 1.461934840425532,
      "grad_norm": 268.13693865907,
      "learning_rate": 1.6699271295392846e-07,
      "loss": 0.2378,
      "step": 8795,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43859649122807015,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5787476280834914,
      "success_rate.epoch.env.math": 0.9737654320987654,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9528301886792453,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5853975674339158,
      "success_rate.epoch.global": 0.8481561822125814,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9971122112211221,
      "tokens_p.mean_in_band": 0.5791015625,
      "tokens_rate.above_band": 0.9588607594936709,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04113924050632911
    },
    {
      "epoch": 1.4627659574468086,
      "grad_norm": 264.3785545733138,
      "learning_rate": 1.6697248513166778e-07,
      "loss": 0.3537,
      "step": 8800,
      "success_rate.epoch.env.abd": 0.5925925925925926,
      "success_rate.epoch.env.agentgym:alfworld": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5787476280834914,
      "success_rate.epoch.env.math": 0.9737654320987654,
      "success_rate.epoch.env.sat": 0.09375,
      "success_rate.epoch.env.science": 0.9525731584258325,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5850274844533858,
      "success_rate.epoch.global": 0.8479202772963604,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9926202623906706,
      "tokens_p.mean_below_band": 1.0089706847793423e-12,
      "tokens_p.mean_in_band": 0.7724609375,
      "tokens_rate.above_band": 0.9581005586592178,
      "tokens_rate.below_band": 0.002793296089385475,
      "tokens_rate.in_band": 0.03910614525139665
    },
    {
      "epoch": 1.463597074468085,
      "grad_norm": 81.86714619302373,
      "learning_rate": 1.6695228043005444e-07,
      "loss": 0.2204,
      "step": 8805,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.43478260869565216,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5795454545454546,
      "success_rate.epoch.env.math": 0.9737654320987654,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.9526527871054399,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5863858452167038,
      "success_rate.epoch.global": 0.8479671280276817,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9935286103542235,
      "tokens_p.mean_in_band": 0.7521484375,
      "tokens_rate.above_band": 0.9483204134366925,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05167958656330749
    },
    {
      "epoch": 1.4644281914893618,
      "grad_norm": 184.7918911546684,
      "learning_rate": 1.6693209888494674e-07,
      "loss": 0.2703,
      "step": 8810,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4396551724137931,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5795454545454546,
      "success_rate.epoch.env.math": 0.9738058551617874,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.9527321488434461,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5868396950820828,
      "success_rate.epoch.global": 0.8481969337076225,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976421734234234,
      "tokens_p.mean_in_band": 0.7494419642857143,
      "tokens_rate.above_band": 0.9844789356984479,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015521064301552107
    },
    {
      "epoch": 1.4652593085106382,
      "grad_norm": 17.43720399263593,
      "learning_rate": 1.6691194053216205e-07,
      "loss": 0.3211,
      "step": 8815,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4396551724137931,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5792452830188679,
      "success_rate.epoch.env.math": 0.9738461538461538,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.9528270324523251,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.58682469606087,
      "success_rate.epoch.global": 0.8482758620689655,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953687673130194,
      "tokens_p.mean_in_band": 0.505078125,
      "tokens_rate.above_band": 0.9601063829787234,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0398936170212766
    },
    {
      "epoch": 1.466090425531915,
      "grad_norm": 69.06664856560502,
      "learning_rate": 1.668918054074765e-07,
      "loss": 0.2096,
      "step": 8820,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4396551724137931,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.5800376647834274,
      "success_rate.epoch.env.math": 0.9738863287250384,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.9529058116232465,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.586535271671721,
      "success_rate.epoch.global": 0.8483218588640276,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9917002012072434,
      "tokens_p.mean_below_band": 6.891787052154541e-07,
      "tokens_p.mean_in_band": 0.6647329757462687,
      "tokens_rate.above_band": 0.8804251550044287,
      "tokens_rate.below_band": 0.0008857395925597874,
      "tokens_rate.in_band": 0.11868910540301152
    },
    {
      "epoch": 1.4669215425531914,
      "grad_norm": 74.35927383568033,
      "learning_rate": 1.6687169354662497e-07,
      "loss": 0.1666,
      "step": 8825,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4396551724137931,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9739263803680982,
      "success_rate.epoch.env.sat": 0.09326424870466321,
      "success_rate.epoch.env.science": 0.9529843281093698,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5864469327414308,
      "success_rate.epoch.global": 0.8483351235230935,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944362017804155,
      "tokens_p.mean_in_band": 0.673583984375,
      "tokens_rate.above_band": 0.9768115942028985,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02318840579710145
    },
    {
      "epoch": 1.467752659574468,
      "grad_norm": 139.5242283709667,
      "learning_rate": 1.6685160498530113e-07,
      "loss": 0.3972,
      "step": 8830,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.5797373358348968,
      "success_rate.epoch.env.math": 0.9739263803680982,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.9530625832223701,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.586140545692382,
      "success_rate.epoch.global": 0.8481664164700836,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9913269731136166,
      "tokens_p.mean_in_band": 0.6199721534653465,
      "tokens_rate.above_band": 0.8509225092250923,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14907749077490776
    },
    {
      "epoch": 1.4685837765957448,
      "grad_norm": 77.31867551880306,
      "learning_rate": 1.668315397591572e-07,
      "loss": 0.2762,
      "step": 8835,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.5797373358348968,
      "success_rate.epoch.env.math": 0.9739663093415007,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.953125,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5861498498515668,
      "success_rate.epoch.global": 0.8483290488431876,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960516178736518,
      "tokens_p.mean_in_band": 0.5710227272727273,
      "tokens_rate.above_band": 0.9833333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016666666666666666
    },
    {
      "epoch": 1.4694148936170213,
      "grad_norm": 74.17165133158827,
      "learning_rate": 1.6681149790380409e-07,
      "loss": 0.3561,
      "step": 8840,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45045045045045046,
      "success_rate.epoch.env.logic": 0.5805243445692884,
      "success_rate.epoch.env.math": 0.9740061162079511,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.953187250996016,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5862306740876448,
      "success_rate.epoch.global": 0.8485237483953787,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940378289473685,
      "tokens_p.mean_in_band": 0.66796875,
      "tokens_rate.above_band": 0.9470404984423676,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0529595015576324
    },
    {
      "epoch": 1.4702460106382977,
      "grad_norm": 50.42447448470959,
      "learning_rate": 1.6679147945481116e-07,
      "loss": 0.3303,
      "step": 8845,
      "success_rate.epoch.env.abd": 0.6071428571428571,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5805243445692884,
      "success_rate.epoch.env.math": 0.9740458015267176,
      "success_rate.epoch.env.sat": 0.09278350515463918,
      "success_rate.epoch.env.science": 0.9529489728296885,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858469948267867,
      "success_rate.epoch.global": 0.8483554036736437,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943889371560961,
      "tokens_p.mean_below_band": 4.9715708883013576e-08,
      "tokens_p.mean_in_band": 0.511228491902834,
      "tokens_rate.above_band": 0.8743985819194733,
      "tokens_rate.below_band": 0.0005064573309698658,
      "tokens_rate.in_band": 0.12509496074955684
    },
    {
      "epoch": 1.4710771276595744,
      "grad_norm": 100.25207053452297,
      "learning_rate": 1.6677148444770627e-07,
      "loss": 0.4462,
      "step": 8850,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5813084112149532,
      "success_rate.epoch.env.math": 0.9740458015267176,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.9529956967891426,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5839759963874266,
      "success_rate.epoch.global": 0.8481228668941979,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9969135802469136,
      "tokens_p.mean_below_band": 2.814663781060113e-07,
      "tokens_p.mean_in_band": 0.10443947885677858,
      "tokens_rate.above_band": 0.27390101444820164,
      "tokens_rate.below_band": 0.0027666769136181985,
      "tokens_rate.in_band": 0.7233323086381801
    },
    {
      "epoch": 1.4719082446808511,
      "grad_norm": 85.29556765683408,
      "learning_rate": 1.6675151291797562e-07,
      "loss": 0.3214,
      "step": 8855,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5813084112149532,
      "success_rate.epoch.env.math": 0.974124809741248,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.9530578512396695,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5839888293569773,
      "success_rate.epoch.global": 0.8483170004260758,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9974102209944752,
      "tokens_p.mean_in_band": 0.58203125,
      "tokens_rate.above_band": 0.9890710382513661,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01092896174863388
    },
    {
      "epoch": 1.4727393617021276,
      "grad_norm": 153.86705675307914,
      "learning_rate": 1.6673156490106382e-07,
      "loss": 0.4592,
      "step": 8860,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.582089552238806,
      "success_rate.epoch.env.math": 0.974124809741248,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.9531353135313532,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5840668842038442,
      "success_rate.epoch.global": 0.8485106382978723,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9980090027700831,
      "tokens_p.mean_in_band": 0.5875,
      "tokens_rate.above_band": 0.9537648612945839,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.046235138705416116
    },
    {
      "epoch": 1.4735704787234043,
      "grad_norm": 215.51987325878264,
      "learning_rate": 1.667116404323737e-07,
      "loss": 0.2616,
      "step": 8865,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.582089552238806,
      "success_rate.epoch.env.math": 0.9741641337386018,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.9531662269129287,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5840732694201104,
      "success_rate.epoch.global": 0.8486072719540718,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9868197278911565,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.4744015957446808,
      "grad_norm": 57.22878032157092,
      "learning_rate": 1.666917395472663e-07,
      "loss": 0.1699,
      "step": 8870,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5828677839851024,
      "success_rate.epoch.env.math": 0.9741641337386018,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.9532125205930807,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5841482262770603,
      "success_rate.epoch.global": 0.8487359252177608,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9923321759259259,
      "tokens_p.mean_below_band": 7.851497230149107e-13,
      "tokens_p.mean_in_band": 0.798828125,
      "tokens_rate.above_band": 0.96,
      "tokens_rate.below_band": 0.0044444444444444444,
      "tokens_rate.in_band": 0.035555555555555556
    },
    {
      "epoch": 1.4752327127659575,
      "grad_norm": 60.02260851710756,
      "learning_rate": 1.6667186228106086e-07,
      "loss": 0.328,
      "step": 8875,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5825602968460112,
      "success_rate.epoch.env.math": 0.9742813918305597,
      "success_rate.epoch.env.sat": 0.09230769230769231,
      "success_rate.epoch.env.science": 0.9532741033234616,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5841365311573555,
      "success_rate.epoch.global": 0.8488125530110263,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951230492196879,
      "tokens_p.mean_in_band": 0.621337890625,
      "tokens_rate.above_band": 0.9811542991755006,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01884570082449941
    },
    {
      "epoch": 1.476063829787234,
      "grad_norm": 27.937648557803165,
      "learning_rate": 1.666520086690346e-07,
      "loss": 0.2021,
      "step": 8880,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5833333333333334,
      "success_rate.epoch.env.math": 0.974320241691843,
      "success_rate.epoch.env.sat": 0.09693877551020408,
      "success_rate.epoch.env.science": 0.9533508541392904,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5846383239179871,
      "success_rate.epoch.global": 0.8490685859441152,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994,
      "tokens_p.mean_below_band": 2.1047890186309814e-07,
      "tokens_p.mean_in_band": 0.810546875,
      "tokens_rate.above_band": 0.9727626459143969,
      "tokens_rate.below_band": 0.0038910505836575876,
      "tokens_rate.in_band": 0.023346303501945526
    },
    {
      "epoch": 1.4768949468085106,
      "grad_norm": 53.5136228833275,
      "learning_rate": 1.6663217874642284e-07,
      "loss": 0.1454,
      "step": 8885,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5833333333333334,
      "success_rate.epoch.env.math": 0.9743589743589743,
      "success_rate.epoch.env.sat": 0.10152284263959391,
      "success_rate.epoch.env.science": 0.9534273532305674,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5850655329077868,
      "success_rate.epoch.global": 0.8492919044599451,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9915865384615384,
      "tokens_p.mean_in_band": 0.72265625,
      "tokens_rate.above_band": 0.9891304347826086,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010869565217391304
    },
    {
      "epoch": 1.4777260638297873,
      "grad_norm": 174.38402611895302,
      "learning_rate": 1.6661237254841885e-07,
      "loss": 0.219,
      "step": 8890,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5833333333333334,
      "success_rate.epoch.env.math": 0.9743589743589743,
      "success_rate.epoch.env.sat": 0.10152284263959391,
      "success_rate.epoch.env.science": 0.953222113182859,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5850468747216315,
      "success_rate.epoch.global": 0.8493353028064993,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9877083333333333,
      "tokens_p.mean_below_band": 6.845220923423767e-08,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.9803921568627451,
      "tokens_rate.below_band": 0.006535947712418301,
      "tokens_rate.in_band": 0.013071895424836602
    },
    {
      "epoch": 1.4785571808510638,
      "grad_norm": 159.8681528008941,
      "learning_rate": 1.6659259011017374e-07,
      "loss": 0.4327,
      "step": 8895,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4358974358974359,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5833333333333334,
      "success_rate.epoch.env.math": 0.9743589743589743,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.9533137446947437,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5854677288064404,
      "success_rate.epoch.global": 0.8495575221238938,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972789115646259,
      "tokens_p.mean_in_band": 0.6131628787878788,
      "tokens_rate.above_band": 0.95703125,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04296875
    },
    {
      "epoch": 1.4793882978723405,
      "grad_norm": 115.93399448210958,
      "learning_rate": 1.6657283146679654e-07,
      "loss": 0.3512,
      "step": 8900,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5830258302583026,
      "success_rate.epoch.env.math": 0.9743975903614458,
      "success_rate.epoch.env.sat": 0.10552763819095477,
      "success_rate.epoch.env.science": 0.9533594259621657,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858335794000286,
      "success_rate.epoch.global": 0.8493899873790492,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9959577114427861,
      "tokens_p.mean_in_band": 0.5632267441860465,
      "tokens_rate.above_band": 0.9655724579663731,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0344275420336269
    },
    {
      "epoch": 1.480219414893617,
      "grad_norm": 60.08968730788985,
      "learning_rate": 1.66553096653354e-07,
      "loss": 0.2483,
      "step": 8905,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5845588235294118,
      "success_rate.epoch.env.math": 0.9743975903614458,
      "success_rate.epoch.env.sat": 0.10552763819095477,
      "success_rate.epoch.env.science": 0.9530791788856305,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5859474654177171,
      "success_rate.epoch.global": 0.8493380962387056,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5166666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9963855421686747,
      "tokens_p.mean_below_band": 2.8405338525772095e-08,
      "tokens_p.mean_in_band": 0.6160300925925926,
      "tokens_rate.above_band": 0.9673659673659674,
      "tokens_rate.below_band": 0.0011655011655011655,
      "tokens_rate.in_band": 0.03146853146853147
    },
    {
      "epoch": 1.4810505319148937,
      "grad_norm": 102.70127530710973,
      "learning_rate": 1.6653338570487053e-07,
      "loss": 0.28,
      "step": 8910,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9744360902255639,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9531554977228367,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858124286461778,
      "success_rate.epoch.global": 0.8491713866163205,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9927014802631579,
      "tokens_p.mean_in_band": 0.7341432733050848,
      "tokens_rate.above_band": 0.9115442278860569,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08845577211394302
    },
    {
      "epoch": 1.4818816489361701,
      "grad_norm": 71.41499388757578,
      "learning_rate": 1.6651369865632824e-07,
      "loss": 0.2772,
      "step": 8915,
      "success_rate.epoch.env.abd": 0.5862068965517241,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9744744744744744,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9532467532467532,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5858242140800712,
      "success_rate.epoch.global": 0.84939254294093,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954315707620529,
      "tokens_p.mean_in_band": 0.6552734375,
      "tokens_rate.above_band": 0.981679389312977,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0183206106870229
    },
    {
      "epoch": 1.4827127659574468,
      "grad_norm": 421.47318922803146,
      "learning_rate": 1.6649403554266688e-07,
      "loss": 0.4243,
      "step": 8920,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9745508982035929,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9532922478105741,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5840589130262424,
      "success_rate.epoch.global": 0.8493723849372385,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9929022082018928,
      "tokens_p.mean_in_band": 0.20500444231820666,
      "tokens_rate.above_band": 0.5097829000268025,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.4902170999731975
    },
    {
      "epoch": 1.4835438829787235,
      "grad_norm": 82.65505652781167,
      "learning_rate": 1.6647439639878363e-07,
      "loss": 0.2155,
      "step": 8925,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9745889387144993,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.953307392996109,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5840637480895551,
      "success_rate.epoch.global": 0.849435382685069,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9894957983193278,
      "tokens_p.mean_below_band": 1.0277290130034089e-10,
      "tokens_rate.above_band": 0.9916666666666667,
      "tokens_rate.below_band": 0.008333333333333333,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.484375,
      "grad_norm": 119.68829124966119,
      "learning_rate": 1.664547812595331e-07,
      "loss": 0.2534,
      "step": 8930,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.44642857142857145,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9745889387144993,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9533980582524272,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5840719903855841,
      "success_rate.epoch.global": 0.849624060150376,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9906015037593985,
      "tokens_p.mean_in_band": 0.79296875,
      "tokens_rate.above_band": 0.9925373134328358,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007462686567164179
    },
    {
      "epoch": 1.4852061170212765,
      "grad_norm": 60.19511614034739,
      "learning_rate": 1.6643519015972743e-07,
      "loss": 0.2971,
      "step": 8935,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9746268656716418,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.953443258971872,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.583720393326876,
      "success_rate.epoch.global": 0.8495722929271855,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9886431116389549,
      "tokens_p.mean_in_band": 0.6542632004310345,
      "tokens_rate.above_band": 0.8789144050104384,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12108559498956159
    },
    {
      "epoch": 1.4860372340425532,
      "grad_norm": 11.759328224689535,
      "learning_rate": 1.6641562313413601e-07,
      "loss": 0.2086,
      "step": 8940,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.5834862385321101,
      "success_rate.epoch.env.math": 0.9731743666169895,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9535333978702807,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.583596542403581,
      "success_rate.epoch.global": 0.8495833333333334,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9944672131147541,
      "tokens_p.mean_below_band": 8.451752364635468e-08,
      "tokens_p.mean_in_band": 0.6826923076923077,
      "tokens_rate.above_band": 0.953125,
      "tokens_rate.below_band": 0.00625,
      "tokens_rate.in_band": 0.040625
    },
    {
      "epoch": 1.4868683510638299,
      "grad_norm": 31.196475492201976,
      "learning_rate": 1.6639608021748553e-07,
      "loss": 0.2216,
      "step": 8945,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.5842490842490843,
      "success_rate.epoch.env.math": 0.9731743666169895,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9536082474226805,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5836726965189787,
      "success_rate.epoch.global": 0.8497711194340408,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9858606557377049,
      "tokens_p.mean_in_band": 0.7458333333333333,
      "tokens_rate.above_band": 0.8714285714285714,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12857142857142856
    },
    {
      "epoch": 1.4876994680851063,
      "grad_norm": 141.03161486347423,
      "learning_rate": 1.6637656144445982e-07,
      "loss": 0.2986,
      "step": 8950,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.5850091407678245,
      "success_rate.epoch.env.math": 0.9731743666169895,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9536977491961415,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.583749929090997,
      "success_rate.epoch.global": 0.8499896114689383,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9947683109118086,
      "tokens_p.mean_in_band": 0.583984375,
      "tokens_rate.above_band": 0.9911111111111112,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008888888888888889
    },
    {
      "epoch": 1.488530585106383,
      "grad_norm": 93.43635198484678,
      "learning_rate": 1.6635706684969995e-07,
      "loss": 0.3848,
      "step": 8955,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.9732540861812778,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9537126325940212,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5836614807304297,
      "success_rate.epoch.global": 0.8499065808594561,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.996875,
      "tokens_p.mean_in_band": 0.6641773897058824,
      "tokens_rate.above_band": 0.9549071618037135,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04509283819628647
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 172.266641715584,
      "learning_rate": 1.6633759646780405e-07,
      "loss": 0.2493,
      "step": 8960,
      "success_rate.epoch.env.abd": 0.5666666666666667,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4424778761061947,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.973293768545994,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9537869062901155,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5836718403723216,
      "success_rate.epoch.global": 0.8500933029234916,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9901785714285715,
      "tokens_p.mean_in_band": 0.83203125,
      "tokens_rate.above_band": 0.9929078014184397,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0070921985815602835
    },
    {
      "epoch": 1.4901928191489362,
      "grad_norm": 284.3213629765886,
      "learning_rate": 1.663181503333273e-07,
      "loss": 0.4245,
      "step": 8965,
      "success_rate.epoch.env.abd": 0.5483870967741935,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.43859649122807015,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.9733333333333334,
      "success_rate.epoch.env.sat": 0.105,
      "success_rate.epoch.env.science": 0.9538313562039115,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5816648458205522,
      "success_rate.epoch.global": 0.8498653965624353,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9939673157162726,
      "tokens_p.mean_below_band": 2.9193082203467685e-07,
      "tokens_p.mean_in_band": 0.3298333845208845,
      "tokens_rate.above_band": 0.8148232094288305,
      "tokens_rate.below_band": 0.0006799637352674524,
      "tokens_rate.in_band": 0.18449682683590207
    },
    {
      "epoch": 1.4910239361702127,
      "grad_norm": 36.14850784228584,
      "learning_rate": 1.6629872848078182e-07,
      "loss": 0.2204,
      "step": 8970,
      "success_rate.epoch.env.abd": 0.5483870967741935,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4434782608695652,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.9733333333333334,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.9535851472471191,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5824910546390168,
      "success_rate.epoch.global": 0.8498759305210918,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947320680993581,
      "tokens_p.mean_below_band": 4.1574821807444096e-07,
      "tokens_p.mean_in_band": 0.5336565290178571,
      "tokens_rate.above_band": 0.8884205306223655,
      "tokens_rate.below_band": 0.0004959087527894868,
      "tokens_rate.in_band": 0.11108356062484503
    },
    {
      "epoch": 1.4918550531914894,
      "grad_norm": 69.67409498344419,
      "learning_rate": 1.662793309446366e-07,
      "loss": 0.339,
      "step": 8975,
      "success_rate.epoch.env.abd": 0.5483870967741935,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.9733333333333334,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.9533098816757275,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5829021760597449,
      "success_rate.epoch.global": 0.849793388429752,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.76,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943860619469026,
      "tokens_p.mean_below_band": 3.9301812648773193e-07,
      "tokens_p.mean_in_band": 0.8189290364583334,
      "tokens_rate.above_band": 0.9584393553859203,
      "tokens_rate.below_band": 0.0008481764206955047,
      "tokens_rate.in_band": 0.04071246819338423
    },
    {
      "epoch": 1.492686170212766,
      "grad_norm": 25.172341789178848,
      "learning_rate": 1.6625995775931753e-07,
      "loss": 0.4,
      "step": 8980,
      "success_rate.epoch.env.abd": 0.5483870967741935,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.9734121122599705,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.9533397251518057,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5829120508236282,
      "success_rate.epoch.global": 0.8499174236168456,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9994762569832403,
      "tokens_p.mean_in_band": 0.7009943181818182,
      "tokens_rate.above_band": 0.984869325997249,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015130674002751032
    },
    {
      "epoch": 1.4935172872340425,
      "grad_norm": 101.60215212174798,
      "learning_rate": 1.6624060895920731e-07,
      "loss": 0.158,
      "step": 8985,
      "success_rate.epoch.env.abd": 0.5483870967741935,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.583941605839416,
      "success_rate.epoch.env.math": 0.9734904270986745,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.9533844189016603,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5829232334225879,
      "success_rate.epoch.global": 0.850072179830893,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9982289042821159,
      "tokens_p.mean_in_band": 0.7236689814814815,
      "tokens_rate.above_band": 0.9932449337002752,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006755066299724793
    },
    {
      "epoch": 1.4943484042553192,
      "grad_norm": 44.46585791465407,
      "learning_rate": 1.6622128457864528e-07,
      "loss": 0.2366,
      "step": 8990,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4482758620689655,
      "success_rate.epoch.env.logic": 0.5836363636363636,
      "success_rate.epoch.env.math": 0.9736070381231672,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.9533992977976381,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5841904289628812,
      "success_rate.epoch.global": 0.8500823723228995,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9988344988344988,
      "tokens_p.mean_in_band": 0.6252170138888888,
      "tokens_rate.above_band": 0.9794520547945206,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02054794520547945
    },
    {
      "epoch": 1.4951795212765957,
      "grad_norm": 55.129395867056154,
      "learning_rate": 1.662019846519275e-07,
      "loss": 0.2492,
      "step": 8995,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.452991452991453,
      "success_rate.epoch.env.logic": 0.5836363636363636,
      "success_rate.epoch.env.math": 0.9736070381231672,
      "success_rate.epoch.env.sat": 0.10945273631840796,
      "success_rate.epoch.env.science": 0.9535031847133758,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5846285633118108,
      "success_rate.epoch.global": 0.850328947368421,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949245939675174,
      "tokens_p.mean_in_band": 0.61767578125,
      "tokens_rate.above_band": 0.9642058165548099,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.035794183445190156
    },
    {
      "epoch": 1.4960106382978724,
      "grad_norm": 121.23035664122499,
      "learning_rate": 1.661827092133066e-07,
      "loss": 0.3351,
      "step": 9000,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4491525423728814,
      "success_rate.epoch.env.logic": 0.5836363636363636,
      "success_rate.epoch.env.math": 0.9736070381231672,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9535475660197263,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5842343474443997,
      "success_rate.epoch.global": 0.8500718833436024,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9883373205741627,
      "tokens_p.mean_in_band": 0.6793653350515464,
      "tokens_rate.above_band": 0.8660220994475138,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13397790055248618
    },
    {
      "epoch": 1.4968417553191489,
      "grad_norm": 52.31826487450914,
      "learning_rate": 1.6616345829699175e-07,
      "loss": 0.3332,
      "step": 9005,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.4,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4491525423728814,
      "success_rate.epoch.env.logic": 0.5851449275362319,
      "success_rate.epoch.env.math": 0.9736456808199122,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9536066094693358,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5843803701758745,
      "success_rate.epoch.global": 0.850287120590648,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971955128205128,
      "tokens_p.mean_below_band": 4.0605664253234863e-07,
      "tokens_p.mean_in_band": 0.15475751768867924,
      "tokens_rate.above_band": 0.7455197132616488,
      "tokens_rate.below_band": 0.0011947431302270011,
      "tokens_rate.in_band": 0.2532855436081243
    },
    {
      "epoch": 1.4976728723404256,
      "grad_norm": 65.10165148066402,
      "learning_rate": 1.6614423193714862e-07,
      "loss": 0.2413,
      "step": 9010,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4406779661016949,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.5858951175406871,
      "success_rate.epoch.env.math": 0.9736456808199122,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9536507936507936,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5943781124619077,
      "success_rate.epoch.global": 0.8505017407331559,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972230913642053,
      "tokens_p.mean_in_band": 0.43419989224137934,
      "tokens_rate.above_band": 0.9821757836508912,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01782421634910879
    },
    {
      "epoch": 1.4985039893617023,
      "grad_norm": 54.229177669455524,
      "learning_rate": 1.6612503016789928e-07,
      "loss": 0.4671,
      "step": 9015,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.5866425992779783,
      "success_rate.epoch.env.math": 0.9736456808199122,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9536948937519822,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013708705006223,
      "success_rate.epoch.global": 0.8506852116997341,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.9642857142857143,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972718253968254,
      "tokens_p.mean_below_band": 4.172325134277344e-07,
      "tokens_p.mean_in_band": 0.609375,
      "tokens_rate.above_band": 0.9940828402366864,
      "tokens_rate.below_band": 0.0019723865877712033,
      "tokens_rate.in_band": 0.0039447731755424065
    },
    {
      "epoch": 1.4993351063829787,
      "grad_norm": 42.83299544093687,
      "learning_rate": 1.6610585302332222e-07,
      "loss": 0.1372,
      "step": 9020,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.5866425992779783,
      "success_rate.epoch.env.math": 0.9736456808199122,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.9537682077264091,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013287620571469,
      "success_rate.epoch.global": 0.8506639427987742,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9922542735042735,
      "tokens_p.mean_below_band": 5.893525667488575e-10,
      "tokens_p.mean_in_band": 0.7458767361111112,
      "tokens_rate.above_band": 0.924901185770751,
      "tokens_rate.below_band": 0.003952569169960474,
      "tokens_rate.in_band": 0.07114624505928854
    },
    {
      "epoch": 1.5001662234042552,
      "grad_norm": 64.11192445922434,
      "learning_rate": 1.6608670053745211e-07,
      "loss": 0.2851,
      "step": 9025,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.5863309352517986,
      "success_rate.epoch.env.math": 0.9737226277372263,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.9535251343661081,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.60128532655995,
      "success_rate.epoch.global": 0.8505301794453507,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963908450704225,
      "tokens_p.mean_in_band": 0.5990032327586207,
      "tokens_rate.above_band": 0.9607577807848444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03924221921515562
    },
    {
      "epoch": 1.500997340425532,
      "grad_norm": 100.63425747748076,
      "learning_rate": 1.6606757274427995e-07,
      "loss": 0.3297,
      "step": 9030,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.5863309352517986,
      "success_rate.epoch.env.math": 0.9737609329446064,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.9532680770445217,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601265440004113,
      "success_rate.epoch.global": 0.8504787125687513,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9931264172335601,
      "tokens_p.mean_in_band": 0.7089146205357143,
      "tokens_rate.above_band": 0.9402985074626866,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05970149253731343
    },
    {
      "epoch": 1.5018284574468086,
      "grad_norm": 33.79839899285133,
      "learning_rate": 1.6604846967775284e-07,
      "loss": 0.2661,
      "step": 9035,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4583333333333333,
      "success_rate.epoch.env.logic": 0.5870736086175943,
      "success_rate.epoch.env.math": 0.9738372093023255,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.9533270261747083,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013452489908132,
      "success_rate.epoch.global": 0.8506916192026037,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9961705748865356,
      "tokens_p.mean_below_band": 6.693881005048752e-10,
      "tokens_p.mean_in_band": 0.7421875,
      "tokens_rate.above_band": 0.9836309523809523,
      "tokens_rate.below_band": 0.001488095238095238,
      "tokens_rate.in_band": 0.01488095238095238
    },
    {
      "epoch": 1.502659574468085,
      "grad_norm": 115.80812163572587,
      "learning_rate": 1.6602939137177414e-07,
      "loss": 0.2782,
      "step": 9040,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5870736086175943,
      "success_rate.epoch.env.math": 0.9738372093023255,
      "success_rate.epoch.env.sat": 0.10837438423645321,
      "success_rate.epoch.env.science": 0.9534151715454832,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6017602243901599,
      "success_rate.epoch.global": 0.8509039203737558,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9934463562753036,
      "tokens_p.mean_in_band": 0.715625,
      "tokens_rate.above_band": 0.96484375,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03515625
    },
    {
      "epoch": 1.5034906914893615,
      "grad_norm": 35.25153601091879,
      "learning_rate": 1.6601033786020309e-07,
      "loss": 0.3294,
      "step": 9045,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44537815126050423,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5857142857142857,
      "success_rate.epoch.env.math": 0.9738751814223512,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9534591194968554,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601595801679845,
      "success_rate.epoch.global": 0.8505374163455689,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976694065757818,
      "tokens_p.mean_in_band": 0.5175304878048781,
      "tokens_rate.above_band": 0.968167701863354,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03183229813664596
    },
    {
      "epoch": 1.5043218085106385,
      "grad_norm": 65.40337430793437,
      "learning_rate": 1.65991309176855e-07,
      "loss": 0.2708,
      "step": 9050,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44166666666666665,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5857142857142857,
      "success_rate.epoch.env.math": 0.9739507959479016,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9535175879396985,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6012705833502593,
      "success_rate.epoch.global": 0.850546780072904,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949392712550608,
      "tokens_p.mean_in_band": 0.73046875,
      "tokens_rate.above_band": 0.993963782696177,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006036217303822937
    },
    {
      "epoch": 1.505152925531915,
      "grad_norm": 21.08796151853228,
      "learning_rate": 1.6597230535550118e-07,
      "loss": 0.4217,
      "step": 9055,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.44166666666666665,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5846702317290553,
      "success_rate.epoch.env.math": 0.9739507959479016,
      "success_rate.epoch.env.sat": 0.1073170731707317,
      "success_rate.epoch.env.science": 0.953590467231107,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6011344707340782,
      "success_rate.epoch.global": 0.8503538928210314,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9940131578947369,
      "tokens_p.mean_in_band": 0.7018229166666666,
      "tokens_rate.above_band": 0.9547738693467337,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04522613065326633
    },
    {
      "epoch": 1.5059840425531914,
      "grad_norm": 41.1613974825275,
      "learning_rate": 1.659533264298687e-07,
      "loss": 0.1876,
      "step": 9060,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4462809917355372,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5846702317290553,
      "success_rate.epoch.env.math": 0.9739507959479016,
      "success_rate.epoch.env.sat": 0.1073170731707317,
      "success_rate.epoch.env.science": 0.9536921151439299,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015631955505957,
      "success_rate.epoch.global": 0.8505955986270947,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9965175953079178,
      "tokens_p.mean_in_band": 0.7786458333333334,
      "tokens_rate.above_band": 0.9912790697674418,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00872093023255814
    },
    {
      "epoch": 1.506815159574468,
      "grad_norm": 31.719517489764847,
      "learning_rate": 1.6593437243364054e-07,
      "loss": 0.2026,
      "step": 9065,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4462809917355372,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5854092526690391,
      "success_rate.epoch.env.math": 0.9739507959479016,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9537788881948782,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015909080346916,
      "success_rate.epoch.global": 0.850634952630518,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9899475524475524,
      "tokens_p.mean_in_band": 0.7780172413793104,
      "tokens_rate.above_band": 0.9079365079365079,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09206349206349207
    },
    {
      "epoch": 1.5076462765957448,
      "grad_norm": 137.53736810330713,
      "learning_rate": 1.659154434004554e-07,
      "loss": 0.217,
      "step": 9070,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4462809917355372,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.45454545454545453,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5865724381625441,
      "success_rate.epoch.env.math": 0.9739507959479016,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9538365564566438,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6017018947397162,
      "success_rate.epoch.global": 0.850674179915476,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951338199513382,
      "tokens_p.mean_in_band": 0.6711956521739131,
      "tokens_rate.above_band": 0.9727810650887574,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027218934911242602
    },
    {
      "epoch": 1.5084773936170213,
      "grad_norm": 50.05467060219551,
      "learning_rate": 1.6589653936390763e-07,
      "loss": 0.2862,
      "step": 9075,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4462809917355372,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4628099173553719,
      "success_rate.epoch.env.logic": 0.5855379188712522,
      "success_rate.epoch.env.math": 0.9739884393063584,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9538797133063259,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5981716668340852,
      "success_rate.epoch.global": 0.8504522613065326,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9958722014925373,
      "tokens_p.mean_in_band": 0.6336096938775511,
      "tokens_rate.above_band": 0.9318497913769124,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06815020862308763
    },
    {
      "epoch": 1.5093085106382977,
      "grad_norm": 63.026998770336384,
      "learning_rate": 1.6587766035754733e-07,
      "loss": 0.4296,
      "step": 9080,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4426229508196721,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5855379188712522,
      "success_rate.epoch.env.math": 0.9739884393063584,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9536403235843186,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5974724891476652,
      "success_rate.epoch.global": 0.8500602167804094,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.2857142857142857,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9911995515695067,
      "tokens_p.mean_below_band": 6.07222318649292e-07,
      "tokens_p.mean_in_band": 0.5039415049638989,
      "tokens_rate.above_band": 0.8004307250538406,
      "tokens_rate.below_band": 0.0007178750897343862,
      "tokens_rate.in_band": 0.19885139985642497
    },
    {
      "epoch": 1.5101396276595744,
      "grad_norm": 38.18815544643185,
      "learning_rate": 1.6585880641488006e-07,
      "loss": 0.2506,
      "step": 9085,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4426229508196721,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5855379188712522,
      "success_rate.epoch.env.math": 0.9739884393063584,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9537267080745342,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5974803422831393,
      "success_rate.epoch.global": 0.8502405773857258,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9832589285714286,
      "tokens_p.mean_in_band": 0.8984375,
      "tokens_rate.above_band": 0.9940828402366864,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005917159763313609
    },
    {
      "epoch": 1.5109707446808511,
      "grad_norm": 111.98814150925904,
      "learning_rate": 1.6583997756936697e-07,
      "loss": 0.4014,
      "step": 9090,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4426229508196721,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5845070422535211,
      "success_rate.epoch.env.math": 0.974025974025974,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9538270839789278,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5973991635564372,
      "success_rate.epoch.global": 0.850310186111667,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976035276073619,
      "tokens_p.mean_in_band": 0.6294642857142857,
      "tokens_rate.above_band": 0.9893778452200304,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010622154779969651
    },
    {
      "epoch": 1.5118018617021276,
      "grad_norm": 149.57921447423726,
      "learning_rate": 1.6582117385442466e-07,
      "loss": 0.2177,
      "step": 9095,
      "success_rate.epoch.env.abd": 0.5625,
      "success_rate.epoch.env.agentgym:alfworld": 0.4426229508196721,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5845070422535211,
      "success_rate.epoch.env.math": 0.974025974025974,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9535891089108911,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.597377529459343,
      "success_rate.epoch.global": 0.8502598960415834,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9942484662576687,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.7103365384615384,
      "tokens_rate.above_band": 0.978978978978979,
      "tokens_rate.below_band": 0.0015015015015015015,
      "tokens_rate.in_band": 0.01951951951951952
    },
    {
      "epoch": 1.5126329787234043,
      "grad_norm": 32.09828574613877,
      "learning_rate": 1.658023953034251e-07,
      "loss": 0.159,
      "step": 9100,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.44715447154471544,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5845070422535211,
      "success_rate.epoch.env.math": 0.974025974025974,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.953646477132262,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5962451144048848,
      "success_rate.epoch.global": 0.8502396166134185,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9865314769975787,
      "tokens_p.mean_in_band": 0.740234375,
      "tokens_rate.above_band": 0.8694736842105263,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13052631578947368
    },
    {
      "epoch": 1.513464095744681,
      "grad_norm": 19.48703555281662,
      "learning_rate": 1.657836419496956e-07,
      "loss": 0.2382,
      "step": 9105,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.44715447154471544,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5845070422535211,
      "success_rate.epoch.env.math": 0.9741007194244604,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9537322640345466,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5962597082504094,
      "success_rate.epoch.global": 0.8504784688995215,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9967447916666666,
      "tokens_p.mean_in_band": 0.4375,
      "tokens_rate.above_band": 0.9970326409495549,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.002967359050445104
    },
    {
      "epoch": 1.5142952127659575,
      "grad_norm": 33.742789360988446,
      "learning_rate": 1.6576491382651882e-07,
      "loss": 0.1538,
      "step": 9110,
      "success_rate.epoch.env.abd": 0.5454545454545454,
      "success_rate.epoch.env.agentgym:alfworld": 0.44715447154471544,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5852372583479789,
      "success_rate.epoch.env.math": 0.9741750358680057,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9537750385208013,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5963367361617057,
      "success_rate.epoch.global": 0.8506571087216248,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9995375264270613,
      "tokens_p.mean_in_band": 0.72998046875,
      "tokens_rate.above_band": 0.9916142557651991,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008385744234800839
    },
    {
      "epoch": 1.515126329787234,
      "grad_norm": 112.96616817973512,
      "learning_rate": 1.6574621096713256e-07,
      "loss": 0.3221,
      "step": 9115,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.44715447154471544,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5852372583479789,
      "success_rate.epoch.env.math": 0.9741750358680057,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9538177339901478,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5975559797459389,
      "success_rate.epoch.global": 0.8507759649820931,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9642857142857143,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.98861646234676,
      "tokens_p.mean_in_band": 0.75,
      "tokens_rate.above_band": 0.964527027027027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03547297297297297
    },
    {
      "epoch": 1.5159574468085106,
      "grad_norm": 67.7413967926489,
      "learning_rate": 1.6572753340472977e-07,
      "loss": 0.266,
      "step": 9120,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.44715447154471544,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5852372583479789,
      "success_rate.epoch.env.math": 0.9742120343839542,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9538745387453874,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5975645073160469,
      "success_rate.epoch.global": 0.8509242695289206,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9902137367915466,
      "tokens_p.mean_in_band": 0.48442055393586003,
      "tokens_rate.above_band": 0.7521676300578035,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.24783236994219654
    },
    {
      "epoch": 1.5167885638297873,
      "grad_norm": 56.2153090918143,
      "learning_rate": 1.6570888117245864e-07,
      "loss": 0.3855,
      "step": 9125,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5842105263157895,
      "success_rate.epoch.env.math": 0.9742857142857143,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9539028887523049,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.597885755457645,
      "success_rate.epoch.global": 0.8509033154655549,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9980926188786373,
      "tokens_p.mean_in_band": 0.6264204545454546,
      "tokens_rate.above_band": 0.9846261355695318,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015373864430468204
    },
    {
      "epoch": 1.5176196808510638,
      "grad_norm": 106.0890985976148,
      "learning_rate": 1.6569025430342223e-07,
      "loss": 0.1821,
      "step": 9130,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5831873905429071,
      "success_rate.epoch.env.math": 0.9742857142857143,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9539453484801965,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977966030899186,
      "success_rate.epoch.global": 0.8508232493552866,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967866323907455,
      "tokens_p.mean_in_band": 0.7315244932432432,
      "tokens_rate.above_band": 0.9546012269938651,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04539877300613497
    },
    {
      "epoch": 1.5184507978723403,
      "grad_norm": 134.16236693681458,
      "learning_rate": 1.656716528306787e-07,
      "loss": 0.2763,
      "step": 9135,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5831873905429071,
      "success_rate.epoch.env.math": 0.9743223965763196,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9540300337113086,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978076365009838,
      "success_rate.epoch.global": 0.8510301109350238,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976580796252927,
      "tokens_p.mean_in_band": 0.5834173387096774,
      "tokens_rate.above_band": 0.9649717514124294,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03502824858757062
    },
    {
      "epoch": 1.519281914893617,
      "grad_norm": 61.672083929726746,
      "learning_rate": 1.6565307678724115e-07,
      "loss": 0.2687,
      "step": 9140,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5831873905429071,
      "success_rate.epoch.env.math": 0.9743589743589743,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9540863177226814,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978160784822589,
      "success_rate.epoch.global": 0.8511775183059569,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9928909952606635,
      "tokens_p.mean_in_band": 0.46875,
      "tokens_rate.above_band": 0.9952830188679245,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0047169811320754715
    },
    {
      "epoch": 1.5201130319148937,
      "grad_norm": 44.872902430958916,
      "learning_rate": 1.6563452620607744e-07,
      "loss": 0.2294,
      "step": 9145,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5828970331588132,
      "success_rate.epoch.env.math": 0.9743589743589743,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9541424640782635,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977947865705762,
      "success_rate.epoch.global": 0.8511563550108717,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9999075443786982,
      "tokens_p.mean_in_band": 0.5841346153846154,
      "tokens_rate.above_band": 0.9811320754716981,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018867924528301886
    },
    {
      "epoch": 1.5209441489361701,
      "grad_norm": 9.310281083891633,
      "learning_rate": 1.6561600112011033e-07,
      "loss": 0.2573,
      "step": 9150,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5836236933797909,
      "success_rate.epoch.env.math": 0.9743954480796586,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9539212694537686,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978440537812276,
      "success_rate.epoch.global": 0.8511940003947108,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9925426136363636,
      "tokens_p.mean_in_band": 0.486328125,
      "tokens_rate.above_band": 0.9887640449438202,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011235955056179775
    },
    {
      "epoch": 1.5217752659574468,
      "grad_norm": 31.75486191419853,
      "learning_rate": 1.655975015622173e-07,
      "loss": 0.277,
      "step": 9155,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5836236933797909,
      "success_rate.epoch.env.math": 0.9744680851063829,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9539914686166971,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978570388893779,
      "success_rate.epoch.global": 0.8513992905005913,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9876838235294118,
      "tokens_p.mean_in_band": 0.826171875,
      "tokens_rate.above_band": 0.9770114942528736,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022988505747126436
    },
    {
      "epoch": 1.5226063829787235,
      "grad_norm": 67.05705649845474,
      "learning_rate": 1.6557902756523056e-07,
      "loss": 0.1623,
      "step": 9160,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5836236933797909,
      "success_rate.epoch.env.math": 0.9745042492917847,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9540334855403348,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978641462629269,
      "success_rate.epoch.global": 0.8515163450177236,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9951652601969058,
      "tokens_p.mean_in_band": 0.746875,
      "tokens_rate.above_band": 0.9930167597765364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006983240223463687
    },
    {
      "epoch": 1.5234375,
      "grad_norm": 104.59529823614973,
      "learning_rate": 1.6556057916193691e-07,
      "loss": 0.2262,
      "step": 9165,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5843478260869566,
      "success_rate.epoch.env.math": 0.9745403111739745,
      "success_rate.epoch.env.sat": 0.10628019323671498,
      "success_rate.epoch.env.science": 0.9540893888719976,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978914348677341,
      "success_rate.epoch.global": 0.8515240904621436,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9925699300699301,
      "tokens_p.mean_in_band": 0.7215909090909091,
      "tokens_rate.above_band": 0.9285714285714286,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07142857142857142
    },
    {
      "epoch": 1.5242686170212765,
      "grad_norm": 223.77072129465301,
      "learning_rate": 1.6554215638507775e-07,
      "loss": 0.4399,
      "step": 9170,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.58578856152513,
      "success_rate.epoch.env.math": 0.9745762711864406,
      "success_rate.epoch.env.sat": 0.10628019323671498,
      "success_rate.epoch.env.science": 0.9541451563923474,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977023039354781,
      "success_rate.epoch.global": 0.8515609660318084,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9969117647058824,
      "tokens_p.mean_in_band": 0.6912977430555556,
      "tokens_rate.above_band": 0.9593679458239278,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040632054176072234
    },
    {
      "epoch": 1.5250997340425532,
      "grad_norm": 48.50251024765517,
      "learning_rate": 1.65523759267349e-07,
      "loss": 0.1936,
      "step": 9175,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.58578856152513,
      "success_rate.epoch.env.math": 0.9745762711864406,
      "success_rate.epoch.env.sat": 0.10628019323671498,
      "success_rate.epoch.env.science": 0.9542285541073052,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977098855459287,
      "success_rate.epoch.global": 0.8517356344381252,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99406400550585,
      "tokens_p.mean_in_band": 0.744194380733945,
      "tokens_rate.above_band": 0.9302176696542894,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06978233034571063
    },
    {
      "epoch": 1.5259308510638299,
      "grad_norm": 114.72551124621418,
      "learning_rate": 1.6550538784140102e-07,
      "loss": 0.2429,
      "step": 9180,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5865051903114187,
      "success_rate.epoch.env.math": 0.9746121297602257,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9542701393095094,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5976896162023196,
      "success_rate.epoch.global": 0.8515471993732864,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9935453400503779,
      "tokens_p.mean_in_band": 0.25830639367816094,
      "tokens_rate.above_band": 0.5328859060402684,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.4671140939597315
    },
    {
      "epoch": 1.5267619680851063,
      "grad_norm": 46.47264155746653,
      "learning_rate": 1.6548704213983863e-07,
      "loss": 0.3098,
      "step": 9185,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5854922279792746,
      "success_rate.epoch.env.math": 0.9746835443037974,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9543254688445251,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5976090509065417,
      "success_rate.epoch.global": 0.8515548601603755,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930555555555556,
      "tokens_p.mean_in_band": 0.6058799342105263,
      "tokens_rate.above_band": 0.9722627737226277,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027737226277372264
    },
    {
      "epoch": 1.527593085106383,
      "grad_norm": 56.0322737807118,
      "learning_rate": 1.654687221952209e-07,
      "loss": 0.258,
      "step": 9190,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5862068965517241,
      "success_rate.epoch.env.math": 0.9747545582047685,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.954380664652568,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5976854943866748,
      "success_rate.epoch.global": 0.8517578125,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.9333333333333332,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953703703703703,
      "tokens_p.mean_below_band": 8.003553375601768e-11,
      "tokens_rate.above_band": 0.9953917050691244,
      "tokens_rate.below_band": 0.004608294930875576,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.5284242021276597,
      "grad_norm": 85.32311690231185,
      "learning_rate": 1.6545042804006128e-07,
      "loss": 0.3552,
      "step": 9195,
      "success_rate.epoch.env.abd": 0.5588235294117647,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.584192439862543,
      "success_rate.epoch.env.math": 0.9747545582047685,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9544219740416541,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5975061173593934,
      "success_rate.epoch.global": 0.8515121951219512,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4666666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9958076923076923,
      "tokens_p.mean_in_band": 0.6093532986111111,
      "tokens_rate.above_band": 0.9475218658892128,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.052478134110787174
    },
    {
      "epoch": 1.5292553191489362,
      "grad_norm": 23.578310643582856,
      "learning_rate": 1.654321597068274e-07,
      "loss": 0.3208,
      "step": 9200,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5831903945111492,
      "success_rate.epoch.env.math": 0.9747899159663865,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9544769369912571,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985691462118147,
      "success_rate.epoch.global": 0.8515198752922837,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9975573491928632,
      "tokens_p.mean_in_band": 0.58125,
      "tokens_rate.above_band": 0.9874161073825504,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012583892617449664
    },
    {
      "epoch": 1.5300864361702127,
      "grad_norm": 219.26967171274,
      "learning_rate": 1.6541391722794108e-07,
      "loss": 0.3675,
      "step": 9205,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.582905982905983,
      "success_rate.epoch.env.math": 0.9747899159663865,
      "success_rate.epoch.env.sat": 0.10476190476190476,
      "success_rate.epoch.env.science": 0.9545180722891566,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985014617172603,
      "success_rate.epoch.global": 0.8513040093421564,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982887874837028,
      "tokens_p.mean_in_band": 0.5896990740740741,
      "tokens_rate.above_band": 0.9659949622166247,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03400503778337532
    },
    {
      "epoch": 1.5309175531914894,
      "grad_norm": 57.81549560444379,
      "learning_rate": 1.6539570063577828e-07,
      "loss": 0.2611,
      "step": 9210,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.448,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5826235093696763,
      "success_rate.epoch.env.math": 0.9747899159663865,
      "success_rate.epoch.env.sat": 0.10426540284360189,
      "success_rate.epoch.env.science": 0.9545864661654135,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5984368633919556,
      "success_rate.epoch.global": 0.8511465215701516,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9972885032537961,
      "tokens_p.mean_in_band": 0.5329733455882353,
      "tokens_rate.above_band": 0.9760056457304164,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02399435426958363
    },
    {
      "epoch": 1.531748670212766,
      "grad_norm": 38.432345147878934,
      "learning_rate": 1.6537750996266894e-07,
      "loss": 0.3295,
      "step": 9215,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5833333333333334,
      "success_rate.epoch.env.math": 0.9748603351955307,
      "success_rate.epoch.env.sat": 0.10426540284360189,
      "success_rate.epoch.env.science": 0.9546137661556958,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5989085448068678,
      "success_rate.epoch.global": 0.8513198757763976,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9989722898903776,
      "tokens_p.mean_in_band": 0.5929581925675675,
      "tokens_rate.above_band": 0.9779630732578916,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022036926742108397
    },
    {
      "epoch": 1.5325797872340425,
      "grad_norm": 55.218612249185014,
      "learning_rate": 1.6535934524089704e-07,
      "loss": 0.1674,
      "step": 9220,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5830508474576271,
      "success_rate.epoch.env.math": 0.9749303621169917,
      "success_rate.epoch.env.sat": 0.10426540284360189,
      "success_rate.epoch.env.science": 0.9546546546546546,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5988929474927509,
      "success_rate.epoch.global": 0.851327776700911,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.998433147632312,
      "tokens_p.mean_in_band": 0.6921164772727273,
      "tokens_rate.above_band": 0.9849108367626886,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015089163237311385
    },
    {
      "epoch": 1.533410904255319,
      "grad_norm": 157.58913675966403,
      "learning_rate": 1.6534120650270059e-07,
      "loss": 0.296,
      "step": 9225,
      "success_rate.epoch.env.abd": 0.5714285714285714,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45901639344262296,
      "success_rate.epoch.env.logic": 0.5827702702702703,
      "success_rate.epoch.env.math": 0.9749652294853964,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.9547226386806597,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.598832079880852,
      "success_rate.epoch.global": 0.8511996904024768,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9963576158940397,
      "tokens_p.mean_in_band": 0.60458984375,
      "tokens_rate.above_band": 0.949685534591195,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050314465408805034
    },
    {
      "epoch": 1.5342420212765957,
      "grad_norm": 156.4276679582101,
      "learning_rate": 1.6532309378027132e-07,
      "loss": 0.3428,
      "step": 9230,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45528455284552843,
      "success_rate.epoch.env.logic": 0.5827702702702703,
      "success_rate.epoch.env.math": 0.9749652294853964,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.9547904191616766,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5970559820636616,
      "success_rate.epoch.global": 0.8510144927536232,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9961231203007519,
      "tokens_p.mean_in_band": 0.27459395559210525,
      "tokens_rate.above_band": 0.5833333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.4166666666666667
    },
    {
      "epoch": 1.5350731382978724,
      "grad_norm": 92.34474294267994,
      "learning_rate": 1.6530500710575493e-07,
      "loss": 0.2839,
      "step": 9235,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45528455284552843,
      "success_rate.epoch.env.logic": 0.5824915824915825,
      "success_rate.epoch.env.math": 0.975,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.9548174745661281,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5970362673491496,
      "success_rate.epoch.global": 0.850965250965251,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.993720718375846,
      "tokens_p.mean_in_band": 0.5350811298076923,
      "tokens_rate.above_band": 0.8602776533811016,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13972234661889835
    },
    {
      "epoch": 1.5359042553191489,
      "grad_norm": 145.6546261255225,
      "learning_rate": 1.652869465112508e-07,
      "loss": 0.2209,
      "step": 9240,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45528455284552843,
      "success_rate.epoch.env.logic": 0.5824915824915825,
      "success_rate.epoch.env.math": 0.9750692520775623,
      "success_rate.epoch.env.sat": 0.10377358490566038,
      "success_rate.epoch.env.science": 0.9548984468339307,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5970499241078191,
      "success_rate.epoch.global": 0.851195065535852,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9894396551724138,
      "tokens_p.mean_in_band": 0.865234375,
      "tokens_rate.above_band": 0.9863945578231292,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013605442176870748
    },
    {
      "epoch": 1.5367353723404256,
      "grad_norm": 48.84491229255858,
      "learning_rate": 1.652689120288121e-07,
      "loss": 0.2878,
      "step": 9245,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45528455284552843,
      "success_rate.epoch.env.logic": 0.5831932773109244,
      "success_rate.epoch.env.math": 0.9751381215469613,
      "success_rate.epoch.env.sat": 0.10328638497652583,
      "success_rate.epoch.env.science": 0.9546404058490003,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5970522262327896,
      "success_rate.epoch.global": 0.8510105871029836,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.575,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9992143146796432,
      "tokens_p.mean_in_band": 0.6204202586206896,
      "tokens_rate.above_band": 0.9770206022187005,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022979397781299524
    },
    {
      "epoch": 1.5375664893617023,
      "grad_norm": 10.066583449628155,
      "learning_rate": 1.6525090369044559e-07,
      "loss": 0.1641,
      "step": 9250,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45528455284552843,
      "success_rate.epoch.env.logic": 0.5831932773109244,
      "success_rate.epoch.env.math": 0.9751724137931035,
      "success_rate.epoch.env.sat": 0.10328638497652583,
      "success_rate.epoch.env.science": 0.9547079856972587,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5970614873322806,
      "success_rate.epoch.global": 0.8511824649105941,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99609375,
      "tokens_p.mean_in_band": 0.5948988970588235,
      "tokens_rate.above_band": 0.974124809741248,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0258751902587519
    },
    {
      "epoch": 1.5383976063829787,
      "grad_norm": 177.5036342591982,
      "learning_rate": 1.6523292152811166e-07,
      "loss": 0.2806,
      "step": 9255,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45528455284552843,
      "success_rate.epoch.env.logic": 0.5838926174496645,
      "success_rate.epoch.env.math": 0.9752066115702479,
      "success_rate.epoch.env.sat": 0.102803738317757,
      "success_rate.epoch.env.science": 0.95473496128648,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5970867479546749,
      "success_rate.epoch.global": 0.8511333077218594,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9954461457233369,
      "tokens_p.mean_in_band": 0.6564360119047619,
      "tokens_rate.above_band": 0.9575328614762386,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.042467138523761376
    },
    {
      "epoch": 1.5392287234042552,
      "grad_norm": 64.04737764050743,
      "learning_rate": 1.6521496557372423e-07,
      "loss": 0.3478,
      "step": 9260,
      "success_rate.epoch.env.abd": 0.5555555555555556,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4596774193548387,
      "success_rate.epoch.env.logic": 0.5845896147403685,
      "success_rate.epoch.env.math": 0.9752066115702479,
      "success_rate.epoch.env.sat": 0.10232558139534884,
      "success_rate.epoch.env.science": 0.9548022598870056,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5975121120890505,
      "success_rate.epoch.global": 0.8511699271192942,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976615646258503,
      "tokens_p.mean_in_band": 0.6053385416666667,
      "tokens_rate.above_band": 0.9607843137254902,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0392156862745098
    },
    {
      "epoch": 1.540059840425532,
      "grad_norm": 186.3566727121957,
      "learning_rate": 1.6519703585915075e-07,
      "loss": 0.3361,
      "step": 9265,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4596774193548387,
      "success_rate.epoch.env.logic": 0.5845896147403685,
      "success_rate.epoch.env.math": 0.9753086419753086,
      "success_rate.epoch.env.sat": 0.10232558139534884,
      "success_rate.epoch.env.science": 0.9545589545589546,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985912700062342,
      "success_rate.epoch.global": 0.8512064343163539,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9903846153846154,
      "tokens_p.mean_below_band": 1.6079866327345371e-09,
      "tokens_rate.above_band": 0.9936305732484076,
      "tokens_rate.below_band": 0.006369426751592357,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.5408909574468086,
      "grad_norm": 492.8450407687255,
      "learning_rate": 1.6517913241621206e-07,
      "loss": 0.3513,
      "step": 9270,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4596774193548387,
      "success_rate.epoch.env.logic": 0.5843071786310517,
      "success_rate.epoch.env.math": 0.9753761969904241,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.9545994065281899,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985323464909194,
      "success_rate.epoch.global": 0.8510516252390057,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998309748427673,
      "tokens_p.mean_in_band": 0.5865478515625,
      "tokens_rate.above_band": 0.9613059250302297,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03869407496977025
    },
    {
      "epoch": 1.541722074468085,
      "grad_norm": 60.77314750814437,
      "learning_rate": 1.651612552766824e-07,
      "loss": 0.2766,
      "step": 9275,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4596774193548387,
      "success_rate.epoch.env.logic": 0.5843071786310517,
      "success_rate.epoch.env.math": 0.9754098360655737,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.9546532305868406,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985402976849012,
      "success_rate.epoch.global": 0.8511938872970392,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9884370701513068,
      "tokens_p.mean_in_band": 0.6088337725903614,
      "tokens_rate.above_band": 0.8141097424412094,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1858902575587906
    },
    {
      "epoch": 1.5425531914893615,
      "grad_norm": 45.810983873685004,
      "learning_rate": 1.6514340447228926e-07,
      "loss": 0.2671,
      "step": 9280,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4523809523809524,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4596774193548387,
      "success_rate.epoch.env.logic": 0.5843071786310517,
      "success_rate.epoch.env.math": 0.9754098360655737,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.9544108940201302,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985182670879277,
      "success_rate.epoch.global": 0.8511166253101737,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9810344827586207,
      "tokens_p.mean_below_band": 7.566995918750763e-10,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9863945578231292,
      "tokens_rate.below_band": 0.006802721088435374,
      "tokens_rate.in_band": 0.006802721088435374
    },
    {
      "epoch": 1.5433843085106385,
      "grad_norm": 77.89024446883836,
      "learning_rate": 1.651255800347135e-07,
      "loss": 0.2916,
      "step": 9285,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4566929133858268,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4596774193548387,
      "success_rate.epoch.env.logic": 0.5833333333333334,
      "success_rate.epoch.env.math": 0.975443383356071,
      "success_rate.epoch.env.sat": 0.10185185185185185,
      "success_rate.epoch.env.science": 0.9544648137196925,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5988296836967654,
      "success_rate.epoch.global": 0.8511246664125047,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9985508601346298,
      "tokens_p.mean_in_band": 0.6669170673076923,
      "tokens_rate.above_band": 0.9903703703703703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00962962962962963
    },
    {
      "epoch": 1.544215425531915,
      "grad_norm": 73.94830135978621,
      "learning_rate": 1.6510778199558913e-07,
      "loss": 0.3128,
      "step": 9290,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4566929133858268,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.456,
      "success_rate.epoch.env.logic": 0.5830564784053156,
      "success_rate.epoch.env.math": 0.975443383356071,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9545320342485976,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5984336457761708,
      "success_rate.epoch.global": 0.8508087535680304,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.375,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.994963171577123,
      "tokens_p.mean_in_band": 0.708,
      "tokens_rate.above_band": 0.9022673964034402,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09773260359655982
    },
    {
      "epoch": 1.5450465425531914,
      "grad_norm": 36.945497337701575,
      "learning_rate": 1.6509001038650327e-07,
      "loss": 0.2269,
      "step": 9295,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4566929133858268,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.456,
      "success_rate.epoch.env.logic": 0.582089552238806,
      "success_rate.epoch.env.math": 0.975443383356071,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9546258102533883,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5983542684887418,
      "success_rate.epoch.global": 0.850845525365761,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9987830996884736,
      "tokens_p.mean_in_band": 0.7193509615384616,
      "tokens_rate.above_band": 0.9801526717557252,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01984732824427481
    },
    {
      "epoch": 1.545877659574468,
      "grad_norm": 42.21455029417714,
      "learning_rate": 1.650722652389962e-07,
      "loss": 0.2648,
      "step": 9300,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4566929133858268,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.456,
      "success_rate.epoch.env.logic": 0.582089552238806,
      "success_rate.epoch.env.math": 0.975443383356071,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9546925566343042,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5983603363415523,
      "success_rate.epoch.global": 0.8509870918754746,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9935722976434426,
      "tokens_p.mean_in_band": 0.5723967535335689,
      "tokens_rate.above_band": 0.8733780760626398,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1266219239373602
    },
    {
      "epoch": 1.5467087765957448,
      "grad_norm": 86.4142358346517,
      "learning_rate": 1.6505454658456117e-07,
      "loss": 0.2932,
      "step": 9305,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4609375,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.456,
      "success_rate.epoch.env.logic": 0.5801652892561984,
      "success_rate.epoch.env.math": 0.9754768392370572,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9547192002352249,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985767384427771,
      "success_rate.epoch.global": 0.8507773985589685,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9999546114742193,
      "tokens_p.mean_in_band": 0.52734375,
      "tokens_rate.above_band": 0.9835714285714285,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016428571428571428
    },
    {
      "epoch": 1.5475398936170213,
      "grad_norm": 97.88257115794653,
      "learning_rate": 1.650368544546445e-07,
      "loss": 0.2481,
      "step": 9310,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4573643410852713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.456,
      "success_rate.epoch.env.logic": 0.5801652892561984,
      "success_rate.epoch.env.math": 0.9755766621438263,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9547458125183661,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982633999223391,
      "success_rate.epoch.global": 0.8507575757575757,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9973347547974414,
      "tokens_p.mean_in_band": 0.6829044117647058,
      "tokens_rate.above_band": 0.9650205761316872,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03497942386831276
    },
    {
      "epoch": 1.5483710106382977,
      "grad_norm": 579.3161108939388,
      "learning_rate": 1.6501918888064538e-07,
      "loss": 0.3687,
      "step": 9315,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4573643410852713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.456,
      "success_rate.epoch.env.logic": 0.5792079207920792,
      "success_rate.epoch.env.math": 0.975609756097561,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9547989433519225,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5981842050426274,
      "success_rate.epoch.global": 0.8507377979568672,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.993786023054755,
      "tokens_p.mean_in_band": 0.5829741379310345,
      "tokens_rate.above_band": 0.9598893499308437,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.040110650069156296
    },
    {
      "epoch": 1.5492021276595744,
      "grad_norm": 62.92559590765751,
      "learning_rate": 1.6500154989391587e-07,
      "loss": 0.1669,
      "step": 9320,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4573643410852713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4523809523809524,
      "success_rate.epoch.env.logic": 0.5792079207920792,
      "success_rate.epoch.env.math": 0.9756756756756757,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9548387096774194,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5978648085230422,
      "success_rate.epoch.global": 0.8507180650037793,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9895728008088979,
      "tokens_p.mean_in_band": 0.6317204301075269,
      "tokens_rate.above_band": 0.8417021276595744,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15829787234042553
    },
    {
      "epoch": 1.5500332446808511,
      "grad_norm": 232.18577267766102,
      "learning_rate": 1.6498393752576081e-07,
      "loss": 0.4462,
      "step": 9325,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4573643410852713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5792079207920792,
      "success_rate.epoch.env.math": 0.9756756756756757,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9548916227299356,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982616152555323,
      "success_rate.epoch.global": 0.850858976779309,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9914579796264855,
      "tokens_p.mean_in_band": 0.6620065789473685,
      "tokens_rate.above_band": 0.96875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03125
    },
    {
      "epoch": 1.5508643617021276,
      "grad_norm": 42.94920339151284,
      "learning_rate": 1.649663518074379e-07,
      "loss": 0.3647,
      "step": 9330,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.4573643410852713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5799011532125206,
      "success_rate.epoch.env.math": 0.9757412398921833,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9549575899385785,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5983365937869499,
      "success_rate.epoch.global": 0.8510838831291234,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9958791208791209,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.5516954787234043,
      "grad_norm": 37.14909379555877,
      "learning_rate": 1.6494879277015744e-07,
      "loss": 0.2881,
      "step": 9335,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.45384615384615384,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.580327868852459,
      "success_rate.epoch.env.math": 0.9757412398921833,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9550102249488752,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5980603359152333,
      "success_rate.epoch.global": 0.8509316770186336,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9985271516393442,
      "tokens_p.mean_in_band": 0.5784040178571429,
      "tokens_rate.above_band": 0.9858585858585859,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014141414141414142
    },
    {
      "epoch": 1.552526595744681,
      "grad_norm": 35.48011641662896,
      "learning_rate": 1.6493126044508246e-07,
      "loss": 0.3229,
      "step": 9340,
      "success_rate.epoch.env.abd": 0.5675675675675675,
      "success_rate.epoch.env.agentgym:alfworld": 0.45384615384615384,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.580327868852459,
      "success_rate.epoch.env.math": 0.9757412398921833,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.954784130688448,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.598039781891558,
      "success_rate.epoch.global": 0.8508837908988341,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9931139122315593,
      "tokens_p.mean_below_band": 2.9976945370435715e-09,
      "tokens_p.mean_in_band": 0.7180989583333334,
      "tokens_rate.above_band": 0.946113074204947,
      "tokens_rate.below_band": 0.0008833922261484099,
      "tokens_rate.in_band": 0.053003533568904596
    },
    {
      "epoch": 1.5533577127659575,
      "grad_norm": 46.997020652647606,
      "learning_rate": 1.649137548633285e-07,
      "loss": 0.2568,
      "step": 9345,
      "success_rate.epoch.env.abd": 0.5526315789473685,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5810147299509002,
      "success_rate.epoch.env.math": 0.9757738896366084,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9548499854354792,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5971323719187505,
      "success_rate.epoch.global": 0.8509480007508917,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9955163043478261,
      "tokens_p.mean_below_band": 8.866190910339355e-07,
      "tokens_p.mean_in_band": 0.12465504335001788,
      "tokens_rate.above_band": 0.3303015797032073,
      "tokens_rate.below_band": 0.00023934897079942556,
      "tokens_rate.in_band": 0.6694590713259932
    },
    {
      "epoch": 1.554188829787234,
      "grad_norm": 331.0569236958991,
      "learning_rate": 1.648962760559637e-07,
      "loss": 0.1984,
      "step": 9350,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5816993464052288,
      "success_rate.epoch.env.math": 0.9758389261744966,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9548631333721608,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982445342900318,
      "success_rate.epoch.global": 0.8510877719429858,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9986293859649122,
      "tokens_p.mean_in_band": 0.657421875,
      "tokens_rate.above_band": 0.9876237623762376,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012376237623762377
    },
    {
      "epoch": 1.5550199468085106,
      "grad_norm": 64.31501432388835,
      "learning_rate": 1.6487882405400865e-07,
      "loss": 0.2072,
      "step": 9355,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5816993464052288,
      "success_rate.epoch.env.math": 0.9758713136729222,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9549287583599884,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982534445160548,
      "success_rate.epoch.global": 0.8512551517422255,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9924812030075187,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9925373134328358,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007462686567164179
    },
    {
      "epoch": 1.5558510638297873,
      "grad_norm": 41.48157066632761,
      "learning_rate": 1.6486139888843637e-07,
      "loss": 0.2507,
      "step": 9360,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5816993464052288,
      "success_rate.epoch.env.math": 0.9759358288770054,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9550333623440673,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982688189877059,
      "success_rate.epoch.global": 0.8515332834704562,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9939393939393939,
      "tokens_p.mean_in_band": 0.8671875,
      "tokens_rate.above_band": 0.9939759036144579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006024096385542169
    },
    {
      "epoch": 1.5566821808510638,
      "grad_norm": 67.48113133943718,
      "learning_rate": 1.648440005901723e-07,
      "loss": 0.1964,
      "step": 9365,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5816993464052288,
      "success_rate.epoch.env.math": 0.976,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9550594375181212,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982770231965285,
      "success_rate.epoch.global": 0.851644245142003,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9982184129429892,
      "tokens_p.mean_in_band": 0.6770833333333334,
      "tokens_rate.above_band": 0.9818456883509834,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018154311649016642
    },
    {
      "epoch": 1.5575132978723403,
      "grad_norm": 20.292430926730685,
      "learning_rate": 1.648266291900941e-07,
      "loss": 0.262,
      "step": 9370,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5807504078303426,
      "success_rate.epoch.env.math": 0.9760319573901465,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9550984936268829,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5981972118259851,
      "success_rate.epoch.global": 0.851596042561135,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9998559907834101,
      "tokens_p.mean_in_band": 0.5848214285714286,
      "tokens_rate.above_band": 0.9893617021276596,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010638297872340425
    },
    {
      "epoch": 1.558344414893617,
      "grad_norm": 40.61589001796227,
      "learning_rate": 1.6480928471903182e-07,
      "loss": 0.2794,
      "step": 9375,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5804878048780487,
      "success_rate.epoch.env.math": 0.9760319573901465,
      "success_rate.epoch.env.sat": 0.10138248847926268,
      "success_rate.epoch.env.science": 0.9551244933410539,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5981757024407012,
      "success_rate.epoch.global": 0.8515202387614251,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958541927409261,
      "tokens_p.mean_in_band": 0.6008831521739131,
      "tokens_rate.above_band": 0.9455621301775148,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.054437869822485205
    },
    {
      "epoch": 1.5591755319148937,
      "grad_norm": 122.61954597959252,
      "learning_rate": 1.6479196720776757e-07,
      "loss": 0.1888,
      "step": 9380,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.4580152671755725,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5804878048780487,
      "success_rate.epoch.env.math": 0.9760956175298805,
      "success_rate.epoch.env.sat": 0.10091743119266056,
      "success_rate.epoch.env.science": 0.9551764025448236,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5981439308095104,
      "success_rate.epoch.global": 0.8515275707898659,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9938134517766497,
      "tokens_p.mean_below_band": 2.1736923372372985e-10,
      "tokens_p.mean_in_band": 0.5928308823529411,
      "tokens_rate.above_band": 0.9162790697674419,
      "tokens_rate.below_band": 0.004651162790697674,
      "tokens_rate.in_band": 0.07906976744186046
    },
    {
      "epoch": 1.5600066489361701,
      "grad_norm": 21.818336979738863,
      "learning_rate": 1.6477467668703576e-07,
      "loss": 0.3972,
      "step": 9385,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5804878048780487,
      "success_rate.epoch.env.math": 0.976158940397351,
      "success_rate.epoch.env.sat": 0.1004566210045662,
      "success_rate.epoch.env.science": 0.9552152557064433,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977958901923175,
      "success_rate.epoch.global": 0.8513488372093023,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9972987959442332,
      "tokens_p.mean_in_band": 0.47944630872483224,
      "tokens_rate.above_band": 0.9636052760136785,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.036394723986321445
    },
    {
      "epoch": 1.5608377659574468,
      "grad_norm": 206.48780514015917,
      "learning_rate": 1.6475741318752278e-07,
      "loss": 0.2428,
      "step": 9390,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5795454545454546,
      "success_rate.epoch.env.math": 0.9762219286657859,
      "success_rate.epoch.env.sat": 0.1004566210045662,
      "success_rate.epoch.env.science": 0.9549783549783549,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5976944117566586,
      "success_rate.epoch.global": 0.8511705685618729,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981694560669456,
      "tokens_p.mean_in_band": 0.57625,
      "tokens_rate.above_band": 0.9348109517601043,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0651890482398957
    },
    {
      "epoch": 1.5616688829787235,
      "grad_norm": 51.58350460559685,
      "learning_rate": 1.6474017673986714e-07,
      "loss": 0.2876,
      "step": 9395,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.580906148867314,
      "success_rate.epoch.env.math": 0.9762219286657859,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.955043227665706,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977824977570808,
      "success_rate.epoch.global": 0.8512059369202226,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9956487341772152,
      "tokens_p.mean_in_band": 0.6483347039473685,
      "tokens_rate.above_band": 0.9614604462474645,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.038539553752535496
    },
    {
      "epoch": 1.5625,
      "grad_norm": 261.705234518782,
      "learning_rate": 1.6472296737465927e-07,
      "loss": 0.2942,
      "step": 9400,
      "success_rate.epoch.env.abd": 0.5641025641025641,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.580906148867314,
      "success_rate.epoch.env.math": 0.9762532981530343,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9550949913644214,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5977900553194412,
      "success_rate.epoch.global": 0.8513438368860056,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921445741758241,
      "tokens_p.mean_in_band": 0.6350520833333333,
      "tokens_rate.above_band": 0.9066002490660025,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09339975093399751
    },
    {
      "epoch": 1.5633311170212765,
      "grad_norm": 56.94746983989885,
      "learning_rate": 1.647057851224416e-07,
      "loss": 0.3251,
      "step": 9405,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5799676898222941,
      "success_rate.epoch.env.math": 0.9762532981530343,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.9551208285385501,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5986566303502378,
      "success_rate.epoch.global": 0.8511111111111112,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9918650793650794,
      "tokens_p.mean_in_band": 0.6862909226190477,
      "tokens_rate.above_band": 0.9183673469387755,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08163265306122448
    },
    {
      "epoch": 1.5641622340425532,
      "grad_norm": 116.8976036136796,
      "learning_rate": 1.6468863001370844e-07,
      "loss": 0.2649,
      "step": 9410,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9763157894736842,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.9551466359976998,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985565161689411,
      "success_rate.epoch.global": 0.8509339744775292,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986178785607196,
      "tokens_p.mean_in_band": 0.5684523809523809,
      "tokens_rate.above_band": 0.9845018450184502,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015498154981549815
    },
    {
      "epoch": 1.5649933510638299,
      "grad_norm": 46.93117213931343,
      "learning_rate": 1.646715020789059e-07,
      "loss": 0.2373,
      "step": 9415,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9763469119579501,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.9552110249784669,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985651990293986,
      "success_rate.epoch.global": 0.8510992056161094,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9946875,
      "tokens_p.mean_in_band": 0.750244140625,
      "tokens_rate.above_band": 0.9259259259259259,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07407407407407407
    },
    {
      "epoch": 1.5658244680851063,
      "grad_norm": 115.72460639209886,
      "learning_rate": 1.6465440134843186e-07,
      "loss": 0.1813,
      "step": 9420,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4566929133858268,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9763469119579501,
      "success_rate.epoch.env.sat": 0.09954751131221719,
      "success_rate.epoch.env.science": 0.9553008595988539,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985733658130702,
      "success_rate.epoch.global": 0.8512915129151292,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9904057017543859,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.991304347826087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008695652173913044
    },
    {
      "epoch": 1.566655585106383,
      "grad_norm": 28.635721832078602,
      "learning_rate": 1.6463732785263593e-07,
      "loss": 0.2779,
      "step": 9425,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4609375,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9763469119579501,
      "success_rate.epoch.env.sat": 0.0990990990990991,
      "success_rate.epoch.env.science": 0.9553392499284283,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5989219626067638,
      "success_rate.epoch.global": 0.8512442396313364,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950657894736842,
      "tokens_p.mean_in_band": 0.65171875,
      "tokens_rate.above_band": 0.9673629242819843,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03263707571801567
    },
    {
      "epoch": 1.5674867021276597,
      "grad_norm": 50.34213786609767,
      "learning_rate": 1.6462028162181937e-07,
      "loss": 0.2623,
      "step": 9430,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4609375,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9764089121887287,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9553775743707094,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5988906838880492,
      "success_rate.epoch.global": 0.8512244522187442,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.991796875,
      "tokens_p.mean_in_band": 0.6741071428571429,
      "tokens_rate.above_band": 0.9195402298850575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08045977011494253
    },
    {
      "epoch": 1.5683178191489362,
      "grad_norm": 58.34430369348738,
      "learning_rate": 1.6460326268623505e-07,
      "loss": 0.1321,
      "step": 9435,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4573643410852713,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9764397905759162,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9554413024850043,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5985744518504813,
      "success_rate.epoch.global": 0.8512320706141964,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.99185667752443,
      "tokens_p.mean_in_band": 0.6206704125615764,
      "tokens_rate.above_band": 0.8193950177935944,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1806049822064057
    },
    {
      "epoch": 1.5691489361702127,
      "grad_norm": 188.27202069788194,
      "learning_rate": 1.6458627107608748e-07,
      "loss": 0.3187,
      "step": 9440,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5787781350482315,
      "success_rate.epoch.env.math": 0.9764397905759162,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9555175363558597,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5982615469988212,
      "success_rate.epoch.global": 0.8512396694214877,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9886904761904762,
      "tokens_p.mean_in_band": 0.6556640625,
      "tokens_rate.above_band": 0.9051724137931034,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09482758620689655
    },
    {
      "epoch": 1.5699800531914894,
      "grad_norm": 69.67043847586811,
      "learning_rate": 1.645693068215325e-07,
      "loss": 0.2209,
      "step": 9445,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5801282051282052,
      "success_rate.epoch.env.math": 0.9764397905759162,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9555555555555556,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5983877369333366,
      "success_rate.epoch.global": 0.8513761467889909,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959795321637427,
      "tokens_p.mean_in_band": 0.6770833333333334,
      "tokens_rate.above_band": 0.9661016949152542,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03389830508474576
    },
    {
      "epoch": 1.570811170212766,
      "grad_norm": 14.729485109307214,
      "learning_rate": 1.6455236995267761e-07,
      "loss": 0.2068,
      "step": 9450,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5801282051282052,
      "success_rate.epoch.env.math": 0.9764397905759162,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9556187766714083,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.598393484307505,
      "success_rate.epoch.global": 0.851512373968836,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959692716236722,
      "tokens_p.mean_in_band": 0.6458333333333334,
      "tokens_rate.above_band": 0.9734121122599705,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026587887740029542
    },
    {
      "epoch": 1.5716422872340425,
      "grad_norm": 57.47890689904436,
      "learning_rate": 1.6453546049958153e-07,
      "loss": 0.2622,
      "step": 9455,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5808,
      "success_rate.epoch.env.math": 0.9764397905759162,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9557069846678024,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5984625754773404,
      "success_rate.epoch.global": 0.8517298187808896,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9963422391857506,
      "tokens_p.mean_in_band": 0.73046875,
      "tokens_rate.above_band": 0.9949367088607595,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005063291139240506
    },
    {
      "epoch": 1.572473404255319,
      "grad_norm": 149.27959587221156,
      "learning_rate": 1.645185784922544e-07,
      "loss": 0.2552,
      "step": 9460,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5808,
      "success_rate.epoch.env.math": 0.9764397905759162,
      "success_rate.epoch.env.sat": 0.09865470852017937,
      "success_rate.epoch.env.science": 0.9557572319909245,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.598467143415806,
      "success_rate.epoch.global": 0.8518383025425279,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9958969465648855,
      "tokens_p.mean_in_band": 0.609375,
      "tokens_rate.above_band": 0.9675036927621861,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03249630723781388
    },
    {
      "epoch": 1.5733045212765957,
      "grad_norm": 54.73657587729029,
      "learning_rate": 1.645017239606577e-07,
      "loss": 0.5639,
      "step": 9465,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5808,
      "success_rate.epoch.env.math": 0.9765013054830287,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9558073654390935,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5984372548293867,
      "success_rate.epoch.global": 0.8518450858604312,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.992231638418079,
      "tokens_p.mean_in_band": 0.6428571428571429,
      "tokens_rate.above_band": 0.9267015706806283,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07329842931937172
    },
    {
      "epoch": 1.5741356382978724,
      "grad_norm": 74.3583783496278,
      "learning_rate": 1.6448489693470409e-07,
      "loss": 0.2607,
      "step": 9470,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.4166666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45384615384615384,
      "success_rate.epoch.env.logic": 0.5808,
      "success_rate.epoch.env.math": 0.9765013054830287,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9558698727015559,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5984429373077924,
      "success_rate.epoch.global": 0.8519802883737908,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9988715277777778,
      "tokens_p.mean_in_band": 0.7268318965517241,
      "tokens_rate.above_band": 0.9612817089452603,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03871829105473965
    },
    {
      "epoch": 1.5749667553191489,
      "grad_norm": 88.98239818161186,
      "learning_rate": 1.6446809744425737e-07,
      "loss": 0.291,
      "step": 9475,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.46153846153846156,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4580152671755725,
      "success_rate.epoch.env.logic": 0.5798722044728435,
      "success_rate.epoch.env.math": 0.9765319426336375,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9559322033898305,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6028253082635143,
      "success_rate.epoch.global": 0.8520408163265306,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992451690821256,
      "tokens_p.mean_in_band": 0.5435697115384616,
      "tokens_rate.above_band": 0.9922109047333733,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007789095266626723
    },
    {
      "epoch": 1.5757978723404256,
      "grad_norm": 74.856323054572,
      "learning_rate": 1.6445132551913253e-07,
      "loss": 0.4029,
      "step": 9480,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.46153846153846156,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4580152671755725,
      "success_rate.epoch.env.logic": 0.5798722044728435,
      "success_rate.epoch.env.math": 0.9765319426336375,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9559819413092551,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6028298298925528,
      "success_rate.epoch.global": 0.8521485797523671,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9969848732624693,
      "tokens_p.mean_in_band": 0.5092329545454546,
      "tokens_rate.above_band": 0.9652722967640095,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03472770323599053
    },
    {
      "epoch": 1.5766289893617023,
      "grad_norm": 95.13952732624814,
      "learning_rate": 1.6443458118909562e-07,
      "loss": 0.2159,
      "step": 9485,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.46153846153846156,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4580152671755725,
      "success_rate.epoch.env.logic": 0.580542264752791,
      "success_rate.epoch.env.math": 0.9765625,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9560439560439561,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6028991601090085,
      "success_rate.epoch.global": 0.8523367885070012,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9922855648535565,
      "tokens_p.mean_in_band": 0.83203125,
      "tokens_rate.above_band": 0.991701244813278,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008298755186721992
    },
    {
      "epoch": 1.5774601063829787,
      "grad_norm": 93.78763965216086,
      "learning_rate": 1.6441786448386378e-07,
      "loss": 0.1987,
      "step": 9490,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.46153846153846156,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4580152671755725,
      "success_rate.epoch.env.logic": 0.5812101910828026,
      "success_rate.epoch.env.math": 0.976592977893368,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9560934421615536,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6029671501400063,
      "success_rate.epoch.global": 0.8524977293369664,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936440677966102,
      "tokens_p.mean_in_band": 0.673828125,
      "tokens_rate.above_band": 0.9833333333333333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016666666666666666
    },
    {
      "epoch": 1.5782912234042552,
      "grad_norm": 84.33063695440337,
      "learning_rate": 1.6440117543310504e-07,
      "loss": 0.2803,
      "step": 9495,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5812101910828026,
      "success_rate.epoch.env.math": 0.976592977893368,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9561674627704412,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5996614387774369,
      "success_rate.epoch.global": 0.8523489932885906,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9918569627346596,
      "tokens_p.mean_in_band": 0.5301011029411765,
      "tokens_rate.above_band": 0.8332944197992062,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16670558020079385
    },
    {
      "epoch": 1.579122340425532,
      "grad_norm": 67.26672162826699,
      "learning_rate": 1.6438451406643834e-07,
      "loss": 0.246,
      "step": 9500,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5800316957210776,
      "success_rate.epoch.env.math": 0.9766233766233766,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9562166713443727,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5995615398630929,
      "success_rate.epoch.global": 0.8522006882811085,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983010708401977,
      "tokens_p.mean_in_band": 0.6546415441176471,
      "tokens_rate.above_band": 0.9727564102564102,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027243589743589744
    },
    {
      "epoch": 1.5799534574468086,
      "grad_norm": 1350.4006573297422,
      "learning_rate": 1.6436788041343357e-07,
      "loss": 0.3314,
      "step": 9505,
      "success_rate.epoch.env.abd": 0.575,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5800316957210776,
      "success_rate.epoch.env.math": 0.9767141009055628,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9562535053280987,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.5995731360690848,
      "success_rate.epoch.global": 0.852361136240275,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9972067039106145,
      "tokens_p.mean_in_band": 0.5234375,
      "tokens_rate.above_band": 0.9835164835164835,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016483516483516484
    },
    {
      "epoch": 1.580784574468085,
      "grad_norm": 148.16181873774264,
      "learning_rate": 1.6435127450361135e-07,
      "loss": 0.2241,
      "step": 9510,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5806962025316456,
      "success_rate.epoch.env.math": 0.9767741935483871,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9563025210084034,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6005858150501969,
      "success_rate.epoch.global": 0.8525745257452575,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9953427189988624,
      "tokens_p.mean_in_band": 0.8008814102564102,
      "tokens_rate.above_band": 0.9575163398692811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.042483660130718956
    },
    {
      "epoch": 1.5816156914893615,
      "grad_norm": 46.40845712135668,
      "learning_rate": 1.6433469636644316e-07,
      "loss": 0.2595,
      "step": 9515,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5806962025316456,
      "success_rate.epoch.env.math": 0.9768339768339769,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9563758389261745,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6005979151595935,
      "success_rate.epoch.global": 0.8527872992964098,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9915497448979592,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.5824468085106385,
      "grad_norm": 94.97964929442708,
      "learning_rate": 1.6431814603135105e-07,
      "loss": 0.2735,
      "step": 9520,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5806962025316456,
      "success_rate.epoch.env.math": 0.9768637532133676,
      "success_rate.epoch.env.sat": 0.09821428571428571,
      "success_rate.epoch.env.science": 0.9564732142857143,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6009823073173052,
      "success_rate.epoch.global": 0.8530524041058887,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9960241730279898,
      "tokens_p.mean_in_band": 0.7786458333333334,
      "tokens_rate.above_band": 0.9924242424242424,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007575757575757576
    },
    {
      "epoch": 1.583277925531915,
      "grad_norm": 24.78217072807551,
      "learning_rate": 1.6430162352770787e-07,
      "loss": 0.2479,
      "step": 9525,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.5806962025316456,
      "success_rate.epoch.env.math": 0.9768934531450578,
      "success_rate.epoch.env.sat": 0.09777777777777778,
      "success_rate.epoch.env.science": 0.9565217391304348,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6009497361209327,
      "success_rate.epoch.global": 0.8530311207051628,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9860026041666666,
      "tokens_p.mean_in_band": 0.6493055555555556,
      "tokens_rate.above_band": 0.9142857142857143,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08571428571428572
    },
    {
      "epoch": 1.5841090425531914,
      "grad_norm": 47.859974559607,
      "learning_rate": 1.64285128884837e-07,
      "loss": 0.2566,
      "step": 9530,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45454545454545453,
      "success_rate.epoch.env.logic": 0.580441640378549,
      "success_rate.epoch.env.math": 0.9769230769230769,
      "success_rate.epoch.env.sat": 0.09777777777777778,
      "success_rate.epoch.env.science": 0.9565580618212197,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6009325892405425,
      "success_rate.epoch.global": 0.8530098831985624,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.996728650137741,
      "tokens_p.mean_in_band": 0.5246394230769231,
      "tokens_rate.above_band": 0.9824086603518268,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017591339648173207
    },
    {
      "epoch": 1.584940159574468,
      "grad_norm": 75.39368286501771,
      "learning_rate": 1.642686621320124e-07,
      "loss": 0.2129,
      "step": 9535,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45864661654135336,
      "success_rate.epoch.env.logic": 0.580441640378549,
      "success_rate.epoch.env.math": 0.9769526248399488,
      "success_rate.epoch.env.sat": 0.10176991150442478,
      "success_rate.epoch.env.science": 0.9566184649610678,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016765207659304,
      "success_rate.epoch.global": 0.8532208864166517,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7666666666666667,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9933505455962588,
      "tokens_p.mean_below_band": 3.1650415621697903e-10,
      "tokens_p.mean_in_band": 0.7725183823529411,
      "tokens_rate.above_band": 0.9734446130500759,
      "tokens_rate.below_band": 0.0007587253414264037,
      "tokens_rate.in_band": 0.025796661608497723
    },
    {
      "epoch": 1.5857712765957448,
      "grad_norm": 103.13253511809297,
      "learning_rate": 1.642522232984585e-07,
      "loss": 0.2818,
      "step": 9540,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45864661654135336,
      "success_rate.epoch.env.logic": 0.580441640378549,
      "success_rate.epoch.env.math": 0.9770408163265306,
      "success_rate.epoch.env.sat": 0.10176991150442478,
      "success_rate.epoch.env.science": 0.9563888888888888,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016636676217851,
      "success_rate.epoch.global": 0.853225806451613,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974888392857143,
      "tokens_p.mean_in_band": 0.5558035714285714,
      "tokens_rate.above_band": 0.96,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04
    },
    {
      "epoch": 1.5866023936170213,
      "grad_norm": 47.3144813182269,
      "learning_rate": 1.6423581241335022e-07,
      "loss": 0.2696,
      "step": 9545,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45864661654135336,
      "success_rate.epoch.env.logic": 0.580441640378549,
      "success_rate.epoch.env.math": 0.9770700636942675,
      "success_rate.epoch.env.sat": 0.10176991150442478,
      "success_rate.epoch.env.science": 0.9564614531336662,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016729232229228,
      "success_rate.epoch.global": 0.8534097010918203,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9987541528239202,
      "tokens_p.mean_in_band": 0.7045036764705882,
      "tokens_rate.above_band": 0.9860769860769861,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013923013923013924
    },
    {
      "epoch": 1.5874335106382977,
      "grad_norm": 50.65825202496181,
      "learning_rate": 1.6421942950581286e-07,
      "loss": 0.2596,
      "step": 9550,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45864661654135336,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.580441640378549,
      "success_rate.epoch.env.math": 0.9770700636942675,
      "success_rate.epoch.env.sat": 0.1013215859030837,
      "success_rate.epoch.env.science": 0.9562569213732004,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013024147405459,
      "success_rate.epoch.global": 0.853083109919571,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9902823920265781,
      "tokens_p.mean_below_band": 1.9744038581848145e-07,
      "tokens_p.mean_in_band": 0.593987462006079,
      "tokens_rate.above_band": 0.8201634877384196,
      "tokens_rate.below_band": 0.0005449591280653951,
      "tokens_rate.in_band": 0.179291553133515
    },
    {
      "epoch": 1.5882646276595744,
      "grad_norm": 19.74064520363544,
      "learning_rate": 1.6420307460492206e-07,
      "loss": 0.257,
      "step": 9555,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5811023622047244,
      "success_rate.epoch.env.math": 0.9770700636942675,
      "success_rate.epoch.env.sat": 0.1013215859030837,
      "success_rate.epoch.env.science": 0.9563053097345132,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6017341475414836,
      "success_rate.epoch.global": 0.8532404927691484,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9974671412924425,
      "tokens_p.mean_in_band": 0.6536458333333334,
      "tokens_rate.above_band": 0.9902386117136659,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009761388286334056
    },
    {
      "epoch": 1.5890957446808511,
      "grad_norm": 27.400443794872835,
      "learning_rate": 1.6418674773970376e-07,
      "loss": 0.3753,
      "step": 9560,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5811023622047244,
      "success_rate.epoch.env.math": 0.9770700636942675,
      "success_rate.epoch.env.sat": 0.1013215859030837,
      "success_rate.epoch.env.science": 0.956365644849489,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601739632551936,
      "success_rate.epoch.global": 0.853371387798787,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9945886075949367,
      "tokens_p.mean_below_band": 3.3527612686157227e-07,
      "tokens_p.mean_in_band": 0.620859375,
      "tokens_rate.above_band": 0.9511196725258849,
      "tokens_rate.below_band": 0.0007223693715386468,
      "tokens_rate.in_band": 0.04815795810257645
    },
    {
      "epoch": 1.5899268617021276,
      "grad_norm": 35.20897838334221,
      "learning_rate": 1.6417044893913415e-07,
      "loss": 0.2764,
      "step": 9565,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5817610062893082,
      "success_rate.epoch.env.math": 0.9770700636942675,
      "success_rate.epoch.env.sat": 0.10043668122270742,
      "success_rate.epoch.env.science": 0.9564137931034483,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6017234405208601,
      "success_rate.epoch.global": 0.8531979333689649,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9964102176541717,
      "tokens_p.mean_in_band": 0.5651483050847458,
      "tokens_rate.above_band": 0.9334085778781038,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06659142212189616
    },
    {
      "epoch": 1.5907579787234043,
      "grad_norm": 22.305761052885384,
      "learning_rate": 1.641541782321396e-07,
      "loss": 0.3602,
      "step": 9570,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4626865671641791,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5824175824175825,
      "success_rate.epoch.env.math": 0.9770992366412213,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9564498346196252,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6021446164713742,
      "success_rate.epoch.global": 0.8533546894465207,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951550387596899,
      "tokens_p.mean_in_band": 0.6875,
      "tokens_rate.above_band": 0.979746835443038,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020253164556962026
    },
    {
      "epoch": 1.591589095744681,
      "grad_norm": 90.64966224663716,
      "learning_rate": 1.6413793564759667e-07,
      "loss": 0.1337,
      "step": 9575,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45925925925925926,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5830721003134797,
      "success_rate.epoch.env.math": 0.9771573604060914,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9564977973568282,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6019021888798333,
      "success_rate.epoch.global": 0.8533854629465079,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9965452261306532,
      "tokens_p.mean_in_band": 0.599609375,
      "tokens_rate.above_band": 0.995,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005
    },
    {
      "epoch": 1.5924202127659575,
      "grad_norm": 67.55648899327868,
      "learning_rate": 1.641217212143319e-07,
      "loss": 0.2594,
      "step": 9580,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45925925925925926,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5834633385335414,
      "success_rate.epoch.env.math": 0.9771863117870723,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9565217391304348,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6019425644593469,
      "success_rate.epoch.global": 0.8533641043848749,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9980733662145499,
      "tokens_p.mean_in_band": 0.7001953125,
      "tokens_rate.above_band": 0.9854191980558931,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014580801944106925
    },
    {
      "epoch": 1.593251329787234,
      "grad_norm": 19.66745065199376,
      "learning_rate": 1.64105534961122e-07,
      "loss": 0.2281,
      "step": 9585,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45925925925925926,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4552238805970149,
      "success_rate.epoch.env.logic": 0.5841121495327103,
      "success_rate.epoch.env.math": 0.9771863117870723,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9565695437053326,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6020058931478984,
      "success_rate.epoch.global": 0.8534941468605889,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9953218562874252,
      "tokens_p.mean_in_band": 0.8984375,
      "tokens_rate.above_band": 0.9985052316890882,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0014947683109118087
    },
    {
      "epoch": 1.5940824468085106,
      "grad_norm": 58.34736606183343,
      "learning_rate": 1.6408937691669357e-07,
      "loss": 0.4847,
      "step": 9590,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45925925925925926,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45185185185185184,
      "success_rate.epoch.env.logic": 0.5822981366459627,
      "success_rate.epoch.env.math": 0.9771863117870723,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9566291517979687,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601539853735237,
      "success_rate.epoch.global": 0.853170386114063,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9953892314468179,
      "tokens_p.mean_in_band": 0.5213496767241379,
      "tokens_rate.above_band": 0.9072927072927073,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09270729270729271
    },
    {
      "epoch": 1.5949135638297873,
      "grad_norm": 42.210974788508544,
      "learning_rate": 1.6407324710972318e-07,
      "loss": 0.3051,
      "step": 9595,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45925925925925926,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5829457364341085,
      "success_rate.epoch.env.math": 0.9772151898734177,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9566648381788261,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013025559323464,
      "success_rate.epoch.global": 0.8531493276716207,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9907378580323786,
      "tokens_p.mean_below_band": 7.338821887969971e-07,
      "tokens_p.mean_in_band": 0.55625,
      "tokens_rate.above_band": 0.8021978021978022,
      "tokens_rate.below_band": 0.0004995004995004995,
      "tokens_rate.in_band": 0.1973026973026973
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 131.84954726109595,
      "learning_rate": 1.6405714556883728e-07,
      "loss": 0.2865,
      "step": 9600,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5826893353941267,
      "success_rate.epoch.env.math": 0.9772151898734177,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9567004658810633,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.600975494145453,
      "success_rate.epoch.global": 0.8529515729939908,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9987898633257403,
      "tokens_p.mean_in_band": 0.5281575520833334,
      "tokens_rate.above_band": 0.9733924611973392,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026607538802660754
    },
    {
      "epoch": 1.5965757978723403,
      "grad_norm": 165.81248437530223,
      "learning_rate": 1.6404107232261217e-07,
      "loss": 0.3138,
      "step": 9605,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5826893353941267,
      "success_rate.epoch.env.math": 0.9773013871374527,
      "success_rate.epoch.env.sat": 0.10434782608695652,
      "success_rate.epoch.env.science": 0.9567360350492881,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.600986563821113,
      "success_rate.epoch.global": 0.8531073446327684,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9931913407821229,
      "tokens_p.mean_in_band": 0.6983506944444444,
      "tokens_rate.above_band": 0.9086294416243654,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09137055837563451
    },
    {
      "epoch": 1.597406914893617,
      "grad_norm": 62.12407310166352,
      "learning_rate": 1.6402502739957396e-07,
      "loss": 0.4182,
      "step": 9610,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45588235294117646,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5817901234567902,
      "success_rate.epoch.env.math": 0.9761306532663316,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.9567833698030634,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6007616244351552,
      "success_rate.epoch.global": 0.8528115635466244,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9942064606741573,
      "tokens_p.mean_below_band": 6.565414878423326e-12,
      "tokens_p.mean_in_band": 0.66015625,
      "tokens_rate.above_band": 0.9595687331536388,
      "tokens_rate.below_band": 0.0013477088948787063,
      "tokens_rate.in_band": 0.03908355795148248
    },
    {
      "epoch": 1.5982380319148937,
      "grad_norm": 81.57105460252536,
      "learning_rate": 1.640090108281984e-07,
      "loss": 0.1507,
      "step": 9615,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.9761606022584692,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.9568188029516261,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6011057500605858,
      "success_rate.epoch.global": 0.8528169014084507,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9970580543933054,
      "tokens_p.mean_in_band": 0.6941105769230769,
      "tokens_rate.above_band": 0.9865841073271414,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013415892672858616
    },
    {
      "epoch": 1.5990691489361701,
      "grad_norm": 77.24029236531815,
      "learning_rate": 1.6399302263691102e-07,
      "loss": 0.1527,
      "step": 9620,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.9761904761904762,
      "success_rate.epoch.env.sat": 0.1038961038961039,
      "success_rate.epoch.env.science": 0.9566284779050737,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6010911635956271,
      "success_rate.epoch.global": 0.8528481012658228,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9913522012578616,
      "tokens_p.mean_below_band": 4.05634636990726e-10,
      "tokens_p.mean_in_band": 0.753125,
      "tokens_rate.above_band": 0.9636363636363636,
      "tokens_rate.below_band": 0.006060606060606061,
      "tokens_rate.in_band": 0.030303030303030304
    },
    {
      "epoch": 1.5999002659574468,
      "grad_norm": 84.89153635794803,
      "learning_rate": 1.639770628540869e-07,
      "loss": 0.3731,
      "step": 9625,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.975,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9566639411283728,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.600945450777335,
      "success_rate.epoch.global": 0.8526519142957499,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5555555555555555,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9918686224489796,
      "tokens_p.mean_below_band": 4.6629367034256575e-15,
      "tokens_p.mean_in_band": 0.7026909722222222,
      "tokens_rate.above_band": 0.9116279069767442,
      "tokens_rate.below_band": 0.004651162790697674,
      "tokens_rate.in_band": 0.08372093023255814
    },
    {
      "epoch": 1.6007313829787235,
      "grad_norm": 58.67035964422717,
      "learning_rate": 1.639611315080508e-07,
      "loss": 0.2224,
      "step": 9630,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.9750312109862672,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9567111353117342,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6009525785200286,
      "success_rate.epoch.global": 0.8527811896824005,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.99475,
      "tokens_p.mean_in_band": 0.8645833333333334,
      "tokens_rate.above_band": 0.9765625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0234375
    },
    {
      "epoch": 1.6015625,
      "grad_norm": 67.140955328308,
      "learning_rate": 1.6394522862707692e-07,
      "loss": 0.2804,
      "step": 9635,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.9750623441396509,
      "success_rate.epoch.env.sat": 0.10300429184549356,
      "success_rate.epoch.env.science": 0.9567582268153386,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.600919327669157,
      "success_rate.epoch.global": 0.852760736196319,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9902146464646465,
      "tokens_p.mean_in_band": 0.67236328125,
      "tokens_rate.above_band": 0.9252336448598131,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07476635514018691
    },
    {
      "epoch": 1.6023936170212765,
      "grad_norm": 51.59720938595861,
      "learning_rate": 1.6392935423938898e-07,
      "loss": 0.259,
      "step": 9640,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.975093399750934,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9568052159739201,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6008864054408364,
      "success_rate.epoch.global": 0.8527403256872702,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9911556603773585,
      "tokens_p.mean_in_band": 0.7270220588235294,
      "tokens_rate.above_band": 0.925764192139738,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07423580786026202
    },
    {
      "epoch": 1.6032247340425532,
      "grad_norm": 70.36176220100445,
      "learning_rate": 1.6391350837316014e-07,
      "loss": 0.3587,
      "step": 9645,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5815384615384616,
      "success_rate.epoch.env.math": 0.975093399750934,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9566395663956639,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6008713463882677,
      "success_rate.epoch.global": 0.8527972027972028,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9901785714285715,
      "tokens_p.mean_in_band": 0.496875,
      "tokens_rate.above_band": 0.9767441860465116,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023255813953488372
    },
    {
      "epoch": 1.6040558510638299,
      "grad_norm": 15.792702063112475,
      "learning_rate": 1.6389769105651295e-07,
      "loss": 0.3159,
      "step": 9650,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4485294117647059,
      "success_rate.epoch.env.logic": 0.5806451612903226,
      "success_rate.epoch.env.math": 0.9751243781094527,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9566982408660352,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6007982875319723,
      "success_rate.epoch.global": 0.8528025144054479,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9987927191679049,
      "tokens_p.mean_in_band": 0.5813337053571429,
      "tokens_rate.above_band": 0.9600570613409415,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039942938659058486
    },
    {
      "epoch": 1.6048869680851063,
      "grad_norm": 40.85080914535933,
      "learning_rate": 1.6388190231751922e-07,
      "loss": 0.3596,
      "step": 9655,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5806451612903226,
      "success_rate.epoch.env.math": 0.9751243781094527,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9567567567567568,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6011695465002962,
      "success_rate.epoch.global": 0.8529565672422815,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9956664098613252,
      "tokens_p.mean_in_band": 0.708984375,
      "tokens_rate.above_band": 0.9938744257274119,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006125574272588055
    },
    {
      "epoch": 1.605718085106383,
      "grad_norm": 66.68457964214342,
      "learning_rate": 1.6386614218420013e-07,
      "loss": 0.3417,
      "step": 9660,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45985401459854014,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5806451612903226,
      "success_rate.epoch.env.math": 0.9751243781094527,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9568151147098516,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6011748517687594,
      "success_rate.epoch.global": 0.8530846985012199,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.998242030538441,
      "tokens_p.mean_below_band": 3.11434268951416e-07,
      "tokens_p.mean_in_band": 0.49734669811320753,
      "tokens_rate.above_band": 0.9579163459071081,
      "tokens_rate.below_band": 0.0012830382345393892,
      "tokens_rate.in_band": 0.04080061585835258
    },
    {
      "epoch": 1.6065492021276597,
      "grad_norm": 84.92666634787885,
      "learning_rate": 1.6385041068452603e-07,
      "loss": 0.2166,
      "step": 9665,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5812883435582822,
      "success_rate.epoch.env.math": 0.9751243781094527,
      "success_rate.epoch.env.sat": 0.10212765957446808,
      "success_rate.epoch.env.science": 0.9568384138117075,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015515917436385,
      "success_rate.epoch.global": 0.8530640668523677,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9943595342066958,
      "tokens_p.mean_in_band": 0.6800054505813954,
      "tokens_rate.above_band": 0.9410958904109589,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0589041095890411
    },
    {
      "epoch": 1.6073803191489362,
      "grad_norm": 75.16921152654156,
      "learning_rate": 1.638347078464165e-07,
      "loss": 0.2992,
      "step": 9670,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5825688073394495,
      "success_rate.epoch.env.math": 0.9751861042183623,
      "success_rate.epoch.env.sat": 0.1016949152542373,
      "success_rate.epoch.env.science": 0.9568733153638814,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016374414820039,
      "success_rate.epoch.global": 0.8530945757997218,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936224489795918,
      "tokens_p.mean_in_band": 0.5872395833333334,
      "tokens_rate.above_band": 0.9560975609756097,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04390243902439024
    },
    {
      "epoch": 1.6082114361702127,
      "grad_norm": 19.544656165755438,
      "learning_rate": 1.6381903369774025e-07,
      "loss": 0.3568,
      "step": 9675,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5825688073394495,
      "success_rate.epoch.env.math": 0.9753086419753086,
      "success_rate.epoch.env.sat": 0.1016949152542373,
      "success_rate.epoch.env.science": 0.956908160517102,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016517490192919,
      "success_rate.epoch.global": 0.8532731376975169,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9972198460222412,
      "tokens_p.mean_in_band": 0.5680338541666666,
      "tokens_rate.above_band": 0.9605587510271159,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03944124897288414
    },
    {
      "epoch": 1.6090425531914894,
      "grad_norm": 150.8497379267538,
      "learning_rate": 1.63803388266315e-07,
      "loss": 0.2288,
      "step": 9680,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5825688073394495,
      "success_rate.epoch.env.math": 0.9753086419753086,
      "success_rate.epoch.env.sat": 0.1016949152542373,
      "success_rate.epoch.env.science": 0.9569661108122647,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601657017227943,
      "success_rate.epoch.global": 0.8534004163775156,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9941852168949772,
      "tokens_p.mean_in_band": 0.5137434554973822,
      "tokens_rate.above_band": 0.8209934395501406,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1790065604498594
    },
    {
      "epoch": 1.609873670212766,
      "grad_norm": 68.53703273612386,
      "learning_rate": 1.637877715799076e-07,
      "loss": 0.252,
      "step": 9685,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5807926829268293,
      "success_rate.epoch.env.math": 0.9753086419753086,
      "success_rate.epoch.env.sat": 0.10126582278481013,
      "success_rate.epoch.env.science": 0.9570008062348832,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014596970952676,
      "success_rate.epoch.global": 0.8530329289428076,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973727876106194,
      "tokens_p.mean_in_band": 0.6693412162162162,
      "tokens_rate.above_band": 0.9734386216798278,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02656137832017229
    },
    {
      "epoch": 1.6107047872340425,
      "grad_norm": 283.55342851032486,
      "learning_rate": 1.637721836662338e-07,
      "loss": 0.1946,
      "step": 9690,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5807926829268293,
      "success_rate.epoch.env.math": 0.9753086419753086,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9570469798657718,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014252140934978,
      "success_rate.epoch.global": 0.852987012987013,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.000475888324873,
      "tokens_p.mean_in_band": 0.6707175925925926,
      "tokens_rate.above_band": 0.9668711656441717,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033128834355828224
    },
    {
      "epoch": 1.611535904255319,
      "grad_norm": 136.53384687625044,
      "learning_rate": 1.637566245529584e-07,
      "loss": 0.2541,
      "step": 9695,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5807926829268293,
      "success_rate.epoch.env.math": 0.9753390875462392,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9571160546770303,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014342614009696,
      "success_rate.epoch.global": 0.8531649948114839,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9895174050632911,
      "tokens_p.mean_in_band": 0.7973090277777778,
      "tokens_rate.above_band": 0.9461077844311377,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05389221556886228
    },
    {
      "epoch": 1.6123670212765957,
      "grad_norm": 63.74202025737574,
      "learning_rate": 1.6374109426769495e-07,
      "loss": 0.2923,
      "step": 9700,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5799086757990868,
      "success_rate.epoch.env.math": 0.9753694581280788,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9571734475374732,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013618756113822,
      "success_rate.epoch.global": 0.853169804802211,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9959112149532711,
      "tokens_p.mean_in_band": 0.56875,
      "tokens_rate.above_band": 0.9553571428571429,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044642857142857144
    },
    {
      "epoch": 1.6131981382978724,
      "grad_norm": 21.803538223183345,
      "learning_rate": 1.6372559283800593e-07,
      "loss": 0.2534,
      "step": 9705,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5799086757990868,
      "success_rate.epoch.env.math": 0.9753694581280788,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9572421165152325,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013681182457241,
      "success_rate.epoch.global": 0.8533218291630716,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917218543046358,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.6140292553191489,
      "grad_norm": 166.94935595492123,
      "learning_rate": 1.637101202914026e-07,
      "loss": 0.2579,
      "step": 9710,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5796661608497724,
      "success_rate.epoch.env.math": 0.97539975399754,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9572763684913218,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013519394181092,
      "success_rate.epoch.global": 0.8533011549732805,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960115708274895,
      "tokens_p.mean_in_band": 0.6730769230769231,
      "tokens_rate.above_band": 0.9820936639118457,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01790633608815427
    },
    {
      "epoch": 1.6148603723404256,
      "grad_norm": 48.72009810112761,
      "learning_rate": 1.6369467665534487e-07,
      "loss": 0.2465,
      "step": 9715,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5796661608497724,
      "success_rate.epoch.env.math": 0.9754299754299754,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9573105656350054,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013577956523017,
      "success_rate.epoch.global": 0.853402239448751,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9930218446601942,
      "tokens_p.mean_in_band": 0.7799479166666666,
      "tokens_rate.above_band": 0.9927710843373494,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007228915662650603
    },
    {
      "epoch": 1.6156914893617023,
      "grad_norm": 6.142620683199756,
      "learning_rate": 1.6367926195724148e-07,
      "loss": 0.2648,
      "step": 9720,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45255474452554745,
      "success_rate.epoch.env.logic": 0.5796661608497724,
      "success_rate.epoch.env.math": 0.9754299754299754,
      "success_rate.epoch.env.sat": 0.10084033613445378,
      "success_rate.epoch.env.science": 0.9573674393818279,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013629659929219,
      "success_rate.epoch.global": 0.8535283993115318,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9967851739788199,
      "tokens_p.mean_in_band": 0.7369791666666666,
      "tokens_rate.above_band": 0.9821693907875185,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017830609212481426
    },
    {
      "epoch": 1.6165226063829787,
      "grad_norm": 57.42820166340494,
      "learning_rate": 1.636638762244497e-07,
      "loss": 0.2926,
      "step": 9725,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5796661608497724,
      "success_rate.epoch.env.math": 0.9754299754299754,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.9571466595688048,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016651740564902,
      "success_rate.epoch.global": 0.8533356258596974,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.5714285714285714,
      "success_rate.window.env_macro_mean": 0.6428571428571428,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9927536231884058,
      "tokens_p.mean_below_band": 2.8405338525772095e-08,
      "tokens_p.mean_in_band": 0.6987847222222222,
      "tokens_rate.above_band": 0.917960088691796,
      "tokens_rate.below_band": 0.0022172949002217295,
      "tokens_rate.in_band": 0.07982261640798226
    },
    {
      "epoch": 1.6173537234042552,
      "grad_norm": 87.56502326847537,
      "learning_rate": 1.6364851948427548e-07,
      "loss": 0.277,
      "step": 9730,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5779122541603631,
      "success_rate.epoch.env.math": 0.9754601226993865,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.9571922361074182,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015126119763644,
      "success_rate.epoch.global": 0.8531684698608965,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973125689084895,
      "tokens_p.mean_in_band": 0.6411290322580645,
      "tokens_rate.above_band": 0.951232302045097,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04876769795490299
    },
    {
      "epoch": 1.618184840425532,
      "grad_norm": 79.98421020975385,
      "learning_rate": 1.636331917639732e-07,
      "loss": 0.2929,
      "step": 9735,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5770392749244713,
      "success_rate.epoch.env.math": 0.9754901960784313,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.9572263549415515,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014390858833903,
      "success_rate.epoch.global": 0.8531228551818806,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.0008439237490072,
      "tokens_p.mean_in_band": 0.5959821428571429,
      "tokens_rate.above_band": 0.96771714066103,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03228285933897002
    },
    {
      "epoch": 1.6190159574468086,
      "grad_norm": 136.0238770530322,
      "learning_rate": 1.6361789309074588e-07,
      "loss": 0.256,
      "step": 9740,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5776772247360482,
      "success_rate.epoch.env.math": 0.9755501222493888,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.957271762208068,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015066570878496,
      "success_rate.epoch.global": 0.8532990574121679,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9958095577746077,
      "tokens_p.mean_in_band": 0.6984375,
      "tokens_rate.above_band": 0.979050279329609,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02094972067039106
    },
    {
      "epoch": 1.619847074468085,
      "grad_norm": 48.87164770039113,
      "learning_rate": 1.6360262349174487e-07,
      "loss": 0.2973,
      "step": 9745,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5776772247360482,
      "success_rate.epoch.env.math": 0.975609756097561,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.9573057544417927,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015151685498402,
      "success_rate.epoch.global": 0.8534246575342466,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9907962328767124,
      "tokens_p.mean_below_band": 4.6798959374427795e-08,
      "tokens_p.mean_in_band": 0.8671875,
      "tokens_rate.above_band": 0.9864864864864865,
      "tokens_rate.below_band": 0.006756756756756757,
      "tokens_rate.in_band": 0.006756756756756757
    },
    {
      "epoch": 1.6206781914893615,
      "grad_norm": 87.45172741279457,
      "learning_rate": 1.6358738299407004e-07,
      "loss": 0.175,
      "step": 9750,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5776772247360482,
      "success_rate.epoch.env.math": 0.9756394640682094,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.9573509933774834,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015219819049619,
      "success_rate.epoch.global": 0.8535500427715996,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9948559670781894,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9918367346938776,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00816326530612245
    },
    {
      "epoch": 1.6215093085106385,
      "grad_norm": 542.6965028363807,
      "learning_rate": 1.6357217162476943e-07,
      "loss": 0.3542,
      "step": 9755,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5776772247360482,
      "success_rate.epoch.env.math": 0.9756394640682094,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.957154192012695,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015040908717993,
      "success_rate.epoch.global": 0.8535293112288498,
      "success_rate.window.env.science": 0.9,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.98725,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.892578125,
      "tokens_rate.above_band": 0.9765625,
      "tokens_rate.below_band": 0.0078125,
      "tokens_rate.in_band": 0.015625
    },
    {
      "epoch": 1.622340425531915,
      "grad_norm": 107.83038425029258,
      "learning_rate": 1.6355698941083954e-07,
      "loss": 0.2323,
      "step": 9760,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.463768115942029,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5776772247360482,
      "success_rate.epoch.env.math": 0.9756986634264885,
      "success_rate.epoch.env.sat": 0.100418410041841,
      "success_rate.epoch.env.science": 0.957176843774782,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6015115318827416,
      "success_rate.epoch.global": 0.8536293766011955,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951467803030303,
      "tokens_p.mean_in_band": 0.679931640625,
      "tokens_rate.above_band": 0.9428571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05714285714285714
    },
    {
      "epoch": 1.6231715425531914,
      "grad_norm": 170.28793044328873,
      "learning_rate": 1.6354183637922513e-07,
      "loss": 0.2531,
      "step": 9765,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5768072289156626,
      "success_rate.epoch.env.math": 0.9757281553398058,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9572107765451664,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6010968552968968,
      "success_rate.epoch.global": 0.8532923916751962,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4666666666666666,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9978021978021978,
      "tokens_p.mean_in_band": 0.6483373397435898,
      "tokens_rate.above_band": 0.9722222222222222,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027777777777777776
    },
    {
      "epoch": 1.624002659574468,
      "grad_norm": 64.14189895342564,
      "learning_rate": 1.6352671255681907e-07,
      "loss": 0.3442,
      "step": 9770,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5768072289156626,
      "success_rate.epoch.env.math": 0.9757281553398058,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9572784810126582,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601103010248487,
      "success_rate.epoch.global": 0.8534423994546694,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.987127253814147,
      "tokens_p.mean_in_band": 0.6112328506097561,
      "tokens_rate.above_band": 0.8146892655367232,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.18531073446327684
    },
    {
      "epoch": 1.6248337765957448,
      "grad_norm": 92.81192114351522,
      "learning_rate": 1.6351161797046246e-07,
      "loss": 0.3274,
      "step": 9775,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5774436090225564,
      "success_rate.epoch.env.math": 0.9757575757575757,
      "success_rate.epoch.env.sat": 0.0995850622406639,
      "success_rate.epoch.env.science": 0.957334737951014,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6011309302215491,
      "success_rate.epoch.global": 0.8534717494894486,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950657894736842,
      "tokens_p.mean_in_band": 0.50146484375,
      "tokens_rate.above_band": 0.9344262295081968,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06557377049180328
    },
    {
      "epoch": 1.6256648936170213,
      "grad_norm": 79.38673202262062,
      "learning_rate": 1.6349655264694446e-07,
      "loss": 0.352,
      "step": 9780,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5774436090225564,
      "success_rate.epoch.env.math": 0.9757575757575757,
      "success_rate.epoch.env.sat": 0.09917355371900827,
      "success_rate.epoch.env.science": 0.9573908469226723,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6010986211715493,
      "success_rate.epoch.global": 0.8534512070724244,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930555555555556,
      "tokens_p.mean_in_band": 0.609619140625,
      "tokens_rate.above_band": 0.9183673469387755,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08163265306122448
    },
    {
      "epoch": 1.6264960106382977,
      "grad_norm": 50.10934825445179,
      "learning_rate": 1.6348151661300235e-07,
      "loss": 0.2157,
      "step": 9785,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5774436090225564,
      "success_rate.epoch.env.math": 0.9757869249394673,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.9574132492113565,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014403353704385,
      "success_rate.epoch.global": 0.853550798504927,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9871987951807228,
      "tokens_p.mean_in_band": 0.6979166666666666,
      "tokens_rate.above_band": 0.9651162790697675,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03488372093023256
    },
    {
      "epoch": 1.6273271276595744,
      "grad_norm": 92.08101166147156,
      "learning_rate": 1.6346650989532143e-07,
      "loss": 0.2566,
      "step": 9790,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5774436090225564,
      "success_rate.epoch.env.math": 0.9758162031438936,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.9574579831932774,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014470637510155,
      "success_rate.epoch.global": 0.8536750976065184,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9945958646616542,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9925373134328358,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007462686567164179
    },
    {
      "epoch": 1.6281582446808511,
      "grad_norm": 57.95508685092905,
      "learning_rate": 1.634515325205349e-07,
      "loss": 0.2988,
      "step": 9795,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.45652173913043476,
      "success_rate.epoch.env.logic": 0.5774436090225564,
      "success_rate.epoch.env.math": 0.9758162031438936,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.9572851153039832,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014313484883524,
      "success_rate.epoch.global": 0.8537040176301068,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9945820433436533,
      "tokens_p.mean_below_band": 9.74978320300579e-10,
      "tokens_p.mean_in_band": 0.6742621527777778,
      "tokens_rate.above_band": 0.9714285714285714,
      "tokens_rate.below_band": 0.0015037593984962407,
      "tokens_rate.in_band": 0.02706766917293233
    },
    {
      "epoch": 1.6289893617021276,
      "grad_norm": 149.77229730209604,
      "learning_rate": 1.6343658451522397e-07,
      "loss": 0.2248,
      "step": 9800,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.5774436090225564,
      "success_rate.epoch.env.math": 0.9759326113116726,
      "success_rate.epoch.env.sat": 0.102880658436214,
      "success_rate.epoch.env.science": 0.9573074908328968,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601799412055854,
      "success_rate.epoch.global": 0.8538774128005419,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.984059633027523,
      "tokens_p.mean_in_band": 0.8650841346153846,
      "tokens_rate.above_band": 0.9767025089605734,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023297491039426525
    },
    {
      "epoch": 1.6298204787234043,
      "grad_norm": 21.134333729103908,
      "learning_rate": 1.6342166590591767e-07,
      "loss": 0.308,
      "step": 9805,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.5765765765765766,
      "success_rate.epoch.env.math": 0.9759326113116726,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9573521716378859,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016863217209665,
      "success_rate.epoch.global": 0.8536874154262517,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.993566833452466,
      "tokens_p.mean_in_band": 0.719640899122807,
      "tokens_rate.above_band": 0.9608516483516484,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03914835164835165
    },
    {
      "epoch": 1.630651595744681,
      "grad_norm": 70.64305279280978,
      "learning_rate": 1.634067767190929e-07,
      "loss": 0.4339,
      "step": 9810,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.460431654676259,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.5765765765765766,
      "success_rate.epoch.env.math": 0.9759615384615384,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9574078912986673,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6016940168855709,
      "success_rate.epoch.global": 0.8538357553227441,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921875,
      "tokens_p.mean_in_band": 0.6150568181818182,
      "tokens_rate.above_band": 0.907563025210084,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09243697478991597
    },
    {
      "epoch": 1.6314827127659575,
      "grad_norm": 31.51493105180416,
      "learning_rate": 1.6339191698117424e-07,
      "loss": 0.3018,
      "step": 9815,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.5757121439280359,
      "success_rate.epoch.env.math": 0.9759903961584634,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9571577847439916,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6012963369728714,
      "success_rate.epoch.global": 0.8534278959810875,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9994365743721829,
      "tokens_p.mean_below_band": 9.918585419654846e-08,
      "tokens_p.mean_in_band": 0.54364013671875,
      "tokens_rate.above_band": 0.9791929382093316,
      "tokens_rate.below_band": 0.0006305170239596469,
      "tokens_rate.in_band": 0.0201765447667087
    },
    {
      "epoch": 1.632313829787234,
      "grad_norm": 157.68248924518582,
      "learning_rate": 1.6337708671853417e-07,
      "loss": 0.3918,
      "step": 9820,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.460431654676259,
      "success_rate.epoch.env.logic": 0.5757121439280359,
      "success_rate.epoch.env.math": 0.9760191846522782,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9572248304642671,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6013050491741524,
      "success_rate.epoch.global": 0.8536009445100354,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9854484732824428,
      "tokens_p.mean_below_band": 4.544854164123535e-07,
      "tokens_p.mean_in_band": 0.15770862800565771,
      "tokens_rate.above_band": 0.2698249227600412,
      "tokens_rate.below_band": 0.0020597322348094747,
      "tokens_rate.in_band": 0.7281153450051493
    },
    {
      "epoch": 1.6331449468085106,
      "grad_norm": 345.0089355512192,
      "learning_rate": 1.6336228595749277e-07,
      "loss": 0.2504,
      "step": 9825,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45714285714285713,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.5769805680119582,
      "success_rate.epoch.env.math": 0.9760765550239234,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9572582746937712,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6017789853827458,
      "success_rate.epoch.global": 0.8537982145864915,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9979580965909091,
      "tokens_p.mean_in_band": 0.49609375,
      "tokens_rate.above_band": 0.9985815602836879,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0014184397163120568
    },
    {
      "epoch": 1.6339760638297873,
      "grad_norm": 25.660032222857822,
      "learning_rate": 1.6334751472431772e-07,
      "loss": 0.1606,
      "step": 9830,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45390070921985815,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.5769805680119582,
      "success_rate.epoch.env.math": 0.97610513739546,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9572916666666667,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6014898786937851,
      "success_rate.epoch.global": 0.8537529451363177,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994299674267101,
      "tokens_p.mean_in_band": 0.6787109375,
      "tokens_rate.above_band": 0.9935275080906149,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006472491909385114
    },
    {
      "epoch": 1.6348071808510638,
      "grad_norm": 81.76529913060513,
      "learning_rate": 1.6333277304522438e-07,
      "loss": 0.1528,
      "step": 9835,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.45390070921985815,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.5761194029850746,
      "success_rate.epoch.env.math": 0.9761336515513126,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9573361082206036,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.601418223301322,
      "success_rate.epoch.global": 0.8537323470073974,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9998337765957447,
      "tokens_p.mean_in_band": 0.6682942708333334,
      "tokens_rate.above_band": 0.9842931937172775,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015706806282722512
    },
    {
      "epoch": 1.6356382978723403,
      "grad_norm": 48.12581691359298,
      "learning_rate": 1.6331806094637558e-07,
      "loss": 0.2638,
      "step": 9840,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4507042253521127,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.5761194029850746,
      "success_rate.epoch.env.math": 0.9761336515513126,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9574025974025974,
      "success_rate.epoch.env.webshop": 0.5714285714285714,
      "success_rate.epoch.env_macro_mean": 0.6011336783298901,
      "success_rate.epoch.global": 0.8537363560033585,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977481036662452,
      "tokens_p.mean_in_band": 0.7026186342592593,
      "tokens_rate.above_band": 0.9669926650366748,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03300733496332518
    },
    {
      "epoch": 1.636469414893617,
      "grad_norm": 71.52089573257668,
      "learning_rate": 1.633033784538817e-07,
      "loss": 0.2687,
      "step": 9845,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.5761194029850746,
      "success_rate.epoch.env.math": 0.9761336515513126,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9574468085106383,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5943576657735087,
      "success_rate.epoch.global": 0.8535480624056366,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9943449575871819,
      "tokens_p.mean_in_band": 0.4790719696969697,
      "tokens_rate.above_band": 0.865415986949429,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13458401305057097
    },
    {
      "epoch": 1.6373005319148937,
      "grad_norm": 68.71381725162301,
      "learning_rate": 1.6328872559380057e-07,
      "loss": 0.2793,
      "step": 9850,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4642857142857143,
      "success_rate.epoch.env.logic": 0.5767511177347243,
      "success_rate.epoch.env.math": 0.9761620977353993,
      "success_rate.epoch.env.sat": 0.10245901639344263,
      "success_rate.epoch.env.science": 0.9574688796680498,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.594419686872704,
      "success_rate.epoch.global": 0.8536462699077955,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9969671741198858,
      "tokens_p.mean_in_band": 0.619140625,
      "tokens_rate.above_band": 0.9831618334892422,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01683816651075772
    },
    {
      "epoch": 1.6381316489361701,
      "grad_norm": 640.2945316924704,
      "learning_rate": 1.6327410239213746e-07,
      "loss": 0.3087,
      "step": 9855,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.5767511177347243,
      "success_rate.epoch.env.math": 0.9761904761904762,
      "success_rate.epoch.env.sat": 0.1016260162601626,
      "success_rate.epoch.env.science": 0.9574909279419388,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5940491977919211,
      "success_rate.epoch.global": 0.8532909060458884,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.45833333333333337,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9934192764578834,
      "tokens_p.mean_below_band": 1.5366822481155396e-07,
      "tokens_p.mean_in_band": 0.5515983166189111,
      "tokens_rate.above_band": 0.9134401972872996,
      "tokens_rate.below_band": 0.0004932182490752158,
      "tokens_rate.in_band": 0.08606658446362515
    },
    {
      "epoch": 1.6389627659574468,
      "grad_norm": 26.582517328401593,
      "learning_rate": 1.6325950887484494e-07,
      "loss": 0.236,
      "step": 9860,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.5767511177347243,
      "success_rate.epoch.env.math": 0.976218787158145,
      "success_rate.epoch.env.sat": 0.1016260162601626,
      "success_rate.epoch.env.science": 0.957545948744499,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5940567734073965,
      "success_rate.epoch.global": 0.8534381796888071,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9923052763819096,
      "tokens_p.mean_in_band": 0.8203125,
      "tokens_rate.above_band": 0.9802955665024631,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019704433497536946
    },
    {
      "epoch": 1.6397938829787235,
      "grad_norm": 119.06521143810635,
      "learning_rate": 1.6324494506782295e-07,
      "loss": 0.4888,
      "step": 9865,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.5765230312035661,
      "success_rate.epoch.env.math": 0.9762470308788599,
      "success_rate.epoch.env.sat": 0.10121457489878542,
      "success_rate.epoch.env.science": 0.9575898629428498,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5940051943188993,
      "success_rate.epoch.global": 0.8532999164578112,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9953225806451613,
      "tokens_p.mean_in_band": 0.6643518518518519,
      "tokens_rate.above_band": 0.9663341645885287,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03366583541147132
    },
    {
      "epoch": 1.640625,
      "grad_norm": 57.04424599716554,
      "learning_rate": 1.6323041099691862e-07,
      "loss": 0.2523,
      "step": 9870,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.5771513353115727,
      "success_rate.epoch.env.math": 0.976303317535545,
      "success_rate.epoch.env.sat": 0.10080645161290322,
      "success_rate.epoch.env.science": 0.9576227390180878,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5940333164601763,
      "success_rate.epoch.global": 0.8533044058744993,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9898574561403509,
      "tokens_p.mean_in_band": 0.6166666666666667,
      "tokens_rate.above_band": 0.9382716049382716,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06172839506172839
    },
    {
      "epoch": 1.6414561170212765,
      "grad_norm": 818.1965300739258,
      "learning_rate": 1.6321590668792644e-07,
      "loss": 0.1898,
      "step": 9875,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.5771513353115727,
      "success_rate.epoch.env.math": 0.9763593380614657,
      "success_rate.epoch.env.sat": 0.10080645161290322,
      "success_rate.epoch.env.science": 0.9576555641621483,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5940413933392654,
      "success_rate.epoch.global": 0.8534267133566783,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.986451048951049,
      "tokens_p.mean_in_band": 0.8716517857142857,
      "tokens_rate.above_band": 0.9533333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04666666666666667
    },
    {
      "epoch": 1.6422872340425532,
      "grad_norm": 61.02273438130012,
      "learning_rate": 1.6320143216658794e-07,
      "loss": 0.4092,
      "step": 9880,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46099290780141844,
      "success_rate.epoch.env.logic": 0.5762962962962963,
      "success_rate.epoch.env.math": 0.9763872491145218,
      "success_rate.epoch.env.sat": 0.10080645161290322,
      "success_rate.epoch.env.science": 0.9576992519989683,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5939701715096837,
      "success_rate.epoch.global": 0.8534066300183242,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9986432706222865,
      "tokens_p.mean_below_band": 2.1316282072803006e-12,
      "tokens_p.mean_in_band": 0.5434283088235294,
      "tokens_rate.above_band": 0.9517906336088154,
      "tokens_rate.below_band": 0.0013774104683195593,
      "tokens_rate.in_band": 0.046831955922865015
    },
    {
      "epoch": 1.6431183510638299,
      "grad_norm": 390.3387918215039,
      "learning_rate": 1.6318698745859192e-07,
      "loss": 0.4407,
      "step": 9885,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.5762962962962963,
      "success_rate.epoch.env.math": 0.9763872491145218,
      "success_rate.epoch.env.sat": 0.10040160642570281,
      "success_rate.epoch.env.science": 0.9575070821529745,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5942609723787521,
      "success_rate.epoch.global": 0.8532690068208285,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7142857142857143,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9879313509544787,
      "tokens_p.mean_in_band": 0.79547119140625,
      "tokens_rate.above_band": 0.9140939597315436,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08590604026845637
    },
    {
      "epoch": 1.6439494680851063,
      "grad_norm": 142.5144629987705,
      "learning_rate": 1.6317257258957414e-07,
      "loss": 0.264,
      "step": 9890,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.5769230769230769,
      "success_rate.epoch.env.math": 0.9764150943396226,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9575726407816919,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5942899340201063,
      "success_rate.epoch.global": 0.8533222591362126,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9886592741935484,
      "tokens_p.mean_in_band": 0.7634765625,
      "tokens_rate.above_band": 0.9253731343283582,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07462686567164178
    },
    {
      "epoch": 1.644780585106383,
      "grad_norm": 702.9882753113421,
      "learning_rate": 1.6315818758511747e-07,
      "loss": 0.3563,
      "step": 9895,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.5775480059084195,
      "success_rate.epoch.env.math": 0.9764150943396226,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9575944487278335,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5943487282866049,
      "success_rate.epoch.global": 0.8533953179478665,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9916974169741697,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.87890625,
      "tokens_rate.above_band": 0.9890510948905109,
      "tokens_rate.below_band": 0.0036496350364963502,
      "tokens_rate.in_band": 0.0072992700729927005
    },
    {
      "epoch": 1.6456117021276597,
      "grad_norm": 115.40388935494721,
      "learning_rate": 1.6314383247075182e-07,
      "loss": 0.268,
      "step": 9900,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4647887323943662,
      "success_rate.epoch.env.logic": 0.5775480059084195,
      "success_rate.epoch.env.math": 0.9764705882352941,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9576488706365504,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5943587206324584,
      "success_rate.epoch.global": 0.8535655058043118,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954128440366973,
      "tokens_p.mean_in_band": 0.40625,
      "tokens_rate.above_band": 0.9969512195121951,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003048780487804878
    },
    {
      "epoch": 1.6464428191489362,
      "grad_norm": 46.18645799126082,
      "learning_rate": 1.6312950727195392e-07,
      "loss": 0.2314,
      "step": 9905,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9765533411488863,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9576814567837907,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5947660988810897,
      "success_rate.epoch.global": 0.8537595230208679,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9999180865006553,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.6472739361702127,
      "grad_norm": 86.79595239960364,
      "learning_rate": 1.6311521201414756e-07,
      "loss": 0.2695,
      "step": 9910,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.44755244755244755,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766081871345029,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.9577356557377049,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5947397932960923,
      "success_rate.epoch.global": 0.8537876281839233,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9984046546546547,
      "tokens_p.mean_in_band": 0.5883413461538461,
      "tokens_rate.above_band": 0.9624277456647399,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03757225433526012
    },
    {
      "epoch": 1.6481050531914894,
      "grad_norm": 51.938943423946014,
      "learning_rate": 1.6310094672270324e-07,
      "loss": 0.3952,
      "step": 9915,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766081871345029,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.9577789150460594,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5944611802233969,
      "success_rate.epoch.global": 0.8537431829449678,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9992455527318933,
      "tokens_p.mean_in_band": 0.6865885416666667,
      "tokens_rate.above_band": 0.9812967581047382,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018703241895261846
    },
    {
      "epoch": 1.648936170212766,
      "grad_norm": 102.08126046801257,
      "learning_rate": 1.6308671142293845e-07,
      "loss": 0.3502,
      "step": 9920,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766355140186916,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.9578220858895705,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5944675891077332,
      "success_rate.epoch.global": 0.8538639365918098,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9941275167785235,
      "tokens_p.mean_in_band": 0.53125,
      "tokens_rate.above_band": 0.9977678571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.002232142857142857
    },
    {
      "epoch": 1.6497672872340425,
      "grad_norm": 35.110625670913386,
      "learning_rate": 1.630725061401173e-07,
      "loss": 0.2041,
      "step": 9925,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4444444444444444,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766355140186916,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.9576530612244898,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5944522232290895,
      "success_rate.epoch.global": 0.853891820580475,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995954425363276,
      "tokens_p.mean_in_band": 0.6505533854166666,
      "tokens_rate.above_band": 0.969270166453265,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030729833546734954
    },
    {
      "epoch": 1.650598404255319,
      "grad_norm": 102.56214821476766,
      "learning_rate": 1.6305833089945072e-07,
      "loss": 0.2444,
      "step": 9930,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4482758620689655,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.46853146853146854,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766355140186916,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.9576962283384302,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5948044582053134,
      "success_rate.epoch.global": 0.8540121931125392,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9928745928338762,
      "tokens_p.mean_in_band": 0.732421875,
      "tokens_rate.above_band": 0.9935275080906149,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006472491909385114
    },
    {
      "epoch": 1.6514295212765957,
      "grad_norm": 195.47797474383552,
      "learning_rate": 1.6304418572609623e-07,
      "loss": 0.2179,
      "step": 9935,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4520547945205479,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4722222222222222,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766627771295215,
      "success_rate.epoch.env.sat": 0.099601593625498,
      "success_rate.epoch.env.science": 0.9574847250509165,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5954667714749181,
      "success_rate.epoch.global": 0.8540157998683344,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.6666666666666666,
      "success_rate.window.env_macro_mean": 0.9333333333333332,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9891895085066162,
      "tokens_p.mean_in_band": 0.7721354166666666,
      "tokens_rate.above_band": 0.9592021758839528,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04079782411604715
    },
    {
      "epoch": 1.6522606382978724,
      "grad_norm": 118.87718007106503,
      "learning_rate": 1.6303007064515812e-07,
      "loss": 0.2728,
      "step": 9940,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4520547945205479,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4722222222222222,
      "success_rate.epoch.env.logic": 0.5781710914454278,
      "success_rate.epoch.env.math": 0.9766899766899767,
      "success_rate.epoch.env.sat": 0.0992063492063492,
      "success_rate.epoch.env.science": 0.9575063613231553,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5954352797852404,
      "success_rate.epoch.global": 0.8539473684210527,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9930334394904459,
      "tokens_p.mean_in_band": 0.6655815972222222,
      "tokens_rate.above_band": 0.8971428571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10285714285714286
    },
    {
      "epoch": 1.6530917553191489,
      "grad_norm": 60.66221421228457,
      "learning_rate": 1.6301598568168717e-07,
      "loss": 0.465,
      "step": 9945,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4520547945205479,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47586206896551725,
      "success_rate.epoch.env.logic": 0.5787923416789397,
      "success_rate.epoch.env.math": 0.9766899766899767,
      "success_rate.epoch.env.sat": 0.0992063492063492,
      "success_rate.epoch.env.science": 0.9572845156369184,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5958024844480194,
      "success_rate.epoch.global": 0.8539030402629416,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9977050388635754,
      "tokens_p.mean_below_band": 1.0058283805847168e-06,
      "tokens_p.mean_in_band": 0.5398448114809783,
      "tokens_rate.above_band": 0.9418149690773697,
      "tokens_rate.below_band": 0.00012621481761958855,
      "tokens_rate.in_band": 0.05805881610501073
    },
    {
      "epoch": 1.6539228723404256,
      "grad_norm": 52.79032072014623,
      "learning_rate": 1.6300193086068074e-07,
      "loss": 0.2674,
      "step": 9950,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4520547945205479,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47586206896551725,
      "success_rate.epoch.env.logic": 0.5770925110132159,
      "success_rate.epoch.env.math": 0.9766899766899767,
      "success_rate.epoch.env.sat": 0.0992063492063492,
      "success_rate.epoch.env.science": 0.9573062261753494,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.595649928072811,
      "success_rate.epoch.global": 0.8536705534570537,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.611111111111111,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9967152412804586,
      "tokens_p.mean_in_band": 0.6524251302083334,
      "tokens_rate.above_band": 0.9886632026452528,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011336797354747285
    },
    {
      "epoch": 1.6547539893617023,
      "grad_norm": 103.80170698926067,
      "learning_rate": 1.629879062070827e-07,
      "loss": 0.2125,
      "step": 9955,
      "success_rate.epoch.env.abd": 0.5853658536585366,
      "success_rate.epoch.env.agentgym:alfworld": 0.4520547945205479,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47586206896551725,
      "success_rate.epoch.env.logic": 0.5770925110132159,
      "success_rate.epoch.env.math": 0.9766899766899767,
      "success_rate.epoch.env.sat": 0.10276679841897234,
      "success_rate.epoch.env.science": 0.9573604060913705,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5959785307208696,
      "success_rate.epoch.global": 0.8538146021328958,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944196428571429,
      "tokens_p.mean_in_band": 0.6907894736842105,
      "tokens_rate.above_band": 0.9218106995884774,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07818930041152264
    },
    {
      "epoch": 1.6555851063829787,
      "grad_norm": 53.56394451332157,
      "learning_rate": 1.6297391174578338e-07,
      "loss": 0.1578,
      "step": 9960,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47586206896551725,
      "success_rate.epoch.env.logic": 0.5770925110132159,
      "success_rate.epoch.env.math": 0.9766899766899767,
      "success_rate.epoch.env.sat": 0.10276679841897234,
      "success_rate.epoch.env.science": 0.9573820395738204,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.597216839217836,
      "success_rate.epoch.global": 0.853910477127398,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9898330479452054,
      "tokens_p.mean_below_band": 8.754432201385498e-08,
      "tokens_p.mean_in_band": 0.8407738095238095,
      "tokens_rate.above_band": 0.9636963696369637,
      "tokens_rate.below_band": 0.0016501650165016502,
      "tokens_rate.in_band": 0.034653465346534656
    },
    {
      "epoch": 1.6564162234042552,
      "grad_norm": 74.24214927650222,
      "learning_rate": 1.6295994750161947e-07,
      "loss": 0.3009,
      "step": 9965,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.5,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4726027397260274,
      "success_rate.epoch.env.logic": 0.5770925110132159,
      "success_rate.epoch.env.math": 0.9767171129220024,
      "success_rate.epoch.env.sat": 0.10236220472440945,
      "success_rate.epoch.env.science": 0.9573928480852143,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5968872048368693,
      "success_rate.epoch.global": 0.853678518761265,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9858751846381093,
      "tokens_p.mean_below_band": 9.424984455108643e-07,
      "tokens_p.mean_in_band": 0.7144990808823529,
      "tokens_rate.above_band": 0.8316953316953317,
      "tokens_rate.below_band": 0.0012285012285012285,
      "tokens_rate.in_band": 0.16707616707616707
    },
    {
      "epoch": 1.657247340425532,
      "grad_norm": 28.241062189574908,
      "learning_rate": 1.6294601349937413e-07,
      "loss": 0.2326,
      "step": 9970,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4726027397260274,
      "success_rate.epoch.env.logic": 0.5770925110132159,
      "success_rate.epoch.env.math": 0.9767171129220024,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.9574036511156186,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5902860541143713,
      "success_rate.epoch.global": 0.8531434184675835,
      "success_rate.window.env.agentgym:sciworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 1.0,
      "tokens_p.mean_below_band": 5.893525667488575e-10,
      "tokens_p.mean_in_band": 0.6446759259259259,
      "tokens_rate.above_band": 0.9535472972972973,
      "tokens_rate.below_band": 0.0008445945945945946,
      "tokens_rate.in_band": 0.04560810810810811
    },
    {
      "epoch": 1.6580784574468086,
      "grad_norm": 168.5435991546668,
      "learning_rate": 1.629321097637768e-07,
      "loss": 0.215,
      "step": 9975,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5770925110132159,
      "success_rate.epoch.env.math": 0.9767981438515081,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.9574468085106383,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5906235018224598,
      "success_rate.epoch.global": 0.8533355134074558,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9880181347150259,
      "tokens_p.mean_below_band": 1.2514647096395493e-09,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9922879177377892,
      "tokens_rate.below_band": 0.002570694087403599,
      "tokens_rate.in_band": 0.005141388174807198
    },
    {
      "epoch": 1.658909574468085,
      "grad_norm": 55.94921874535783,
      "learning_rate": 1.6291823631950322e-07,
      "loss": 0.2574,
      "step": 9980,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5762463343108505,
      "success_rate.epoch.env.math": 0.9767981438515081,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.9574791192103265,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5905495140040347,
      "success_rate.epoch.global": 0.8532679738562091,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992559523809523,
      "tokens_p.mean_in_band": 0.44375,
      "tokens_rate.above_band": 0.9853372434017595,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01466275659824047
    },
    {
      "epoch": 1.6597406914893615,
      "grad_norm": 69.42549739576562,
      "learning_rate": 1.629043931911753e-07,
      "loss": 0.2439,
      "step": 9985,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.575402635431918,
      "success_rate.epoch.env.math": 0.9768518518518519,
      "success_rate.epoch.env.sat": 0.10116731517509728,
      "success_rate.epoch.env.science": 0.9575113808801214,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.590480629530508,
      "success_rate.epoch.global": 0.8532484492327783,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947323462414579,
      "tokens_p.mean_in_band": 0.6727430555555556,
      "tokens_rate.above_band": 0.9701657458563536,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02983425414364641
    },
    {
      "epoch": 1.6605718085106385,
      "grad_norm": 21.98729136609232,
      "learning_rate": 1.6289058040336123e-07,
      "loss": 0.251,
      "step": 9990,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.575402635431918,
      "success_rate.epoch.env.math": 0.9768518518518519,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.9575328614762386,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5904115627857007,
      "success_rate.epoch.global": 0.8530179445350734,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9968622795115333,
      "tokens_p.mean_in_band": 0.6169871794871795,
      "tokens_rate.above_band": 0.9497422680412371,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05025773195876289
    },
    {
      "epoch": 1.661402925531915,
      "grad_norm": 121.54956901877497,
      "learning_rate": 1.6287679798057533e-07,
      "loss": 0.2917,
      "step": 9995,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5745614035087719,
      "success_rate.epoch.env.math": 0.9768518518518519,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.9575971731448764,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903409336716545,
      "success_rate.epoch.global": 0.8530226495030145,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9981786809815951,
      "tokens_p.mean_below_band": 1.6916601452976465e-10,
      "tokens_p.mean_in_band": 0.544921875,
      "tokens_rate.above_band": 0.9775112443778111,
      "tokens_rate.below_band": 0.0014992503748125937,
      "tokens_rate.in_band": 0.020989505247376312
    },
    {
      "epoch": 1.6622340425531914,
      "grad_norm": 62.16036825763515,
      "learning_rate": 1.6286304594727802e-07,
      "loss": 0.2061,
      "step": 10000,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5751824817518248,
      "success_rate.epoch.env.math": 0.9768518518518519,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.9576292559899118,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5904003119523898,
      "success_rate.epoch.global": 0.8531183846279108,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9950244413407822,
      "tokens_p.mean_in_band": 0.859375,
      "tokens_rate.above_band": 0.9808219178082191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019178082191780823
    },
    {
      "epoch": 1.663065159574468,
      "grad_norm": 182.5395723992753,
      "learning_rate": 1.628493243278758e-07,
      "loss": 0.2208,
      "step": 10005,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5743440233236151,
      "success_rate.epoch.env.math": 0.9768518518518519,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.9576719576719577,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903279704300112,
      "success_rate.epoch.global": 0.8530751708428246,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9980755131964809,
      "tokens_p.mean_in_band": 0.7940340909090909,
      "tokens_rate.above_band": 0.9841269841269841,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015873015873015872
    },
    {
      "epoch": 1.6638962765957448,
      "grad_norm": 62.62513574123092,
      "learning_rate": 1.6283563314672118e-07,
      "loss": 0.2351,
      "step": 10010,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5743440233236151,
      "success_rate.epoch.env.math": 0.9769585253456221,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.9577039274924471,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903405743676712,
      "success_rate.epoch.global": 0.8532423208191127,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9896449704142012,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9941176470588236,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0058823529411764705
    },
    {
      "epoch": 1.6647273936170213,
      "grad_norm": 129.17829421785518,
      "learning_rate": 1.628219724281126e-07,
      "loss": 0.2205,
      "step": 10015,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5743440233236151,
      "success_rate.epoch.env.math": 0.9770114942528736,
      "success_rate.epoch.env.sat": 0.10038610038610038,
      "success_rate.epoch.env.science": 0.9577571033442294,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903502238912197,
      "success_rate.epoch.global": 0.8534090909090909,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9917452830188679,
      "tokens_p.mean_in_band": 0.577392578125,
      "tokens_rate.above_band": 0.8688524590163934,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13114754098360656
    },
    {
      "epoch": 1.6655585106382977,
      "grad_norm": 34.35706374232816,
      "learning_rate": 1.6280834219629457e-07,
      "loss": 0.1444,
      "step": 10020,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5743440233236151,
      "success_rate.epoch.env.math": 0.9770114942528736,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9578101456554495,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903199458844125,
      "success_rate.epoch.global": 0.8533895556276354,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.993408203125,
      "tokens_p.mean_in_band": 0.6596354166666667,
      "tokens_rate.above_band": 0.9446494464944649,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.055350553505535055
    },
    {
      "epoch": 1.6663896276595744,
      "grad_norm": 59.36509805064336,
      "learning_rate": 1.627947424754574e-07,
      "loss": 0.2737,
      "step": 10025,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4557823129251701,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5749636098981077,
      "success_rate.epoch.env.math": 0.9770114942528736,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9578524836929252,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903801208491368,
      "success_rate.epoch.global": 0.8535083454869551,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9884026508226691,
      "tokens_p.mean_in_band": 0.5456517269736842,
      "tokens_rate.above_band": 0.7421981004070556,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.25780189959294436
    },
    {
      "epoch": 1.6672207446808511,
      "grad_norm": 126.21370400205834,
      "learning_rate": 1.627811732897372e-07,
      "loss": 0.2022,
      "step": 10030,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5747460087082729,
      "success_rate.epoch.env.math": 0.9770114942528736,
      "success_rate.epoch.env.sat": 0.09961685823754789,
      "success_rate.epoch.env.science": 0.9578736208625878,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5906617154629246,
      "success_rate.epoch.global": 0.8533268576979116,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9981194690265487,
      "tokens_p.mean_in_band": 0.627197265625,
      "tokens_rate.above_band": 0.9724612736660929,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.027538726333907058
    },
    {
      "epoch": 1.6680518617021276,
      "grad_norm": 86.34771415370268,
      "learning_rate": 1.6276763466321599e-07,
      "loss": 0.3635,
      "step": 10035,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5753623188405798,
      "success_rate.epoch.env.math": 0.9770114942528736,
      "success_rate.epoch.env.sat": 0.09961685823754789,
      "success_rate.epoch.env.science": 0.9576759328825445,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5906997720222212,
      "success_rate.epoch.global": 0.8533074559275433,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9973783783783784,
      "tokens_p.mean_in_band": 0.5087890625,
      "tokens_rate.above_band": 0.996982108212977,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003017891787023065
    },
    {
      "epoch": 1.6688829787234043,
      "grad_norm": 61.34112800208512,
      "learning_rate": 1.627541266199215e-07,
      "loss": 0.2135,
      "step": 10040,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5745296671490593,
      "success_rate.epoch.env.math": 0.9770378874856487,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9577077077077077,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5909417804988917,
      "success_rate.epoch.global": 0.8532880917757312,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950703017832647,
      "tokens_p.mean_below_band": 2.5331974029541016e-07,
      "tokens_p.mean_in_band": 0.7449776785714286,
      "tokens_rate.above_band": 0.989145183175034,
      "tokens_rate.below_band": 0.0013568521031207597,
      "tokens_rate.in_band": 0.009497964721845319
    },
    {
      "epoch": 1.669714095744681,
      "grad_norm": 21.816264318816746,
      "learning_rate": 1.6274064918382726e-07,
      "loss": 0.2009,
      "step": 10045,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5745296671490593,
      "success_rate.epoch.env.math": 0.9770378874856487,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9577605598600349,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5909465852400123,
      "success_rate.epoch.global": 0.853406522441072,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9951117318435754,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9944444444444445,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005555555555555556
    },
    {
      "epoch": 1.6705452127659575,
      "grad_norm": 242.47526879546342,
      "learning_rate": 1.6272720237885236e-07,
      "loss": 0.2633,
      "step": 10050,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5745296671490593,
      "success_rate.epoch.env.math": 0.9770642201834863,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9578027465667915,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5909528142767936,
      "success_rate.epoch.global": 0.8535247620583966,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.998876953125,
      "tokens_p.mean_in_band": 0.2304322429906542,
      "tokens_rate.above_band": 0.7995003123048094,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.2004996876951905
    },
    {
      "epoch": 1.671376329787234,
      "grad_norm": 46.722616071256425,
      "learning_rate": 1.6271378622886158e-07,
      "loss": 0.2906,
      "step": 10055,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47619047619047616,
      "success_rate.epoch.env.logic": 0.5736994219653179,
      "success_rate.epoch.env.math": 0.977116704805492,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9578343313373253,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5908849801139571,
      "success_rate.epoch.global": 0.853505237711523,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9975400874635568,
      "tokens_p.mean_in_band": 0.6324404761904762,
      "tokens_rate.above_band": 0.9702970297029703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0297029702970297
    },
    {
      "epoch": 1.6722074468085106,
      "grad_norm": 34.4290066472054,
      "learning_rate": 1.6270040075766532e-07,
      "loss": 0.275,
      "step": 10060,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5736994219653179,
      "success_rate.epoch.env.math": 0.9771428571428571,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9576376775479691,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911912303037081,
      "success_rate.epoch.global": 0.8535093367675467,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950559701492537,
      "tokens_p.mean_below_band": 2.2351741790771484e-07,
      "tokens_p.mean_in_band": 0.8046875,
      "tokens_rate.above_band": 0.9852941176470589,
      "tokens_rate.below_band": 0.0029411764705882353,
      "tokens_rate.in_band": 0.011764705882352941
    },
    {
      "epoch": 1.6730385638297873,
      "grad_norm": 286.8431186446181,
      "learning_rate": 1.6268704598901948e-07,
      "loss": 0.4636,
      "step": 10065,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5736994219653179,
      "success_rate.epoch.env.math": 0.9771428571428571,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9576693227091634,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.591194107136544,
      "success_rate.epoch.global": 0.8536036036036037,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9937616333178222,
      "tokens_p.mean_in_band": 0.5348777770996094,
      "tokens_rate.above_band": 0.8935550935550935,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10644490644490645
    },
    {
      "epoch": 1.6738696808510638,
      "grad_norm": 47.635321748134814,
      "learning_rate": 1.6267372194662553e-07,
      "loss": 0.1339,
      "step": 10070,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5743145743145743,
      "success_rate.epoch.env.math": 0.9771949828962372,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9577009206270216,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5912576413202254,
      "success_rate.epoch.global": 0.8537447765991643,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9911380597014925,
      "tokens_p.mean_in_band": 0.875,
      "tokens_rate.above_band": 0.9804878048780488,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01951219512195122
    },
    {
      "epoch": 1.6747007978723403,
      "grad_norm": 145.78876682012896,
      "learning_rate": 1.626604286541304e-07,
      "loss": 0.1893,
      "step": 10075,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5749279538904899,
      "success_rate.epoch.env.math": 0.9771949828962372,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9577534791252486,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5913181811451474,
      "success_rate.epoch.global": 0.8538856775850996,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9951923076923077,
      "tokens_p.mean_in_band": 0.69287109375,
      "tokens_rate.above_band": 0.9391634980988594,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.060836501901140684
    },
    {
      "epoch": 1.675531914893617,
      "grad_norm": 36.710432490602784,
      "learning_rate": 1.626471661351264e-07,
      "loss": 0.2268,
      "step": 10080,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5732758620689655,
      "success_rate.epoch.env.math": 0.9772209567198178,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9575471698113207,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911515968440682,
      "success_rate.epoch.global": 0.8535685645549318,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9984214469178082,
      "tokens_p.mean_below_band": 9.74978320300579e-10,
      "tokens_p.mean_in_band": 0.5121837797619048,
      "tokens_rate.above_band": 0.9644921552436003,
      "tokens_rate.below_band": 0.0008257638315441783,
      "tokens_rate.in_band": 0.03468208092485549
    },
    {
      "epoch": 1.6763630319148937,
      "grad_norm": 409.60930771746746,
      "learning_rate": 1.6263393441315128e-07,
      "loss": 0.2764,
      "step": 10085,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5730659025787965,
      "success_rate.epoch.env.math": 0.9772468714448237,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9575787645745473,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911377377529831,
      "success_rate.epoch.global": 0.853549110719436,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.996875,
      "tokens_p.mean_in_band": 0.6640625,
      "tokens_rate.above_band": 0.9773371104815864,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0226628895184136
    },
    {
      "epoch": 1.6771941489361701,
      "grad_norm": 69.08792672327564,
      "learning_rate": 1.6262073351168805e-07,
      "loss": 0.2881,
      "step": 10090,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5722460658082976,
      "success_rate.epoch.env.math": 0.9772727272727273,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9576208178438662,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910693806917761,
      "success_rate.epoch.global": 0.8535296942532415,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944098240469208,
      "tokens_p.mean_in_band": 0.59375,
      "tokens_rate.above_band": 0.9855491329479769,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014450867052023121
    },
    {
      "epoch": 1.6780252659574468,
      "grad_norm": 29.666642928477334,
      "learning_rate": 1.6260756345416514e-07,
      "loss": 0.2498,
      "step": 10095,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9772727272727273,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9576732673267326,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.590999831155698,
      "success_rate.epoch.global": 0.8535103150487766,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9945488721804512,
      "tokens_p.mean_in_band": 0.7315848214285714,
      "tokens_rate.above_band": 0.9895833333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010416666666666666
    },
    {
      "epoch": 1.6788563829787235,
      "grad_norm": 59.49638031278995,
      "learning_rate": 1.6259442426395612e-07,
      "loss": 0.2152,
      "step": 10100,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9772727272727273,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9574678536102869,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5909811571814756,
      "success_rate.epoch.global": 0.8534441425603324,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957983193277311,
      "tokens_p.mean_below_band": 8.149072527885437e-09,
      "tokens_p.mean_in_band": 0.49609375,
      "tokens_rate.above_band": 0.9916666666666667,
      "tokens_rate.below_band": 0.004166666666666667,
      "tokens_rate.in_band": 0.004166666666666667
    },
    {
      "epoch": 1.6796875,
      "grad_norm": 11.649435299692804,
      "learning_rate": 1.6258131596437986e-07,
      "loss": 0.2046,
      "step": 10105,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4594594594594595,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9772727272727273,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9574783683559951,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5909821130674491,
      "success_rate.epoch.global": 0.8534675615212528,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966694078947368,
      "tokens_p.mean_in_band": 0.6659007352941176,
      "tokens_rate.above_band": 0.9781209781209781,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021879021879021878
    },
    {
      "epoch": 1.6805186170212765,
      "grad_norm": 69.37480691445676,
      "learning_rate": 1.6256823857870037e-07,
      "loss": 0.2424,
      "step": 10110,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4797297297297297,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9772727272727273,
      "success_rate.epoch.env.sat": 0.10305343511450382,
      "success_rate.epoch.env.science": 0.9575518262586377,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5907084619192088,
      "success_rate.epoch.global": 0.8534950526651771,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9929078014184397,
      "tokens_p.mean_in_band": 0.73046875,
      "tokens_rate.above_band": 0.9825783972125436,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.017421602787456445
    },
    {
      "epoch": 1.6813497340425532,
      "grad_norm": 54.02517472302923,
      "learning_rate": 1.6255519213012684e-07,
      "loss": 0.3338,
      "step": 10115,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9772985244040863,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.9575832305795314,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903853437992349,
      "success_rate.epoch.global": 0.8533163265306123,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.99124430523918,
      "tokens_p.mean_in_band": 0.5678310706967213,
      "tokens_rate.above_band": 0.8436899423446509,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15631005765534914
    },
    {
      "epoch": 1.6821808510638299,
      "grad_norm": 146.83583222193596,
      "learning_rate": 1.6254217664181346e-07,
      "loss": 0.2577,
      "step": 10120,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9773242630385488,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.9576145884672252,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5903905343921583,
      "success_rate.epoch.global": 0.8534098151688974,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.000234962406015,
      "tokens_p.mean_below_band": 2.384185791015625e-07,
      "tokens_p.mean_in_band": 0.6331521739130435,
      "tokens_rate.above_band": 0.9708029197080292,
      "tokens_rate.below_band": 0.0012165450121654502,
      "tokens_rate.in_band": 0.027980535279805353
    },
    {
      "epoch": 1.6830119680851063,
      "grad_norm": 0.0,
      "learning_rate": 1.625291921368596e-07,
      "loss": 0.3413,
      "step": 10125,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.5714285714285714,
      "success_rate.epoch.env.math": 0.9773242630385488,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.9576771653543307,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.590396223200077,
      "success_rate.epoch.global": 0.8535498248965298,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.99140625,
      "tokens_p.mean_in_band": 0.8859375,
      "tokens_rate.above_band": 0.9795918367346939,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02040816326530612
    },
    {
      "epoch": 1.683843085106383,
      "grad_norm": 66.18924581622116,
      "learning_rate": 1.6251623863830954e-07,
      "loss": 0.2457,
      "step": 10130,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.572039942938659,
      "success_rate.epoch.env.math": 0.9774011299435028,
      "success_rate.epoch.env.sat": 0.10266159695817491,
      "success_rate.epoch.env.science": 0.9576771653543307,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5904587903287172,
      "success_rate.epoch.global": 0.8536430162265352,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9966299019607843,
      "tokens_p.mean_in_band": 0.61796875,
      "tokens_rate.above_band": 0.9315068493150684,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0684931506849315
    },
    {
      "epoch": 1.6846742021276597,
      "grad_norm": 40.92045417282505,
      "learning_rate": 1.6250331616915255e-07,
      "loss": 0.2115,
      "step": 10135,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.572039942938659,
      "success_rate.epoch.env.math": 0.9774266365688488,
      "success_rate.epoch.env.sat": 0.10606060606060606,
      "success_rate.epoch.env.science": 0.9577083845586427,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5907729480498162,
      "success_rate.epoch.global": 0.8537593387378795,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9889794685990339,
      "tokens_p.mean_in_band": 0.73046875,
      "tokens_rate.above_band": 0.971830985915493,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028169014084507043
    },
    {
      "epoch": 1.6855053191489362,
      "grad_norm": 71.33398430746944,
      "learning_rate": 1.6249042475232288e-07,
      "loss": 0.2197,
      "step": 10140,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.572039942938659,
      "success_rate.epoch.env.math": 0.9774266365688488,
      "success_rate.epoch.env.sat": 0.10566037735849057,
      "success_rate.epoch.env.science": 0.9577395577395578,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5907393975478888,
      "success_rate.epoch.global": 0.853693407466243,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.994377444589309,
      "tokens_p.mean_in_band": 0.7024356617647058,
      "tokens_rate.above_band": 0.9783163265306123,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021683673469387755
    },
    {
      "epoch": 1.6863364361702127,
      "grad_norm": 263.2534420007352,
      "learning_rate": 1.6247756441069964e-07,
      "loss": 0.1926,
      "step": 10145,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.47651006711409394,
      "success_rate.epoch.env.logic": 0.572039942938659,
      "success_rate.epoch.env.math": 0.9774266365688488,
      "success_rate.epoch.env.sat": 0.10566037735849057,
      "success_rate.epoch.env.science": 0.9577914110429447,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5907441114845603,
      "success_rate.epoch.global": 0.8538095238095238,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9949596774193549,
      "tokens_p.mean_in_band": 0.671875,
      "tokens_rate.above_band": 0.9908675799086758,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0091324200913242
    },
    {
      "epoch": 1.6871675531914894,
      "grad_norm": 82.19205191007491,
      "learning_rate": 1.6246473516710675e-07,
      "loss": 0.2647,
      "step": 10150,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9774520856820744,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9578328021573915,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910867645173548,
      "success_rate.epoch.global": 0.8538363982244769,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9947677752293578,
      "tokens_p.mean_in_band": 0.5349392361111112,
      "tokens_rate.above_band": 0.960352422907489,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039647577092511016
    },
    {
      "epoch": 1.687998670212766,
      "grad_norm": 12.523020155808688,
      "learning_rate": 1.62451937044313e-07,
      "loss": 0.2109,
      "step": 10155,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9774520856820744,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9578534672874296,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.59108864316554,
      "success_rate.epoch.global": 0.8538827258320126,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9949006276150628,
      "tokens_p.mean_below_band": 4.926614671774132e-16,
      "tokens_p.mean_in_band": 0.68359375,
      "tokens_rate.above_band": 0.987603305785124,
      "tokens_rate.below_band": 0.004132231404958678,
      "tokens_rate.in_band": 0.008264462809917356
    },
    {
      "epoch": 1.6888297872340425,
      "grad_norm": 119.39907150208509,
      "learning_rate": 1.624391700650319e-07,
      "loss": 0.2037,
      "step": 10160,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9774774774774775,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9579050416054822,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910956400849451,
      "success_rate.epoch.global": 0.8540215326155794,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9958916083916084,
      "tokens_p.mean_in_band": 0.7164713541666666,
      "tokens_rate.above_band": 0.9834938101788171,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016506189821182942
    },
    {
      "epoch": 1.689660904255319,
      "grad_norm": 42.26509537627254,
      "learning_rate": 1.6242643425192172e-07,
      "loss": 0.1724,
      "step": 10165,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9775028121484814,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.957956489855781,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910667799835126,
      "success_rate.epoch.global": 0.8540249881385419,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9929298642533937,
      "tokens_p.mean_below_band": 2.983724378680108e-16,
      "tokens_p.mean_in_band": 0.5394287109375,
      "tokens_rate.above_band": 0.8700787401574803,
      "tokens_rate.below_band": 0.003937007874015748,
      "tokens_rate.in_band": 0.12598425196850394
    },
    {
      "epoch": 1.6904920212765957,
      "grad_norm": 28.70767043001444,
      "learning_rate": 1.6241372962758544e-07,
      "loss": 0.2155,
      "step": 10170,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9775280898876404,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.9577739809616793,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910524862421543,
      "success_rate.epoch.global": 0.8540284360189574,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921875,
      "tokens_p.mean_in_band": 0.65625,
      "tokens_rate.above_band": 0.9655172413793104,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.034482758620689655
    },
    {
      "epoch": 1.6913231382978724,
      "grad_norm": 35.94883382158681,
      "learning_rate": 1.6240105621457062e-07,
      "loss": 0.1965,
      "step": 10175,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9775784753363229,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.9578254509995124,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910617458318375,
      "success_rate.epoch.global": 0.8541896796591447,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9848790322580645,
      "tokens_p.mean_below_band": 1.5688783605583012e-11,
      "tokens_p.mean_in_band": 0.86328125,
      "tokens_rate.above_band": 0.9763779527559056,
      "tokens_rate.below_band": 0.007874015748031496,
      "tokens_rate.in_band": 0.015748031496062992
    },
    {
      "epoch": 1.6921542553191489,
      "grad_norm": 31.281027107994543,
      "learning_rate": 1.6238841403536948e-07,
      "loss": 0.2562,
      "step": 10180,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48,
      "success_rate.epoch.env.logic": 0.5726495726495726,
      "success_rate.epoch.env.math": 0.9775784753363229,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.9578460038986355,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5910636142772123,
      "success_rate.epoch.global": 0.8542356838618078,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9831288343558282,
      "tokens_p.mean_in_band": 0.6658653846153846,
      "tokens_rate.above_band": 0.7358916478555305,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.26410835214446954
    },
    {
      "epoch": 1.6929853723404256,
      "grad_norm": 63.50940821636169,
      "learning_rate": 1.6237580311241877e-07,
      "loss": 0.3285,
      "step": 10185,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5718349928876245,
      "success_rate.epoch.env.math": 0.9775784753363229,
      "success_rate.epoch.env.sat": 0.10486891385767791,
      "success_rate.epoch.env.science": 0.9578972986128012,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5913072891464387,
      "success_rate.epoch.global": 0.8542388906397731,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998769915651359,
      "tokens_p.mean_in_band": 0.47860054347826086,
      "tokens_rate.above_band": 0.9788990825688073,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02110091743119266
    },
    {
      "epoch": 1.6938164893617023,
      "grad_norm": 24.172246707858598,
      "learning_rate": 1.623632234680998e-07,
      "loss": 0.2436,
      "step": 10190,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5718349928876245,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9579280155642024,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5912767912486523,
      "success_rate.epoch.global": 0.8541961895764446,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9892015706806283,
      "tokens_p.mean_in_band": 0.6983695652173914,
      "tokens_rate.above_band": 0.8925233644859814,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10747663551401869
    },
    {
      "epoch": 1.6946476063829787,
      "grad_norm": 75.7898734696799,
      "learning_rate": 1.6235067512473837e-07,
      "loss": 0.2681,
      "step": 10195,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.573049645390071,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9579791110031577,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5913918592433253,
      "success_rate.epoch.global": 0.8543567159484114,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9973487482614742,
      "tokens_p.mean_in_band": 0.6661305147058824,
      "tokens_rate.above_band": 0.9769021739130435,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02309782608695652
    },
    {
      "epoch": 1.6954787234042552,
      "grad_norm": 312.48961708992596,
      "learning_rate": 1.623381581046047e-07,
      "loss": 0.2542,
      "step": 10200,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5736543909348442,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9580300824842309,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5914514698820386,
      "success_rate.epoch.global": 0.8544940289126336,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940944881889764,
      "tokens_p.mean_in_band": 0.6376953125,
      "tokens_rate.above_band": 0.9407407407407408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05925925925925926
    },
    {
      "epoch": 1.696309840425532,
      "grad_norm": 45.30250931641802,
      "learning_rate": 1.6232567242991345e-07,
      "loss": 0.2029,
      "step": 10205,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5742574257425742,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.9580606060606061,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5914737576797351,
      "success_rate.epoch.global": 0.8544512482336316,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9908216783216783,
      "tokens_p.mean_below_band": 5.617039278149605e-09,
      "tokens_p.mean_in_band": 0.6668198529411765,
      "tokens_rate.above_band": 0.9407894736842105,
      "tokens_rate.below_band": 0.003289473684210526,
      "tokens_rate.in_band": 0.05592105263157895
    },
    {
      "epoch": 1.6971409574468086,
      "grad_norm": 500.92703051734617,
      "learning_rate": 1.6231321812282362e-07,
      "loss": 0.2372,
      "step": 10210,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5734463276836158,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.9581012351658997,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5914037150475837,
      "success_rate.epoch.global": 0.8544085346721054,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936926605504587,
      "tokens_p.mean_in_band": 0.7523082386363636,
      "tokens_rate.above_band": 0.9674556213017751,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03254437869822485
    },
    {
      "epoch": 1.697972074468085,
      "grad_norm": 30.399568209774646,
      "learning_rate": 1.6230079520543854e-07,
      "loss": 0.262,
      "step": 10215,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5734463276836158,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.9581519109820996,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5914083219399655,
      "success_rate.epoch.global": 0.8545226524533626,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9971374045801527,
      "tokens_p.mean_in_band": 0.6201699746621622,
      "tokens_rate.above_band": 0.9340463458110517,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0659536541889483
    },
    {
      "epoch": 1.6988031914893615,
      "grad_norm": 63.983874781983076,
      "learning_rate": 1.6228840369980587e-07,
      "loss": 0.3167,
      "step": 10220,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4563758389261745,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5734463276836158,
      "success_rate.epoch.env.math": 0.9776035834266518,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.9581721470019342,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5914101615781323,
      "success_rate.epoch.global": 0.8545682494906754,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9881298449612403,
      "tokens_p.mean_in_band": 0.875,
      "tokens_rate.above_band": 0.9923076923076923,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007692307692307693
    },
    {
      "epoch": 1.6996343085106385,
      "grad_norm": 53.81705412365549,
      "learning_rate": 1.622760436279175e-07,
      "loss": 0.0836,
      "step": 10225,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5746478873239437,
      "success_rate.epoch.env.math": 0.9776536312849162,
      "success_rate.epoch.env.sat": 0.10408921933085502,
      "success_rate.epoch.env.science": 0.958192363460609,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5912491905203529,
      "success_rate.epoch.global": 0.8545710707576706,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.996079335793358,
      "tokens_p.mean_in_band": 0.376953125,
      "tokens_rate.above_band": 0.9963235294117647,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003676470588235294
    },
    {
      "epoch": 1.700465425531915,
      "grad_norm": 434.85146269190784,
      "learning_rate": 1.622637150117095e-07,
      "loss": 0.3462,
      "step": 10230,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5746478873239437,
      "success_rate.epoch.env.math": 0.9777034559643255,
      "success_rate.epoch.env.sat": 0.1037037037037037,
      "success_rate.epoch.env.science": 0.9582528957528957,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5912241760971296,
      "success_rate.epoch.global": 0.8546193528216351,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9899364406779662,
      "tokens_p.mean_in_band": 0.649658203125,
      "tokens_rate.above_band": 0.917098445595855,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08290155440414508
    },
    {
      "epoch": 1.7012965425531914,
      "grad_norm": 167.78709232247775,
      "learning_rate": 1.6225141787306218e-07,
      "loss": 0.3321,
      "step": 10235,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5738396624472574,
      "success_rate.epoch.env.math": 0.9777777777777777,
      "success_rate.epoch.env.sat": 0.1037037037037037,
      "success_rate.epoch.env.science": 0.9582629674306393,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911583732439032,
      "success_rate.epoch.global": 0.8545766947828803,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9990126382306477,
      "tokens_p.mean_in_band": 0.4296875,
      "tokens_rate.above_band": 0.975346687211094,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02465331278890601
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 175.3900408936531,
      "learning_rate": 1.622391522337999e-07,
      "loss": 0.3905,
      "step": 10240,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5738396624472574,
      "success_rate.epoch.env.math": 0.9778024417314095,
      "success_rate.epoch.env.sat": 0.1033210332103321,
      "success_rate.epoch.env.science": 0.9583132530120482,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911303986113277,
      "success_rate.epoch.global": 0.854579497581526,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9915570175438596,
      "tokens_p.mean_in_band": 0.6846354166666667,
      "tokens_rate.above_band": 0.95,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05
    },
    {
      "epoch": 1.7029587765957448,
      "grad_norm": 136.28871503097866,
      "learning_rate": 1.6222691811569124e-07,
      "loss": 0.2561,
      "step": 10245,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.574438202247191,
      "success_rate.epoch.env.math": 0.9778516057585825,
      "success_rate.epoch.env.sat": 0.1033210332103321,
      "success_rate.epoch.env.science": 0.9583734359961501,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911947519578011,
      "success_rate.epoch.global": 0.854783421626675,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9938271604938271,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7037898936170213,
      "grad_norm": 8.77574415806428,
      "learning_rate": 1.6221471554044868e-07,
      "loss": 0.2716,
      "step": 10250,
      "success_rate.epoch.env.abd": 0.5952380952380952,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.574438202247191,
      "success_rate.epoch.env.math": 0.9779005524861878,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.9584034623707622,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5911673988998442,
      "success_rate.epoch.global": 0.8547633872976339,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9933805418719212,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.6450892857142857,
      "tokens_rate.above_band": 0.875,
      "tokens_rate.below_band": 0.004310344827586207,
      "tokens_rate.in_band": 0.1206896551724138
    },
    {
      "epoch": 1.7046210106382977,
      "grad_norm": 39.22581444306054,
      "learning_rate": 1.6220254452972885e-07,
      "loss": 0.2501,
      "step": 10255,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5742296918767507,
      "success_rate.epoch.env.math": 0.977924944812362,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.958423455900024,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5920082119032622,
      "success_rate.epoch.global": 0.8547433903576983,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9961269744835966,
      "tokens_p.mean_in_band": 0.671875,
      "tokens_rate.above_band": 0.986810551558753,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013189448441247002
    },
    {
      "epoch": 1.7054521276595744,
      "grad_norm": 57.89307138942302,
      "learning_rate": 1.6219040510513229e-07,
      "loss": 0.1655,
      "step": 10260,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4533333333333333,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5742296918767507,
      "success_rate.epoch.env.math": 0.977924944812362,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.9584633853541417,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5920118418536365,
      "success_rate.epoch.global": 0.8548336959900529,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9973821989528796,
      "tokens_p.mean_in_band": 0.7799479166666666,
      "tokens_rate.above_band": 0.9922077922077922,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007792207792207792
    },
    {
      "epoch": 1.7062832446808511,
      "grad_norm": 31.96955060423507,
      "learning_rate": 1.6217829728820355e-07,
      "loss": 0.4077,
      "step": 10265,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.45695364238410596,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5734265734265734,
      "success_rate.epoch.env.math": 0.9779735682819384,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.9584932821497121,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5922750882959767,
      "success_rate.epoch.global": 0.8548362055581431,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960801393728222,
      "tokens_p.mean_in_band": 0.6644345238095238,
      "tokens_rate.above_band": 0.9761904761904762,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023809523809523808
    },
    {
      "epoch": 1.7071143617021276,
      "grad_norm": 43.90933398727875,
      "learning_rate": 1.6216622110043095e-07,
      "loss": 0.2693,
      "step": 10270,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5734265734265734,
      "success_rate.epoch.env.math": 0.9779735682819384,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.9585231359386238,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.592602590768184,
      "success_rate.epoch.global": 0.8549262994569433,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9950819672131147,
      "tokens_p.mean_below_band": 3.213062882423401e-08,
      "tokens_rate.above_band": 0.9983633387888707,
      "tokens_rate.below_band": 0.0016366612111292963,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7079454787234043,
      "grad_norm": 71.79104818520806,
      "learning_rate": 1.6215417656324685e-07,
      "loss": 0.2196,
      "step": 10275,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48344370860927155,
      "success_rate.epoch.env.logic": 0.5740223463687151,
      "success_rate.epoch.env.math": 0.977997799779978,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.958552946813608,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5926616648877444,
      "success_rate.epoch.global": 0.8550387596899225,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9926609848484849,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.708776595744681,
      "grad_norm": 244.5435219242203,
      "learning_rate": 1.6214216369802734e-07,
      "loss": 0.1956,
      "step": 10280,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5738161559888579,
      "success_rate.epoch.env.math": 0.977997799779978,
      "success_rate.epoch.env.sat": 0.10294117647058823,
      "success_rate.epoch.env.science": 0.9585827148671295,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5929545716447945,
      "success_rate.epoch.global": 0.8550185873605948,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976662777129521,
      "tokens_p.mean_in_band": 0.5078125,
      "tokens_rate.above_band": 0.9884659746251442,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011534025374855825
    },
    {
      "epoch": 1.7096077127659575,
      "grad_norm": 34.44395721733804,
      "learning_rate": 1.6213018252609225e-07,
      "loss": 0.301,
      "step": 10285,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5738161559888579,
      "success_rate.epoch.env.math": 0.978021978021978,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.958642122878317,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5929278909490402,
      "success_rate.epoch.global": 0.8550433168316832,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9981831395348837,
      "tokens_p.mean_in_band": 0.66875,
      "tokens_rate.above_band": 0.958217270194986,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04178272980501393
    },
    {
      "epoch": 1.710438829787234,
      "grad_norm": 116.68288408940043,
      "learning_rate": 1.621182330687053e-07,
      "loss": 0.2429,
      "step": 10290,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5738161559888579,
      "success_rate.epoch.env.math": 0.9780461031833151,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9586717630195891,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5929327787038228,
      "success_rate.epoch.global": 0.8551329622758194,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.990234375,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7112699468085106,
      "grad_norm": 114.45902887762509,
      "learning_rate": 1.6210631534707383e-07,
      "loss": 0.47,
      "step": 10295,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.42857142857142855,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5738161559888579,
      "success_rate.epoch.env.math": 0.9780701754385965,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9587013607066126,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5929376577894869,
      "success_rate.epoch.global": 0.8552224969097652,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9919407894736842,
      "tokens_p.mean_in_band": 0.5783203125,
      "tokens_rate.above_band": 0.9047619047619048,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09523809523809523
    },
    {
      "epoch": 1.7121010638297873,
      "grad_norm": 93.52849488096403,
      "learning_rate": 1.6209442938234884e-07,
      "loss": 0.3634,
      "step": 10300,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5738161559888579,
      "success_rate.epoch.env.math": 0.9780941949616648,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9587407584068686,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5964066264548108,
      "success_rate.epoch.global": 0.855356591540599,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9926714601769911,
      "tokens_p.mean_in_band": 0.8203125,
      "tokens_rate.above_band": 0.9658119658119658,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03418803418803419
    },
    {
      "epoch": 1.7129321808510638,
      "grad_norm": 89.39181197037155,
      "learning_rate": 1.6208257519562502e-07,
      "loss": 0.4059,
      "step": 10305,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4868421052631579,
      "success_rate.epoch.env.logic": 0.5736111111111111,
      "success_rate.epoch.env.math": 0.9780941949616648,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.958541815582559,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5963699003000784,
      "success_rate.epoch.global": 0.8551819864281308,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.7857142857142857,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995435393258427,
      "tokens_p.mean_in_band": 0.7138157894736842,
      "tokens_rate.above_band": 0.9740082079343365,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025991792065663474
    },
    {
      "epoch": 1.7137632978723403,
      "grad_norm": 20.732901057952994,
      "learning_rate": 1.6207075280794068e-07,
      "loss": 0.3115,
      "step": 10310,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48366013071895425,
      "success_rate.epoch.env.logic": 0.5736111111111111,
      "success_rate.epoch.env.math": 0.9780941949616648,
      "success_rate.epoch.env.sat": 0.10256410256410256,
      "success_rate.epoch.env.science": 0.9585714285714285,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5960833219768662,
      "success_rate.epoch.global": 0.8551171393341553,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9855603448275863,
      "tokens_p.mean_below_band": 6.230038707144558e-11,
      "tokens_p.mean_in_band": 0.5818452380952381,
      "tokens_rate.above_band": 0.7604895104895105,
      "tokens_rate.below_band": 0.0008741258741258741,
      "tokens_rate.in_band": 0.23863636363636365
    },
    {
      "epoch": 1.714594414893617,
      "grad_norm": 106.56519575102756,
      "learning_rate": 1.6205896224027763e-07,
      "loss": 0.2949,
      "step": 10315,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48366013071895425,
      "success_rate.epoch.env.logic": 0.5736111111111111,
      "success_rate.epoch.env.math": 0.9781181619256017,
      "success_rate.epoch.env.sat": 0.10181818181818182,
      "success_rate.epoch.env.science": 0.9586108468125595,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5960212732913341,
      "success_rate.epoch.global": 0.8549653579676675,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.6111111111111112,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9947660098522167,
      "tokens_p.mean_below_band": 4.3655745685100555e-09,
      "tokens_p.mean_in_band": 0.6572916666666667,
      "tokens_rate.above_band": 0.8675213675213675,
      "tokens_rate.below_band": 0.004273504273504274,
      "tokens_rate.in_band": 0.1282051282051282
    },
    {
      "epoch": 1.7154255319148937,
      "grad_norm": 102.50648502958545,
      "learning_rate": 1.6204720351356125e-07,
      "loss": 0.2732,
      "step": 10320,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.48366013071895425,
      "success_rate.epoch.env.logic": 0.5736111111111111,
      "success_rate.epoch.env.math": 0.9781181619256017,
      "success_rate.epoch.env.sat": 0.10144927536231885,
      "success_rate.epoch.env.science": 0.9586501901140685,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5959913130045748,
      "success_rate.epoch.global": 0.8549230769230769,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9971969696969697,
      "tokens_p.mean_in_band": 0.6460822610294118,
      "tokens_rate.above_band": 0.9604190919674039,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03958090803259604
    },
    {
      "epoch": 1.7162566489361701,
      "grad_norm": 101.46431613221785,
      "learning_rate": 1.6203547664866039e-07,
      "loss": 0.2174,
      "step": 10325,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.487012987012987,
      "success_rate.epoch.env.logic": 0.5736111111111111,
      "success_rate.epoch.env.math": 0.9781181619256017,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.9587188612099644,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5962690661426279,
      "success_rate.epoch.global": 0.8549700414810263,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9938969258589512,
      "tokens_p.mean_in_band": 0.7200520833333334,
      "tokens_rate.above_band": 0.968476357267951,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03152364273204904
    },
    {
      "epoch": 1.7170877659574468,
      "grad_norm": 135.6309527122214,
      "learning_rate": 1.620237816663874e-07,
      "loss": 0.2315,
      "step": 10330,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.487012987012987,
      "success_rate.epoch.env.logic": 0.5736111111111111,
      "success_rate.epoch.env.math": 0.9781420765027322,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.958757999525954,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5962747982238206,
      "success_rate.epoch.global": 0.855081363217685,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9896907216494846,
      "tokens_p.mean_in_band": 0.7215909090909091,
      "tokens_rate.above_band": 0.9463414634146341,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05365853658536585
    },
    {
      "epoch": 1.7179188829787235,
      "grad_norm": 78.59761609004616,
      "learning_rate": 1.6201211858749794e-07,
      "loss": 0.4263,
      "step": 10335,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.487012987012987,
      "success_rate.epoch.env.logic": 0.574792243767313,
      "success_rate.epoch.env.math": 0.9781420765027322,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.9587970636987924,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5963857252082788,
      "success_rate.epoch.global": 0.8552147239263803,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9918154761904762,
      "tokens_p.mean_in_band": 0.8854166666666666,
      "tokens_rate.above_band": 0.9739130434782609,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02608695652173913
    },
    {
      "epoch": 1.71875,
      "grad_norm": 60.52785511157568,
      "learning_rate": 1.6200048743269118e-07,
      "loss": 0.1425,
      "step": 10340,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.487012987012987,
      "success_rate.epoch.env.logic": 0.574792243767313,
      "success_rate.epoch.env.math": 0.9781420765027322,
      "success_rate.epoch.env.sat": 0.10108303249097472,
      "success_rate.epoch.env.science": 0.9588263132986276,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5963883842628093,
      "success_rate.epoch.global": 0.8552813122796259,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0004222972972974,
      "tokens_p.mean_in_band": 0.6685267857142857,
      "tokens_rate.above_band": 0.976897689768977,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0231023102310231
    },
    {
      "epoch": 1.7195811170212765,
      "grad_norm": 103.86867022095156,
      "learning_rate": 1.6198888822260952e-07,
      "loss": 0.323,
      "step": 10345,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.487012987012987,
      "success_rate.epoch.env.logic": 0.5753803596127247,
      "success_rate.epoch.env.math": 0.9781897491821155,
      "success_rate.epoch.env.sat": 0.10071942446043165,
      "success_rate.epoch.env.science": 0.9588457899716177,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5964148985507403,
      "success_rate.epoch.global": 0.8552611425945781,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.5599999999999999,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9885367298578199,
      "tokens_p.mean_below_band": 4.4411353883333504e-07,
      "tokens_p.mean_in_band": 0.5539869225543478,
      "tokens_rate.above_band": 0.7403508771929824,
      "tokens_rate.below_band": 0.0014035087719298245,
      "tokens_rate.in_band": 0.2582456140350877
    },
    {
      "epoch": 1.7204122340425532,
      "grad_norm": 274.99167270874347,
      "learning_rate": 1.6197732097783875e-07,
      "loss": 0.2658,
      "step": 10350,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.487012987012987,
      "success_rate.epoch.env.logic": 0.576551724137931,
      "success_rate.epoch.env.math": 0.9781897491821155,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.9588652482269504,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.596490336847029,
      "success_rate.epoch.global": 0.8552188552188552,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9960550742574258,
      "tokens_p.mean_in_band": 0.7421875,
      "tokens_rate.above_band": 0.9607609988109393,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039239001189060645
    },
    {
      "epoch": 1.7212433510638299,
      "grad_norm": 57.14280439553784,
      "learning_rate": 1.619657857189079e-07,
      "loss": 0.1345,
      "step": 10355,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4605263157894737,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49032258064516127,
      "success_rate.epoch.env.logic": 0.576551724137931,
      "success_rate.epoch.env.math": 0.9782135076252724,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.958913813459268,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.596797783874997,
      "success_rate.epoch.global": 0.855373796055649,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9863119834710744,
      "tokens_p.mean_in_band": 0.8367660984848485,
      "tokens_rate.above_band": 0.9361702127659575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06382978723404255
    },
    {
      "epoch": 1.7220744680851063,
      "grad_norm": 39.674688935714364,
      "learning_rate": 1.6195428246628921e-07,
      "loss": 0.2505,
      "step": 10360,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.46405228758169936,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49032258064516127,
      "success_rate.epoch.env.logic": 0.576551724137931,
      "success_rate.epoch.env.math": 0.9782135076252724,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.958913813459268,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5971183267651994,
      "success_rate.epoch.global": 0.8553959033934576,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.0006067961165048,
      "tokens_p.mean_in_band": 0.48388671875,
      "tokens_rate.above_band": 0.9914438502673797,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008556149732620321
    },
    {
      "epoch": 1.722905585106383,
      "grad_norm": 146.885037908392,
      "learning_rate": 1.6194281124039818e-07,
      "loss": 0.279,
      "step": 10365,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.46405228758169936,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4935897435897436,
      "success_rate.epoch.env.logic": 0.576551724137931,
      "success_rate.epoch.env.math": 0.9782608695652174,
      "success_rate.epoch.env.sat": 0.1003584229390681,
      "success_rate.epoch.env.science": 0.9589428975932044,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5974222912214233,
      "success_rate.epoch.global": 0.8555284056200366,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9996926229508196,
      "tokens_p.mean_in_band": 0.6299252717391305,
      "tokens_rate.above_band": 0.9875876956287102,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0124123043712898
    },
    {
      "epoch": 1.7237367021276597,
      "grad_norm": 63.79654858497648,
      "learning_rate": 1.6193137206159332e-07,
      "loss": 0.2423,
      "step": 10370,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4935897435897436,
      "success_rate.epoch.env.logic": 0.576551724137931,
      "success_rate.epoch.env.math": 0.9783315276273022,
      "success_rate.epoch.env.sat": 0.1,
      "success_rate.epoch.env.science": 0.9589428975932044,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5977125107735857,
      "success_rate.epoch.global": 0.8554860369296505,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9898549910071942,
      "tokens_p.mean_below_band": 7.338821887969971e-07,
      "tokens_p.mean_in_band": 0.5164233576642335,
      "tokens_rate.above_band": 0.8017303532804614,
      "tokens_rate.below_band": 0.0007209805335255948,
      "tokens_rate.in_band": 0.19754866618601297
    },
    {
      "epoch": 1.7245678191489362,
      "grad_norm": 173.8553614973995,
      "learning_rate": 1.6191996495017648e-07,
      "loss": 0.2652,
      "step": 10375,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4935897435897436,
      "success_rate.epoch.env.logic": 0.576551724137931,
      "success_rate.epoch.env.math": 0.9783549783549783,
      "success_rate.epoch.env.sat": 0.099644128113879,
      "success_rate.epoch.env.science": 0.9590009425070688,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5976875674786238,
      "success_rate.epoch.global": 0.8555098308184728,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9904371584699454,
      "tokens_p.mean_in_band": 0.6208333333333333,
      "tokens_rate.above_band": 0.9242424242424242,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07575757575757576
    },
    {
      "epoch": 1.7253989361702127,
      "grad_norm": 45.36719262322075,
      "learning_rate": 1.6190858992639246e-07,
      "loss": 0.3356,
      "step": 10380,
      "success_rate.epoch.env.abd": 0.6046511627906976,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49044585987261147,
      "success_rate.epoch.env.logic": 0.5757575757575758,
      "success_rate.epoch.env.math": 0.9783549783549783,
      "success_rate.epoch.env.sat": 0.099644128113879,
      "success_rate.epoch.env.science": 0.9590491880442457,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5973339505185956,
      "success_rate.epoch.global": 0.8553593179049939,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9920753588516746,
      "tokens_p.mean_in_band": 0.6927816901408451,
      "tokens_rate.above_band": 0.8982808022922636,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1017191977077364
    },
    {
      "epoch": 1.7262300531914894,
      "grad_norm": 57.86538853952683,
      "learning_rate": 1.6189724701042907e-07,
      "loss": 0.2898,
      "step": 10385,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4936708860759494,
      "success_rate.epoch.env.logic": 0.5757575757575758,
      "success_rate.epoch.env.math": 0.978401727861771,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9590780809031044,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5984187251951973,
      "success_rate.epoch.global": 0.8553832116788321,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949825479930192,
      "tokens_p.mean_in_band": 0.7357536764705882,
      "tokens_rate.above_band": 0.9711864406779661,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0288135593220339
    },
    {
      "epoch": 1.727061170212766,
      "grad_norm": 58.51387472457898,
      "learning_rate": 1.618859362224173e-07,
      "loss": 0.2234,
      "step": 10390,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49056603773584906,
      "success_rate.epoch.env.logic": 0.5757575757575758,
      "success_rate.epoch.env.math": 0.978401727861771,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9590973201692524,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5981382152793835,
      "success_rate.epoch.global": 0.8552971576227391,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9902991107518189,
      "tokens_p.mean_in_band": 0.6035067873303167,
      "tokens_rate.above_band": 0.8484224965706447,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.15157750342935528
    },
    {
      "epoch": 1.7278922872340425,
      "grad_norm": 498.98309869079554,
      "learning_rate": 1.6187465758243098e-07,
      "loss": 0.1654,
      "step": 10395,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49056603773584906,
      "success_rate.epoch.env.logic": 0.5757575757575758,
      "success_rate.epoch.env.math": 0.9784250269687162,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9591357444809769,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5981438264992626,
      "success_rate.epoch.global": 0.8554070473876063,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9881198347107438,
      "tokens_p.mean_in_band": 0.84375,
      "tokens_rate.above_band": 0.952755905511811,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.047244094488188976
    },
    {
      "epoch": 1.728723404255319,
      "grad_norm": 147.55376008926604,
      "learning_rate": 1.6186341111048696e-07,
      "loss": 0.3727,
      "step": 10400,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49056603773584906,
      "success_rate.epoch.env.logic": 0.5749656121045392,
      "success_rate.epoch.env.math": 0.978448275862069,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9591453392815215,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5980748155938863,
      "success_rate.epoch.global": 0.8553210869895248,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9936509986225895,
      "tokens_p.mean_in_band": 0.681586869266055,
      "tokens_rate.above_band": 0.9301729660474055,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06982703395259449
    },
    {
      "epoch": 1.7295545212765957,
      "grad_norm": 104.33171998318714,
      "learning_rate": 1.6185219682654495e-07,
      "loss": 0.1567,
      "step": 10405,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49056603773584906,
      "success_rate.epoch.env.logic": 0.5755494505494505,
      "success_rate.epoch.env.math": 0.978448275862069,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9591740966682308,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5981305061240336,
      "success_rate.epoch.global": 0.8554088909118495,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.999304008908686,
      "tokens_p.mean_in_band": 0.7515625,
      "tokens_rate.above_band": 0.9889867841409692,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011013215859030838
    },
    {
      "epoch": 1.7303856382978724,
      "grad_norm": 19.196243021943218,
      "learning_rate": 1.6184101475050756e-07,
      "loss": 0.2917,
      "step": 10410,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4675324675324675,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49056603773584906,
      "success_rate.epoch.env.logic": 0.5755494505494505,
      "success_rate.epoch.env.math": 0.9784714747039828,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9592123769338959,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5981360951338135,
      "success_rate.epoch.global": 0.8555184960582171,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9931437644341802,
      "tokens_p.mean_in_band": 0.74609375,
      "tokens_rate.above_band": 0.9665178571428571,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033482142857142856
    },
    {
      "epoch": 1.7312167553191489,
      "grad_norm": 45.34125122882448,
      "learning_rate": 1.6182986490222024e-07,
      "loss": 0.302,
      "step": 10415,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49056603773584906,
      "success_rate.epoch.env.logic": 0.5747599451303155,
      "success_rate.epoch.env.math": 0.978494623655914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9592314901593252,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5977939513390876,
      "success_rate.epoch.global": 0.8553249507650356,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.3666666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9997020262216925,
      "tokens_p.mean_below_band": 3.259629011154175e-07,
      "tokens_p.mean_in_band": 0.6005284926470589,
      "tokens_rate.above_band": 0.9789964994165694,
      "tokens_rate.below_band": 0.0011668611435239206,
      "tokens_rate.in_band": 0.019836639439906652
    },
    {
      "epoch": 1.7320478723404256,
      "grad_norm": 79.44963280425318,
      "learning_rate": 1.6181874730147124e-07,
      "loss": 0.3958,
      "step": 10420,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5747599451303155,
      "success_rate.epoch.env.math": 0.978494623655914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9592601264340904,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5975178239335346,
      "success_rate.epoch.global": 0.8552611657834973,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9979173750425026,
      "tokens_p.mean_in_band": 0.680908203125,
      "tokens_rate.above_band": 0.9387168847749761,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.061283115225023936
    },
    {
      "epoch": 1.7328789893617023,
      "grad_norm": 181.90025568672738,
      "learning_rate": 1.6180766196799153e-07,
      "loss": 0.2172,
      "step": 10425,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5747599451303155,
      "success_rate.epoch.env.math": 0.978494623655914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9593172784662146,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5975230195728186,
      "success_rate.epoch.global": 0.855392527605506,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9909957627118644,
      "tokens_p.mean_in_band": 0.880859375,
      "tokens_rate.above_band": 0.9672131147540983,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03278688524590164
    },
    {
      "epoch": 1.7337101063829787,
      "grad_norm": 64.85418381299172,
      "learning_rate": 1.6179660892145494e-07,
      "loss": 0.1828,
      "step": 10430,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5747599451303155,
      "success_rate.epoch.env.math": 0.978494623655914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9593647828117702,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5975273381496873,
      "success_rate.epoch.global": 0.8555018137847642,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952496859296482,
      "tokens_p.mean_in_band": 0.5434027777777778,
      "tokens_rate.above_band": 0.9778869778869779,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022113022113022112
    },
    {
      "epoch": 1.7345412234042552,
      "grad_norm": 36.679096149326476,
      "learning_rate": 1.617855881814779e-07,
      "loss": 0.2724,
      "step": 10435,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5753424657534246,
      "success_rate.epoch.env.math": 0.9785177228786252,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9593932322053675,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5975849808078162,
      "success_rate.epoch.global": 0.855610934904093,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9967447916666666,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.735372340425532,
      "grad_norm": 59.830329808567896,
      "learning_rate": 1.6177459976761948e-07,
      "loss": 0.2245,
      "step": 10440,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4875,
      "success_rate.epoch.env.logic": 0.5759233926128591,
      "success_rate.epoch.env.math": 0.9785637727759914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9594216417910447,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.597644561384405,
      "success_rate.epoch.global": 0.8557416628942206,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9916125541125541,
      "tokens_p.mean_in_band": 0.86171875,
      "tokens_rate.above_band": 0.9788135593220338,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0211864406779661
    },
    {
      "epoch": 1.7362034574468086,
      "grad_norm": 144.78075304979205,
      "learning_rate": 1.617636436993815e-07,
      "loss": 0.2663,
      "step": 10445,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4906832298136646,
      "success_rate.epoch.env.logic": 0.5770804911323328,
      "success_rate.epoch.env.math": 0.9785637727759914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.95947834187238,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5980442912402663,
      "success_rate.epoch.global": 0.8559373116335142,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9901256732495511,
      "tokens_p.mean_in_band": 0.87734375,
      "tokens_rate.above_band": 0.982363315696649,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01763668430335097
    },
    {
      "epoch": 1.737034574468085,
      "grad_norm": 49.76619192841472,
      "learning_rate": 1.617527199962082e-07,
      "loss": 0.3506,
      "step": 10450,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4906832298136646,
      "success_rate.epoch.env.logic": 0.5770804911323328,
      "success_rate.epoch.env.math": 0.9785637727759914,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9595160539785947,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5980477196135585,
      "success_rate.epoch.global": 0.8560240963855422,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9980459835691465,
      "tokens_p.mean_in_band": 0.6064453125,
      "tokens_rate.above_band": 0.9856050382366172,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014394961763382817
    },
    {
      "epoch": 1.7378656914893615,
      "grad_norm": 45.83232461524707,
      "learning_rate": 1.6174182867748652e-07,
      "loss": 0.245,
      "step": 10455,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4906832298136646,
      "success_rate.epoch.env.logic": 0.5770804911323328,
      "success_rate.epoch.env.math": 0.9785867237687366,
      "success_rate.epoch.env.sat": 0.09929078014184398,
      "success_rate.epoch.env.science": 0.9595630955147572,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.598054082570732,
      "success_rate.epoch.global": 0.8561540776406861,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.000457579672696,
      "tokens_p.mean_in_band": 0.5912298387096774,
      "tokens_rate.above_band": 0.9739932885906041,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026006711409395974
    },
    {
      "epoch": 1.7386968085106385,
      "grad_norm": 14.621711006868432,
      "learning_rate": 1.617309697625459e-07,
      "loss": 0.1439,
      "step": 10460,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4906832298136646,
      "success_rate.epoch.env.logic": 0.5776566757493188,
      "success_rate.epoch.env.math": 0.9786324786324786,
      "success_rate.epoch.env.sat": 0.0989399293286219,
      "success_rate.epoch.env.science": 0.9595912679981421,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5980812881299039,
      "success_rate.epoch.global": 0.8561551179918834,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9956121575342466,
      "tokens_p.mean_in_band": 0.7606336805555556,
      "tokens_rate.above_band": 0.9419354838709677,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05806451612903226
    },
    {
      "epoch": 1.739527925531915,
      "grad_norm": 62.87382226545363,
      "learning_rate": 1.6172014327065827e-07,
      "loss": 0.3308,
      "step": 10465,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4906832298136646,
      "success_rate.epoch.env.logic": 0.5776566757493188,
      "success_rate.epoch.env.math": 0.9786780383795309,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9596287703016241,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.59805716831333,
      "success_rate.epoch.global": 0.8561561561561561,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995752427184466,
      "tokens_p.mean_in_band": 0.6630859375,
      "tokens_rate.above_band": 0.865546218487395,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13445378151260504
    },
    {
      "epoch": 1.7403590425531914,
      "grad_norm": 34.247594341288874,
      "learning_rate": 1.61709349221038e-07,
      "loss": 0.2736,
      "step": 10470,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4906832298136646,
      "success_rate.epoch.env.logic": 0.5760869565217391,
      "success_rate.epoch.env.math": 0.9786780383795309,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9596474953617811,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5979161688435642,
      "success_rate.epoch.global": 0.8559423769507803,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9963070497147515,
      "tokens_p.mean_in_band": 0.5689019097222222,
      "tokens_rate.above_band": 0.9714964370546318,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028503562945368172
    },
    {
      "epoch": 1.741190159574468,
      "grad_norm": 269.5388240565678,
      "learning_rate": 1.6169858763284178e-07,
      "loss": 0.1886,
      "step": 10475,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49079754601226994,
      "success_rate.epoch.env.logic": 0.5760869565217391,
      "success_rate.epoch.env.math": 0.9786780383795309,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9596848934198332,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5979299610487149,
      "success_rate.epoch.global": 0.8559220389805098,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9930200180614088,
      "tokens_p.mean_in_band": 0.6934956395348837,
      "tokens_rate.above_band": 0.987221396731055,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.012778603268945022
    },
    {
      "epoch": 1.7420212765957448,
      "grad_norm": 229.2316977777791,
      "learning_rate": 1.616878585251689e-07,
      "loss": 0.2363,
      "step": 10480,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49079754601226994,
      "success_rate.epoch.env.logic": 0.5772357723577236,
      "success_rate.epoch.env.math": 0.9786780383795309,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9597128965038203,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5980369445868942,
      "success_rate.epoch.global": 0.8560299625468165,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.996871362048894,
      "tokens_p.mean_in_band": 0.7535807291666666,
      "tokens_rate.above_band": 0.9930635838150289,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006936416184971098
    },
    {
      "epoch": 1.7428523936170213,
      "grad_norm": 284.467066088806,
      "learning_rate": 1.6167716191706087e-07,
      "loss": 0.2567,
      "step": 10485,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49079754601226994,
      "success_rate.epoch.env.logic": 0.5772357723577236,
      "success_rate.epoch.env.math": 0.9786780383795309,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9597501734906315,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.598040333403877,
      "success_rate.epoch.global": 0.8561161850576433,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963804713804714,
      "tokens_p.mean_in_band": 0.6646581338652482,
      "tokens_rate.above_band": 0.9132841328413284,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08671586715867159
    },
    {
      "epoch": 1.7436835106382977,
      "grad_norm": 139.3418643651137,
      "learning_rate": 1.6166649782750152e-07,
      "loss": 0.1964,
      "step": 10490,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4645161290322581,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49390243902439024,
      "success_rate.epoch.env.logic": 0.577807848443843,
      "success_rate.epoch.env.math": 0.9786780383795309,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9597780859916782,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.598377140821994,
      "success_rate.epoch.global": 0.8562238180730102,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.992269392033543,
      "tokens_p.mean_in_band": 0.87890625,
      "tokens_rate.above_band": 0.997907949790795,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0020920502092050207
    },
    {
      "epoch": 1.7445146276595744,
      "grad_norm": 113.38370202310955,
      "learning_rate": 1.6165586627541704e-07,
      "loss": 0.3081,
      "step": 10495,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46794871794871795,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49390243902439024,
      "success_rate.epoch.env.logic": 0.5783783783783784,
      "success_rate.epoch.env.math": 0.9787007454739084,
      "success_rate.epoch.env.sat": 0.09859154929577464,
      "success_rate.epoch.env.science": 0.9598152424942263,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.598746502862714,
      "success_rate.epoch.global": 0.8563742340457331,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.993455497382199,
      "tokens_p.mean_in_band": 0.7376302083333334,
      "tokens_rate.above_band": 0.9408866995073891,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.059113300492610835
    },
    {
      "epoch": 1.7453457446808511,
      "grad_norm": 161.48573772761986,
      "learning_rate": 1.6164526727967583e-07,
      "loss": 0.2275,
      "step": 10500,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46794871794871795,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49390243902439024,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9787234042553191,
      "success_rate.epoch.env.sat": 0.0979020979020979,
      "success_rate.epoch.env.science": 0.9598523304107061,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5987409833487948,
      "success_rate.epoch.global": 0.8562472010747872,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.992816091954023,
      "tokens_p.mean_in_band": 0.5581896551724138,
      "tokens_rate.above_band": 0.9,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1
    },
    {
      "epoch": 1.7461768617021276,
      "grad_norm": 44.95849973332664,
      "learning_rate": 1.6163470085908848e-07,
      "loss": 0.304,
      "step": 10505,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49390243902439024,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9787460148777896,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.9598893499308437,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5984444326913212,
      "success_rate.epoch.global": 0.8560990158067402,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9960548172757475,
      "tokens_p.mean_in_band": 0.6958705357142857,
      "tokens_rate.above_band": 0.9148936170212766,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0851063829787234
    },
    {
      "epoch": 1.7470079787234043,
      "grad_norm": 92.58629026333666,
      "learning_rate": 1.616241670324078e-07,
      "loss": 0.2984,
      "step": 10510,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9787685774946921,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.9599263012436665,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5987286846799605,
      "success_rate.epoch.global": 0.856227651966627,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957957342083675,
      "tokens_p.mean_in_band": 0.7117745535714286,
      "tokens_rate.above_band": 0.9886455798864558,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0113544201135442
    },
    {
      "epoch": 1.747839095744681,
      "grad_norm": 281.1879377554055,
      "learning_rate": 1.6161366581832878e-07,
      "loss": 0.2461,
      "step": 10515,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5789473684210527,
      "success_rate.epoch.env.math": 0.9787685774946921,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.9599723947550034,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5987328749991729,
      "success_rate.epoch.global": 0.85633467321721,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9857324399260629,
      "tokens_p.mean_below_band": 1.0058283805847168e-06,
      "tokens_p.mean_in_band": 0.7421223958333333,
      "tokens_rate.above_band": 0.8172205438066465,
      "tokens_rate.below_band": 0.0015105740181268882,
      "tokens_rate.in_band": 0.18126888217522658
    },
    {
      "epoch": 1.7486702127659575,
      "grad_norm": 63.34607721558829,
      "learning_rate": 1.6160319723548847e-07,
      "loss": 0.186,
      "step": 10520,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5795148247978437,
      "success_rate.epoch.env.math": 0.9787685774946921,
      "success_rate.epoch.env.sat": 0.0975609756097561,
      "success_rate.epoch.env.science": 0.9599908024833295,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5987861353723655,
      "success_rate.epoch.global": 0.8563988095238095,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9943467336683417,
      "tokens_p.mean_in_band": 0.875,
      "tokens_rate.above_band": 0.9851485148514851,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01485148514851485
    },
    {
      "epoch": 1.749501329787234,
      "grad_norm": 22.65245025462587,
      "learning_rate": 1.6159276130246606e-07,
      "loss": 0.1918,
      "step": 10525,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5795148247978437,
      "success_rate.epoch.env.math": 0.9787910922587487,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.9600275671950379,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993592746668847,
      "success_rate.epoch.global": 0.856548238442099,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9890684410646388,
      "tokens_p.mean_in_band": 0.7847222222222222,
      "tokens_rate.above_band": 0.9669117647058824,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03308823529411765
    },
    {
      "epoch": 1.7503324468085106,
      "grad_norm": 51.56959633581304,
      "learning_rate": 1.6158235803778275e-07,
      "loss": 0.2721,
      "step": 10530,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5787348586810229,
      "success_rate.epoch.env.math": 0.9787910922587487,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.9600734281780633,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992925378365396,
      "success_rate.epoch.global": 0.8565275508688549,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994343471810089,
      "tokens_p.mean_below_band": 3.841705620288849e-09,
      "tokens_p.mean_in_band": 0.6805752840909091,
      "tokens_rate.above_band": 0.9670014347202296,
      "tokens_rate.below_band": 0.0014347202295552368,
      "tokens_rate.in_band": 0.03156384505021521
    },
    {
      "epoch": 1.7511635638297873,
      "grad_norm": 126.4828648171792,
      "learning_rate": 1.6157198745990182e-07,
      "loss": 0.1748,
      "step": 10535,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5793010752688172,
      "success_rate.epoch.env.math": 0.9787910922587487,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.9601191840476736,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993481716963036,
      "success_rate.epoch.global": 0.856655290102389,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9924089068825911,
      "tokens_p.mean_below_band": 1.126900315284729e-07,
      "tokens_p.mean_in_band": 0.8645833333333334,
      "tokens_rate.above_band": 0.9840637450199203,
      "tokens_rate.below_band": 0.00398406374501992,
      "tokens_rate.in_band": 0.01195219123505976
    },
    {
      "epoch": 1.7519946808510638,
      "grad_norm": 40.72336368621944,
      "learning_rate": 1.615616495872285e-07,
      "loss": 0.3656,
      "step": 10540,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5777479892761395,
      "success_rate.epoch.env.math": 0.9788135593220338,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.9601465872652314,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992115157225004,
      "success_rate.epoch.global": 0.8564862861378799,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9935196492007105,
      "tokens_p.mean_in_band": 0.5662370017331022,
      "tokens_rate.above_band": 0.8864396772288919,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11356032277110804
    },
    {
      "epoch": 1.7528257978723403,
      "grad_norm": 40.38528191942742,
      "learning_rate": 1.6155134443810997e-07,
      "loss": 0.1394,
      "step": 10545,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5777479892761395,
      "success_rate.epoch.env.math": 0.9788359788359788,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.960183066361556,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992168701416158,
      "success_rate.epoch.global": 0.8565925925925926,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957344213649851,
      "tokens_p.mean_in_band": 0.7295673076923077,
      "tokens_rate.above_band": 0.9810771470160117,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018922852983988356
    },
    {
      "epoch": 1.753656914893617,
      "grad_norm": 99.92699471056089,
      "learning_rate": 1.6154107203083533e-07,
      "loss": 0.215,
      "step": 10550,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46496815286624205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5777479892761395,
      "success_rate.epoch.env.math": 0.9788806758183738,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.9602103818888634,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992234167334071,
      "success_rate.epoch.global": 0.8566987416728349,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9906965648854962,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7544880319148937,
      "grad_norm": 15.806897027386105,
      "learning_rate": 1.615308323836356e-07,
      "loss": 0.1437,
      "step": 10555,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46835443037974683,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5777479892761395,
      "success_rate.epoch.env.math": 0.9789029535864979,
      "success_rate.epoch.env.sat": 0.10380622837370242,
      "success_rate.epoch.env.science": 0.9602467443454421,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5995365910732441,
      "success_rate.epoch.global": 0.856825913326431,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.994281045751634,
      "tokens_p.mean_in_band": 0.81640625,
      "tokens_rate.above_band": 0.996742671009772,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003257328990228013
    },
    {
      "epoch": 1.7553191489361701,
      "grad_norm": 17.631819211192283,
      "learning_rate": 1.6152062551468369e-07,
      "loss": 0.2076,
      "step": 10560,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46835443037974683,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5783132530120482,
      "success_rate.epoch.env.math": 0.9789029535864979,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9602467443454421,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5995554375481782,
      "success_rate.epoch.global": 0.856720390359308,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9929187192118226,
      "tokens_p.mean_in_band": 0.6519396551724138,
      "tokens_rate.above_band": 0.9545454545454546,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.045454545454545456
    },
    {
      "epoch": 1.7561502659574468,
      "grad_norm": 67.89578263728303,
      "learning_rate": 1.615104514420942e-07,
      "loss": 0.2159,
      "step": 10565,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46835443037974683,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5783132530120482,
      "success_rate.epoch.env.math": 0.9789473684210527,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9602649006622517,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5995611258346658,
      "success_rate.epoch.global": 0.856805083493424,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9933510638297872,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9929577464788732,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007042253521126761
    },
    {
      "epoch": 1.7569813829787235,
      "grad_norm": 272.199993757412,
      "learning_rate": 1.615003101839237e-07,
      "loss": 0.375,
      "step": 10570,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46835443037974683,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5788770053475936,
      "success_rate.epoch.env.math": 0.9789915966386554,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9602739726027397,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5996172215159055,
      "success_rate.epoch.global": 0.8568896765618077,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9977080908032596,
      "tokens_p.mean_in_band": 0.72509765625,
      "tokens_rate.above_band": 0.9817142857142858,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018285714285714287
    },
    {
      "epoch": 1.7578125,
      "grad_norm": 4.328831016811341,
      "learning_rate": 1.614902017581704e-07,
      "loss": 0.2748,
      "step": 10575,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46835443037974683,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5794392523364486,
      "success_rate.epoch.env.math": 0.9789915966386554,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9603102189781022,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5996716300035616,
      "success_rate.epoch.global": 0.856995277449823,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9986942896935933,
      "tokens_p.mean_in_band": 0.52734375,
      "tokens_rate.above_band": 0.9972222222222222,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.002777777777777778
    },
    {
      "epoch": 1.7586436170212765,
      "grad_norm": 16.380425973142383,
      "learning_rate": 1.6148012618277427e-07,
      "loss": 0.1598,
      "step": 10580,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46835443037974683,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5794392523364486,
      "success_rate.epoch.env.math": 0.9789915966386554,
      "success_rate.epoch.env.sat": 0.10344827586206896,
      "success_rate.epoch.env.science": 0.9603463992707384,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.599674919121074,
      "success_rate.epoch.global": 0.8570796460176991,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921511627906977,
      "tokens_p.mean_in_band": 0.439453125,
      "tokens_rate.above_band": 0.9953703703703703,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004629629629629629
    },
    {
      "epoch": 1.7594747340425532,
      "grad_norm": 87.07863047658616,
      "learning_rate": 1.6147008347561698e-07,
      "loss": 0.1633,
      "step": 10585,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.46540880503144655,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49696969696969695,
      "success_rate.epoch.env.logic": 0.5786666666666667,
      "success_rate.epoch.env.math": 0.9789915966386554,
      "success_rate.epoch.env.sat": 0.10309278350515463,
      "success_rate.epoch.env.science": 0.960145752675928,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992863418510915,
      "success_rate.epoch.global": 0.8566165635131152,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.41666666666666663,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9990371734762223,
      "tokens_p.mean_below_band": 4.274625098332763e-11,
      "tokens_p.mean_in_band": 0.6464251893939394,
      "tokens_rate.above_band": 0.9777341191879503,
      "tokens_rate.below_band": 0.0006548788474132286,
      "tokens_rate.in_band": 0.021611001964636542
    },
    {
      "epoch": 1.7603058510638299,
      "grad_norm": 78.82315458697826,
      "learning_rate": 1.6146007365452194e-07,
      "loss": 0.3379,
      "step": 10590,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5792276964047937,
      "success_rate.epoch.env.math": 0.9790356394129979,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.9601548269581056,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5987416003421007,
      "success_rate.epoch.global": 0.8561966440977333,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9946760193782802,
      "tokens_p.mean_in_band": 0.5518380979073244,
      "tokens_rate.above_band": 0.8810243642183888,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11897563578161124
    },
    {
      "epoch": 1.7611369680851063,
      "grad_norm": 76.83334921370717,
      "learning_rate": 1.6145009673725407e-07,
      "loss": 0.1736,
      "step": 10595,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5792276964047937,
      "success_rate.epoch.env.math": 0.9790575916230366,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.9601910828025477,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.598746891983417,
      "success_rate.epoch.global": 0.856302397411384,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9897388059701493,
      "tokens_p.mean_in_band": 0.8515625,
      "tokens_rate.above_band": 0.9852941176470589,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014705882352941176
    },
    {
      "epoch": 1.761968085106383,
      "grad_norm": 315.4143076224078,
      "learning_rate": 1.6144015274151998e-07,
      "loss": 0.3128,
      "step": 10600,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5797872340425532,
      "success_rate.epoch.env.math": 0.9790575916230366,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.9602363099295614,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5988018705983964,
      "success_rate.epoch.global": 0.8564290962527553,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9954954954954955,
      "tokens_p.mean_in_band": 0.6953125,
      "tokens_rate.above_band": 0.9955156950672646,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004484304932735426
    },
    {
      "epoch": 1.7627992021276597,
      "grad_norm": 73.75337475244935,
      "learning_rate": 1.614302416849678e-07,
      "loss": 0.2492,
      "step": 10605,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5797872340425532,
      "success_rate.epoch.env.math": 0.9791231732776617,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.9602453430258974,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5988086537575747,
      "success_rate.epoch.global": 0.8565134380966368,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9910287081339713,
      "tokens_p.mean_in_band": 0.5538793103448276,
      "tokens_rate.above_band": 0.8781512605042017,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12184873949579832
    },
    {
      "epoch": 1.7636303191489362,
      "grad_norm": 0.7034346217662198,
      "learning_rate": 1.6142036358518724e-07,
      "loss": 0.1612,
      "step": 10610,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4939759036144578,
      "success_rate.epoch.env.logic": 0.5803452855245684,
      "success_rate.epoch.env.math": 0.9791666666666666,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.960272417707151,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5988658009895996,
      "success_rate.epoch.global": 0.856639765223771,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9883191747572816,
      "tokens_p.mean_in_band": 0.8802083333333334,
      "tokens_rate.above_band": 0.9856459330143541,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014354066985645933
    },
    {
      "epoch": 1.7644614361702127,
      "grad_norm": 37.57350612689455,
      "learning_rate": 1.6141051845970954e-07,
      "loss": 0.2963,
      "step": 10615,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49101796407185627,
      "success_rate.epoch.env.logic": 0.5809018567639257,
      "success_rate.epoch.env.math": 0.9791666666666666,
      "success_rate.epoch.env.sat": 0.10238907849829351,
      "success_rate.epoch.env.science": 0.9603084599682468,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5986507713494044,
      "success_rate.epoch.global": 0.8566192640375312,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9906858048349056,
      "tokens_p.mean_below_band": 4.991888999938965e-07,
      "tokens_p.mean_in_band": 0.5673249551166966,
      "tokens_rate.above_band": 0.8585168311819793,
      "tokens_rate.below_band": 0.0005062009617818274,
      "tokens_rate.in_band": 0.14097696785623892
    },
    {
      "epoch": 1.7652925531914894,
      "grad_norm": 12.558511457793411,
      "learning_rate": 1.6140070632600733e-07,
      "loss": 0.1631,
      "step": 10620,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49101796407185627,
      "success_rate.epoch.env.logic": 0.5809018567639257,
      "success_rate.epoch.env.math": 0.9791883454734651,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9603264565858082,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5989319326036603,
      "success_rate.epoch.global": 0.8567032967032967,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917561349693251,
      "tokens_p.mean_in_band": 0.7421875,
      "tokens_rate.above_band": 0.9760479041916168,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023952095808383235
    },
    {
      "epoch": 1.766123670212766,
      "grad_norm": 83.80576165897881,
      "learning_rate": 1.6139092720149478e-07,
      "loss": 0.1593,
      "step": 10625,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49101796407185627,
      "success_rate.epoch.env.logic": 0.5809018567639257,
      "success_rate.epoch.env.math": 0.9791883454734651,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9603624009060022,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5989352002691324,
      "success_rate.epoch.global": 0.8567872309269293,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9938479965156795,
      "tokens_p.mean_in_band": 0.7503142959770115,
      "tokens_rate.above_band": 0.9295546558704454,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07044534412955465
    },
    {
      "epoch": 1.7669547872340425,
      "grad_norm": 228.61911920987004,
      "learning_rate": 1.6138118110352744e-07,
      "loss": 0.1194,
      "step": 10630,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5809018567639257,
      "success_rate.epoch.env.math": 0.9792099792099792,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9604072398190046,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.599216666416885,
      "success_rate.epoch.global": 0.8569338794616735,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9908216783216783,
      "tokens_p.mean_in_band": 0.78515625,
      "tokens_rate.above_band": 0.9965156794425087,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003484320557491289
    },
    {
      "epoch": 1.767785904255319,
      "grad_norm": 32.3489141796363,
      "learning_rate": 1.6137146804940222e-07,
      "loss": 0.4175,
      "step": 10635,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5809018567639257,
      "success_rate.epoch.env.math": 0.9792099792099792,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9602169981916817,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.599199371723492,
      "success_rate.epoch.global": 0.8568713450292398,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.985176282051282,
      "tokens_p.mean_below_band": 4.6798959374427795e-08,
      "tokens_rate.above_band": 0.9936305732484076,
      "tokens_rate.below_band": 0.006369426751592357,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7686170212765957,
      "grad_norm": 142.57846639845263,
      "learning_rate": 1.6136178805635745e-07,
      "loss": 0.1124,
      "step": 10640,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5814569536423841,
      "success_rate.epoch.env.math": 0.9792746113989638,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9602439575333183,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992581615788629,
      "success_rate.epoch.global": 0.857017671973127,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9986275337837838,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.9966329966329966,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003367003367003367
    },
    {
      "epoch": 1.7694481382978724,
      "grad_norm": 32.15966394505021,
      "learning_rate": 1.6135214114157273e-07,
      "loss": 0.1893,
      "step": 10645,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5814569536423841,
      "success_rate.epoch.env.math": 0.979296066252588,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9603067207938656,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992658177710604,
      "success_rate.epoch.global": 0.8571845368344274,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944073783359497,
      "tokens_p.mean_in_band": 0.6701388888888888,
      "tokens_rate.above_band": 0.9860681114551083,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01393188854489164
    },
    {
      "epoch": 1.7702792553191489,
      "grad_norm": 61.83727802351752,
      "learning_rate": 1.6134252732216892e-07,
      "loss": 0.2424,
      "step": 10650,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5806878306878307,
      "success_rate.epoch.env.math": 0.9793174767321613,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.960315670800451,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5991986575466609,
      "success_rate.epoch.global": 0.8571011956838729,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9969468390804598,
      "tokens_p.mean_in_band": 0.6474609375,
      "tokens_rate.above_band": 0.9886363636363636,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011363636363636364
    },
    {
      "epoch": 1.7711103723404256,
      "grad_norm": 45.13221231646338,
      "learning_rate": 1.6133294661520826e-07,
      "loss": 0.286,
      "step": 10655,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5812417437252312,
      "success_rate.epoch.env.math": 0.9793601651186791,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9603335587108407,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992545202134161,
      "success_rate.epoch.global": 0.8572053038030016,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9957306338028169,
      "tokens_p.mean_in_band": 0.5216619318181818,
      "tokens_rate.above_band": 0.955585464333782,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04441453566621804
    },
    {
      "epoch": 1.7719414893617023,
      "grad_norm": 60.32894950868391,
      "learning_rate": 1.6132339903769417e-07,
      "loss": 0.2419,
      "step": 10660,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5812417437252312,
      "success_rate.epoch.env.math": 0.979381443298969,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9603692861968025,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5992597025467117,
      "success_rate.epoch.global": 0.8573092603377985,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9947337042925278,
      "tokens_p.mean_in_band": 0.7075892857142857,
      "tokens_rate.above_band": 0.9889937106918238,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0110062893081761
    },
    {
      "epoch": 1.7727726063829787,
      "grad_norm": 148.7396810129139,
      "learning_rate": 1.6131388460657119e-07,
      "loss": 0.1919,
      "step": 10665,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5817941952506597,
      "success_rate.epoch.env.math": 0.9794026776519053,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9603782080144079,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993126668827089,
      "success_rate.epoch.global": 0.8573715616358608,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.7142857142857143,
      "success_rate.window.env_macro_mean": 0.9047619047619048,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965377697841726,
      "tokens_p.mean_below_band": 1.126900315284729e-07,
      "tokens_p.mean_in_band": 0.6722530241935484,
      "tokens_rate.above_band": 0.9559834938101788,
      "tokens_rate.below_band": 0.001375515818431912,
      "tokens_rate.in_band": 0.04264099037138927
    },
    {
      "epoch": 1.7736037234042552,
      "grad_norm": 62.75924004314427,
      "learning_rate": 1.6130440333872517e-07,
      "loss": 0.2203,
      "step": 10670,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5823451910408433,
      "success_rate.epoch.env.math": 0.9794238683127572,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9604138551506972,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993679244815567,
      "success_rate.epoch.global": 0.8574960011632979,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.996875,
      "tokens_p.mean_in_band": 0.8525390625,
      "tokens_rate.above_band": 0.9939759036144579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006024096385542169
    },
    {
      "epoch": 1.774434840425532,
      "grad_norm": 26.635178446257964,
      "learning_rate": 1.6129495525098297e-07,
      "loss": 0.2278,
      "step": 10675,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5823451910408433,
      "success_rate.epoch.env.math": 0.9794450154162384,
      "success_rate.epoch.env.sat": 0.1054421768707483,
      "success_rate.epoch.env.science": 0.9604494382022472,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993730817683777,
      "success_rate.epoch.global": 0.8575995350188899,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9935774858663119,
      "tokens_p.mean_in_band": 0.7221513605442177,
      "tokens_rate.above_band": 0.9533925174381738,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04660748256182625
    },
    {
      "epoch": 1.7752659574468086,
      "grad_norm": 34.247749283077695,
      "learning_rate": 1.612855403601127e-07,
      "loss": 0.2061,
      "step": 10680,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5834428383705651,
      "success_rate.epoch.env.math": 0.9794661190965093,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.9604849573417154,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5994455216812345,
      "success_rate.epoch.global": 0.8576197387518142,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954318936877077,
      "tokens_p.mean_in_band": 0.6220128676470589,
      "tokens_rate.above_band": 0.9465408805031447,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05345911949685535
    },
    {
      "epoch": 1.776097074468085,
      "grad_norm": 44.89425586317634,
      "learning_rate": 1.6127615868282347e-07,
      "loss": 0.249,
      "step": 10685,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.583989501312336,
      "success_rate.epoch.env.math": 0.9794661190965093,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.9602871886919453,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5994772393441437,
      "success_rate.epoch.global": 0.8575572961995939,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9375,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9901463963963963,
      "tokens_p.mean_below_band": 3.1650415621697903e-10,
      "tokens_p.mean_in_band": 0.7125,
      "tokens_rate.above_band": 0.9736842105263158,
      "tokens_rate.below_band": 0.0043859649122807015,
      "tokens_rate.in_band": 0.021929824561403508
    },
    {
      "epoch": 1.7769281914893615,
      "grad_norm": 66.04998950180257,
      "learning_rate": 1.6126681023576544e-07,
      "loss": 0.2835,
      "step": 10690,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.583989501312336,
      "success_rate.epoch.env.math": 0.9795291709314228,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.9603139013452915,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5994853997521672,
      "success_rate.epoch.global": 0.8576811594202899,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9989577343300747,
      "tokens_p.mean_in_band": 0.5974657012195121,
      "tokens_rate.above_band": 0.9769662921348314,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.023033707865168538
    },
    {
      "epoch": 1.7777593085106385,
      "grad_norm": 116.14493202306781,
      "learning_rate": 1.612574950355298e-07,
      "loss": 0.3844,
      "step": 10695,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.583989501312336,
      "success_rate.epoch.env.math": 0.9795709908069459,
      "success_rate.epoch.env.sat": 0.10508474576271186,
      "success_rate.epoch.env.science": 0.9603494623655914,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5994924343790603,
      "success_rate.epoch.global": 0.857804807413843,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9983219844357977,
      "tokens_p.mean_in_band": 0.44703125,
      "tokens_rate.above_band": 0.9809160305343512,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019083969465648856
    },
    {
      "epoch": 1.778590425531915,
      "grad_norm": 70.88412104735612,
      "learning_rate": 1.6124821309864876e-07,
      "loss": 0.2229,
      "step": 10700,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5845347313237221,
      "success_rate.epoch.env.math": 0.9795918367346939,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.9603849597135183,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5995148486748856,
      "success_rate.epoch.global": 0.8578041371329379,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9929577464788732,
      "tokens_p.mean_in_band": 0.72109375,
      "tokens_rate.above_band": 0.9342105263157895,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06578947368421052
    },
    {
      "epoch": 1.7794215425531914,
      "grad_norm": 541.3729652006937,
      "learning_rate": 1.6123896444159547e-07,
      "loss": 0.2195,
      "step": 10705,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5856209150326798,
      "success_rate.epoch.env.math": 0.9796126401630989,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.9603938241217275,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5996162897244831,
      "success_rate.epoch.global": 0.8578863669220761,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env.webshop": 0.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9945956256358087,
      "tokens_p.mean_in_band": 0.48607016509433965,
      "tokens_rate.above_band": 0.8607705779334501,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.13922942206654992
    },
    {
      "epoch": 1.780252659574468,
      "grad_norm": 84.96117863549608,
      "learning_rate": 1.612297490807841e-07,
      "loss": 0.2867,
      "step": 10710,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5856209150326798,
      "success_rate.epoch.env.math": 0.9797365754812564,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.9604026845637584,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5996283620663184,
      "success_rate.epoch.global": 0.8580300404390526,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9889423076923077,
      "tokens_p.mean_below_band": 1.2014061212539673e-07,
      "tokens_rate.above_band": 0.9923664122137404,
      "tokens_rate.below_band": 0.007633587786259542,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7810837765957448,
      "grad_norm": 36.91675718570145,
      "learning_rate": 1.6122056703256958e-07,
      "loss": 0.188,
      "step": 10715,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5856209150326798,
      "success_rate.epoch.env.math": 0.979757085020243,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.9604645968282332,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5996358549575421,
      "success_rate.epoch.global": 0.858193883439123,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917410714285714,
      "tokens_p.mean_in_band": 0.78125,
      "tokens_rate.above_band": 0.9929078014184397,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0070921985815602835
    },
    {
      "epoch": 1.7819148936170213,
      "grad_norm": 26.620477620727552,
      "learning_rate": 1.6121141831324785e-07,
      "loss": 0.3729,
      "step": 10720,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.49404761904761907,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9797979797979798,
      "success_rate.epoch.env.sat": 0.10472972972972973,
      "success_rate.epoch.env.science": 0.9604822505023443,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5996903561679721,
      "success_rate.epoch.global": 0.8582960934121379,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.55,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.990301724137931,
      "tokens_p.mean_below_band": 4.544854164123535e-07,
      "tokens_p.mean_in_band": 0.15381205673758866,
      "tokens_rate.above_band": 0.3232484076433121,
      "tokens_rate.below_band": 0.0031847133757961785,
      "tokens_rate.in_band": 0.6735668789808917
    },
    {
      "epoch": 1.7827460106382977,
      "grad_norm": 64.2413703790169,
      "learning_rate": 1.6120230293905559e-07,
      "loss": 0.245,
      "step": 10725,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4970414201183432,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9797979797979798,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.9604998884177639,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5999320664982919,
      "success_rate.epoch.global": 0.858233683907218,
      "success_rate.window.env.ded": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9885493094518775,
      "tokens_p.mean_in_band": 0.5636362128450106,
      "tokens_rate.above_band": 0.8310616929698709,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.16893830703012913
    },
    {
      "epoch": 1.7835771276595744,
      "grad_norm": 77.78724534866353,
      "learning_rate": 1.611932209261704e-07,
      "loss": 0.1425,
      "step": 10730,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.4970414201183432,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9797979797979798,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.9605439144003567,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5999360688603458,
      "success_rate.epoch.global": 0.8583357327958537,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9896634615384615,
      "tokens_p.mean_in_band": 0.85546875,
      "tokens_rate.above_band": 0.9923664122137404,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007633587786259542
    },
    {
      "epoch": 1.7844082446808511,
      "grad_norm": 32.303789831973695,
      "learning_rate": 1.611841722907106e-07,
      "loss": 0.1799,
      "step": 10735,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9798183652875883,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.9605790645879733,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6002100793656987,
      "success_rate.epoch.global": 0.8584579976985041,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9967468454258676,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7852393617021276,
      "grad_norm": 47.68586764099244,
      "learning_rate": 1.6117515704873534e-07,
      "loss": 0.1262,
      "step": 10740,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9798590130916415,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.9605966162065895,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.600215370222305,
      "success_rate.epoch.global": 0.8585393904542841,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.996484375,
      "tokens_p.mean_in_band": 0.853125,
      "tokens_rate.above_band": 0.9795918367346939,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02040816326530612
    },
    {
      "epoch": 1.7860704787234043,
      "grad_norm": 17.16289170253508,
      "learning_rate": 1.6116617521624444e-07,
      "loss": 0.2204,
      "step": 10745,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.4625,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9798792756539235,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.9606229143492769,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6002196030136658,
      "success_rate.epoch.global": 0.8586206896551725,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9870084269662921,
      "tokens_p.mean_in_band": 0.7760416666666666,
      "tokens_rate.above_band": 0.9834254143646409,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016574585635359115
    },
    {
      "epoch": 1.786901595744681,
      "grad_norm": 108.8161588564367,
      "learning_rate": 1.6115722680917845e-07,
      "loss": 0.2069,
      "step": 10750,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9798994974874372,
      "success_rate.epoch.env.sat": 0.10437710437710437,
      "success_rate.epoch.env.science": 0.9606579239831073,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.599963472164565,
      "success_rate.epoch.global": 0.8585989089865059,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949524940617577,
      "tokens_p.mean_in_band": 0.6748046875,
      "tokens_rate.above_band": 0.9952718676122931,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004728132387706856
    },
    {
      "epoch": 1.7877327127659575,
      "grad_norm": 155.21564865186264,
      "learning_rate": 1.611483118434186e-07,
      "loss": 0.1781,
      "step": 10755,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9799398194583752,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9606841403820524,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6004662206299046,
      "success_rate.epoch.global": 0.8586177229710352,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9966322055137845,
      "tokens_p.mean_in_band": 0.6277721774193549,
      "tokens_rate.above_band": 0.962605548854041,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03739445114595899
    },
    {
      "epoch": 1.788563829787234,
      "grad_norm": 17.373103121455166,
      "learning_rate": 1.6113943033478675e-07,
      "loss": 0.1922,
      "step": 10760,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5861618798955613,
      "success_rate.epoch.env.math": 0.9799599198396793,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9607190412782957,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6004712207460452,
      "success_rate.epoch.global": 0.8587190141854134,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.988,
      "tokens_p.mean_in_band": 0.8359375,
      "tokens_rate.above_band": 0.9920634920634921,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007936507936507936
    },
    {
      "epoch": 1.7893949468085106,
      "grad_norm": 59.74296882587284,
      "learning_rate": 1.6113058229904547e-07,
      "loss": 0.234,
      "step": 10765,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5867014341590613,
      "success_rate.epoch.env.math": 0.9799599198396793,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9605409000221681,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6005040764739882,
      "success_rate.epoch.global": 0.8586972083035075,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9920948616600791,
      "tokens_p.mean_below_band": 1.4637180356658064e-12,
      "tokens_p.mean_in_band": 0.559814453125,
      "tokens_rate.above_band": 0.937037037037037,
      "tokens_rate.below_band": 0.003703703703703704,
      "tokens_rate.in_band": 0.05925925925925926
    },
    {
      "epoch": 1.7902260638297873,
      "grad_norm": 47.34291211186402,
      "learning_rate": 1.6112176775189776e-07,
      "loss": 0.2077,
      "step": 10770,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5867014341590613,
      "success_rate.epoch.env.math": 0.97997997997998,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9605583868823399,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6005074898376676,
      "success_rate.epoch.global": 0.8587578706353749,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9858870967741935,
      "tokens_p.mean_in_band": 0.7919921875,
      "tokens_rate.above_band": 0.950920245398773,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049079754601226995
    },
    {
      "epoch": 1.7910571808510638,
      "grad_norm": 102.0355084399512,
      "learning_rate": 1.6111298670898735e-07,
      "loss": 0.186,
      "step": 10775,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.58777633289987,
      "success_rate.epoch.env.math": 0.97997997997998,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9605845881310895,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6006075898367182,
      "success_rate.epoch.global": 0.8588588588588588,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952651515151515,
      "tokens_p.mean_in_band": 0.6335720486111112,
      "tokens_rate.above_band": 0.9705882352941176,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029411764705882353
    },
    {
      "epoch": 1.7918882978723403,
      "grad_norm": 129.2380060196005,
      "learning_rate": 1.6110423918589843e-07,
      "loss": 0.2641,
      "step": 10780,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.58777633289987,
      "success_rate.epoch.env.math": 0.98,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9606368863334808,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6006141642205738,
      "success_rate.epoch.global": 0.859,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.99,
      "tokens_p.mean_in_band": 0.8779296875,
      "tokens_rate.above_band": 0.974025974025974,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025974025974025976
    },
    {
      "epoch": 1.792719414893617,
      "grad_norm": 1.930725702269604,
      "learning_rate": 1.6109552519815573e-07,
      "loss": 0.2438,
      "step": 10785,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.58777633289987,
      "success_rate.epoch.env.math": 0.98,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9606716747680071,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6006173268055307,
      "success_rate.epoch.global": 0.8590805254140491,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9943548387096774,
      "tokens_p.mean_in_band": 0.677734375,
      "tokens_rate.above_band": 0.9914712153518124,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008528784648187633
    },
    {
      "epoch": 1.7935505319148937,
      "grad_norm": 54.248138108864985,
      "learning_rate": 1.610868447612244e-07,
      "loss": 0.2339,
      "step": 10790,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.58777633289987,
      "success_rate.epoch.env.math": 0.98001998001998,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9607150739351137,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6006230885498114,
      "success_rate.epoch.global": 0.8592011412268188,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9923780487804879,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.7943816489361701,
      "grad_norm": 37.33686049422359,
      "learning_rate": 1.6107819789051007e-07,
      "loss": 0.2256,
      "step": 10795,
      "success_rate.epoch.env.abd": 0.6136363636363636,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5875486381322957,
      "success_rate.epoch.env.math": 0.9800598205383848,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9607324067946172,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6006075866052962,
      "success_rate.epoch.global": 0.8591790193842646,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949270767279645,
      "tokens_p.mean_in_band": 0.7235243055555556,
      "tokens_rate.above_band": 0.9563371740448757,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.043662825955124315
    },
    {
      "epoch": 1.7952127659574468,
      "grad_norm": 56.47097629263309,
      "learning_rate": 1.6106958460135887e-07,
      "loss": 0.3491,
      "step": 10800,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5875486381322957,
      "success_rate.epoch.env.math": 0.9800995024875622,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9607670266696055,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993746718950965,
      "success_rate.epoch.global": 0.8591769898903603,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.7083333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9892490671641792,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.17683390345876093,
      "tokens_rate.above_band": 0.337361530715005,
      "tokens_rate.below_band": 0.00025176233635448137,
      "tokens_rate.in_band": 0.6623867069486404
    },
    {
      "epoch": 1.7960438829787235,
      "grad_norm": 84.01805980590433,
      "learning_rate": 1.6106100490905728e-07,
      "loss": 0.2668,
      "step": 10805,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45962732919254656,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5873221216041398,
      "success_rate.epoch.env.math": 0.9801192842942346,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9607929515418502,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5993582346360747,
      "success_rate.epoch.global": 0.8591549295774648,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964862440191388,
      "tokens_p.mean_in_band": 0.5183823529411765,
      "tokens_rate.above_band": 0.9800703399765534,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01992966002344666
    },
    {
      "epoch": 1.796875,
      "grad_norm": 165.19382631484845,
      "learning_rate": 1.6105245882883211e-07,
      "loss": 0.2009,
      "step": 10810,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5873221216041398,
      "success_rate.epoch.env.math": 0.9801783944499505,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9608102157639806,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5991072499671738,
      "success_rate.epoch.global": 0.8591329068941009,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9942010309278351,
      "tokens_p.mean_in_band": 0.4375,
      "tokens_rate.above_band": 0.9965753424657534,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003424657534246575
    },
    {
      "epoch": 1.7977061170212765,
      "grad_norm": 33.51566170180076,
      "learning_rate": 1.610439463758506e-07,
      "loss": 0.1779,
      "step": 10815,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5873221216041398,
      "success_rate.epoch.env.math": 0.9801980198019802,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9608446986361636,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.5991121688966476,
      "success_rate.epoch.global": 0.8592329545454546,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9919258373205742,
      "tokens_p.mean_below_band": 2.2065682614424986e-15,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.990521327014218,
      "tokens_rate.below_band": 0.004739336492890996,
      "tokens_rate.in_band": 0.004739336492890996
    },
    {
      "epoch": 1.7985372340425532,
      "grad_norm": 14.049088660533068,
      "learning_rate": 1.6103546756522025e-07,
      "loss": 0.187,
      "step": 10820,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.4666666666666667,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5873221216041398,
      "success_rate.epoch.env.math": 0.9802176063303659,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9608619173262972,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.599115514825604,
      "success_rate.epoch.global": 0.8592929149510152,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9935830700746697,
      "tokens_p.mean_in_band": 0.5491980651731161,
      "tokens_rate.above_band": 0.8764158066951926,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12358419330480745
    },
    {
      "epoch": 1.7993683510638299,
      "grad_norm": 94.23614605392928,
      "learning_rate": 1.6102702241198886e-07,
      "loss": 0.2219,
      "step": 10825,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4567901234567901,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5058139534883721,
      "success_rate.epoch.env.logic": 0.5873221216041398,
      "success_rate.epoch.env.math": 0.9802371541501976,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.960896309314587,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6021507214748272,
      "success_rate.epoch.global": 0.8594126826500212,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.76,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9929481672394044,
      "tokens_p.mean_below_band": 1.9190338207408786e-10,
      "tokens_p.mean_in_band": 0.5601619525547445,
      "tokens_rate.above_band": 0.863928748144483,
      "tokens_rate.below_band": 0.0004948045522018803,
      "tokens_rate.in_band": 0.1355764473033152
    },
    {
      "epoch": 1.8001994680851063,
      "grad_norm": 21.725552557153158,
      "learning_rate": 1.6101861093114452e-07,
      "loss": 0.2472,
      "step": 10830,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.58656330749354,
      "success_rate.epoch.env.math": 0.9802955665024631,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9609220636663007,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6020943147421709,
      "success_rate.epoch.global": 0.8593085860017002,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.998381388121547,
      "tokens_p.mean_in_band": 0.6746323529411765,
      "tokens_rate.above_band": 0.9883959044368601,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011604095563139932
    },
    {
      "epoch": 1.801030585106383,
      "grad_norm": 15.513609986208968,
      "learning_rate": 1.6101023313761557e-07,
      "loss": 0.3737,
      "step": 10835,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.58656330749354,
      "success_rate.epoch.env.math": 0.9803343166175025,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9609649122807018,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6021017328084836,
      "success_rate.epoch.global": 0.859447983014862,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9903085443037974,
      "tokens_p.mean_in_band": 0.85888671875,
      "tokens_rate.above_band": 0.9518072289156626,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04819277108433735
    },
    {
      "epoch": 1.8018617021276597,
      "grad_norm": 50.888313834838925,
      "learning_rate": 1.610018890462705e-07,
      "loss": 0.1737,
      "step": 10840,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5886889460154242,
      "success_rate.epoch.env.math": 0.9803536345776032,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9609734707301031,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6022975068931551,
      "success_rate.epoch.global": 0.8595672464997879,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9994687017001546,
      "tokens_p.mean_in_band": 0.669375,
      "tokens_rate.above_band": 0.9810462471569371,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018953752843062926
    },
    {
      "epoch": 1.8026928191489362,
      "grad_norm": 117.19268834545286,
      "learning_rate": 1.6099357867191804e-07,
      "loss": 0.2364,
      "step": 10845,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4539877300613497,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5895140664961637,
      "success_rate.epoch.env.math": 0.9803536345776032,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9609905763751918,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.602374072904594,
      "success_rate.epoch.global": 0.8595450049455984,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9934219380888291,
      "tokens_p.mean_in_band": 0.5498870481927711,
      "tokens_rate.above_band": 0.8817944457631142,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11820555423688583
    },
    {
      "epoch": 1.8035239361702127,
      "grad_norm": 54.87329252872173,
      "learning_rate": 1.609853020293071e-07,
      "loss": 0.2712,
      "step": 10850,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5895140664961637,
      "success_rate.epoch.env.math": 0.9803536345776032,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9610076670317634,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6021239704309889,
      "success_rate.epoch.global": 0.8594632768361582,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.995777027027027,
      "tokens_p.mean_in_band": 0.5938720703125,
      "tokens_rate.above_band": 0.9327731092436975,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06722689075630252
    },
    {
      "epoch": 1.8043550531914894,
      "grad_norm": 59.80113712265346,
      "learning_rate": 1.6097705913312663e-07,
      "loss": 0.1564,
      "step": 10855,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5895140664961637,
      "success_rate.epoch.env.math": 0.9803921568627451,
      "success_rate.epoch.env.sat": 0.1040268456375839,
      "success_rate.epoch.env.science": 0.9610332749562172,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.602129800450043,
      "success_rate.epoch.global": 0.8595624558927312,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9893617021276596,
      "tokens_p.mean_in_band": 0.6083333333333333,
      "tokens_rate.above_band": 0.9261083743842364,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07389162561576355
    },
    {
      "epoch": 1.805186170212766,
      "grad_norm": 82.76704370089003,
      "learning_rate": 1.6096884999800582e-07,
      "loss": 0.2698,
      "step": 10860,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5895140664961637,
      "success_rate.epoch.env.math": 0.980411361410382,
      "success_rate.epoch.env.sat": 0.10367892976588629,
      "success_rate.epoch.env.science": 0.9610843900306077,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6021045644273458,
      "success_rate.epoch.global": 0.8595798674749753,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9934971098265896,
      "tokens_p.mean_in_band": 0.6182291666666667,
      "tokens_rate.above_band": 0.9202127659574468,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0797872340425532
    },
    {
      "epoch": 1.8060172872340425,
      "grad_norm": 73.75541550187319,
      "learning_rate": 1.6096067463851383e-07,
      "loss": 0.3175,
      "step": 10865,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5895140664961637,
      "success_rate.epoch.env.math": 0.9804305283757339,
      "success_rate.epoch.env.sat": 0.10367892976588629,
      "success_rate.epoch.env.science": 0.9611098973126502,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6021086257225635,
      "success_rate.epoch.global": 0.8596590108496548,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.4166666666666667,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9910987074030553,
      "tokens_p.mean_below_band": 1.8533319234848022e-07,
      "tokens_p.mean_in_band": 0.4982205802603037,
      "tokens_rate.above_band": 0.8217458478176902,
      "tokens_rate.below_band": 0.00019312475859405175,
      "tokens_rate.in_band": 0.1780610274237157
    },
    {
      "epoch": 1.806848404255319,
      "grad_norm": 32.79037574406223,
      "learning_rate": 1.6095253306915995e-07,
      "loss": 0.3057,
      "step": 10870,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5086705202312138,
      "success_rate.epoch.env.logic": 0.5895140664961637,
      "success_rate.epoch.env.math": 0.98046875,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9611438550534818,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6023867999285524,
      "success_rate.epoch.global": 0.8597972972972973,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9920180722891566,
      "tokens_p.mean_in_band": 0.8184523809523809,
      "tokens_rate.above_band": 0.9518348623853211,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0481651376146789
    },
    {
      "epoch": 1.8076795212765957,
      "grad_norm": 37.94694572669038,
      "learning_rate": 1.6094442530439343e-07,
      "loss": 0.157,
      "step": 10875,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5887611749680716,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9611523352247927,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6020550953582646,
      "success_rate.epoch.global": 0.8595948227349466,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9908613445378152,
      "tokens_p.mean_in_band": 0.49795502440106476,
      "tokens_rate.above_band": 0.7252559726962458,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.27474402730375425
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 92.51440367889073,
      "learning_rate": 1.6093635135860358e-07,
      "loss": 0.3007,
      "step": 10880,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5880102040816326,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9611523352247927,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6019868252776793,
      "success_rate.epoch.global": 0.8594739063159376,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.science": 0.6,
      "success_rate.window.env_macro_mean": 0.45,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 1.0003950140449438,
      "tokens_p.mean_below_band": 5.029141902923584e-08,
      "tokens_p.mean_in_band": 0.5941840277777778,
      "tokens_rate.above_band": 0.9861495844875346,
      "tokens_rate.below_band": 0.0013850415512465374,
      "tokens_rate.in_band": 0.012465373961218837
    },
    {
      "epoch": 1.8093417553191489,
      "grad_norm": 138.38660870721642,
      "learning_rate": 1.6092831124611973e-07,
      "loss": 0.357,
      "step": 10885,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5880102040816326,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9611862189271696,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6046637024057029,
      "success_rate.epoch.global": 0.8595726736013495,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9945507117437722,
      "tokens_p.mean_in_band": 0.837890625,
      "tokens_rate.above_band": 0.9929328621908127,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007067137809187279
    },
    {
      "epoch": 1.8101728723404256,
      "grad_norm": 32.394591454361134,
      "learning_rate": 1.6092030498121102e-07,
      "loss": 0.1672,
      "step": 10890,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5880102040816326,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9612453733942957,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6046690800845326,
      "success_rate.epoch.global": 0.859710714787249,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9908376963350786,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.8110039893617023,
      "grad_norm": 1.1973372800391116,
      "learning_rate": 1.609123325780867e-07,
      "loss": 0.2145,
      "step": 10895,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5880102040816326,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9612875163114397,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6046729112588184,
      "success_rate.epoch.global": 0.8598091495930396,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9946853741496599,
      "tokens_p.mean_in_band": 0.498046875,
      "tokens_rate.above_band": 0.9966101694915255,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003389830508474576
    },
    {
      "epoch": 1.8118351063829787,
      "grad_norm": 54.81361441209326,
      "learning_rate": 1.6090439405089574e-07,
      "loss": 0.2421,
      "step": 10900,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5880102040816326,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9613127580960661,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6046752059665116,
      "success_rate.epoch.global": 0.8598681441997476,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9933456873315364,
      "tokens_p.mean_in_band": 0.7465277777777778,
      "tokens_rate.above_band": 0.9763157894736842,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02368421052631579
    },
    {
      "epoch": 1.8126662234042552,
      "grad_norm": 1.7934461595338502,
      "learning_rate": 1.6089648941372717e-07,
      "loss": 0.1687,
      "step": 10905,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5057471264367817,
      "success_rate.epoch.env.logic": 0.5885350318471337,
      "success_rate.epoch.env.math": 0.9804878048780488,
      "success_rate.epoch.env.sat": 0.10666666666666667,
      "success_rate.epoch.env.science": 0.9613631430431951,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6047274980312962,
      "success_rate.epoch.global": 0.8600056053811659,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9933501237186285,
      "tokens_p.mean_in_band": 0.723043893129771,
      "tokens_rate.above_band": 0.9557432432432432,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.044256756756756756
    },
    {
      "epoch": 1.813497340425532,
      "grad_norm": 35.773572796412076,
      "learning_rate": 1.608886186806097e-07,
      "loss": 0.3519,
      "step": 10910,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5885350318471337,
      "success_rate.epoch.env.math": 0.9805068226120858,
      "success_rate.epoch.env.sat": 0.10631229235880399,
      "success_rate.epoch.env.science": 0.9614050303555941,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6049575737470435,
      "success_rate.epoch.global": 0.8600223964165733,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9912819253438114,
      "tokens_p.mean_in_band": 0.6825284090909091,
      "tokens_rate.above_band": 0.9686013320647003,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03139866793529972
    },
    {
      "epoch": 1.8143284574468086,
      "grad_norm": 32.06052618910017,
      "learning_rate": 1.6088078186551203e-07,
      "loss": 0.1763,
      "step": 10915,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5885350318471337,
      "success_rate.epoch.env.math": 0.9805258033106135,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.9614384748700173,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6052313606591303,
      "success_rate.epoch.global": 0.8601398601398601,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944036532951289,
      "tokens_p.mean_in_band": 0.6878551136363636,
      "tokens_rate.above_band": 0.9844851904090268,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015514809590973202
    },
    {
      "epoch": 1.815159574468085,
      "grad_norm": 47.28900936919914,
      "learning_rate": 1.6087297898234256e-07,
      "loss": 0.2481,
      "step": 10920,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.45121951219512196,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.589058524173028,
      "success_rate.epoch.env.math": 0.9805258033106135,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.9614551754006063,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6052804691006288,
      "success_rate.epoch.global": 0.8601985181042919,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9941339590443686,
      "tokens_p.mean_in_band": 0.80078125,
      "tokens_rate.above_band": 0.9865319865319865,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013468013468013467
    },
    {
      "epoch": 1.8159906914893615,
      "grad_norm": 157.81453079796705,
      "learning_rate": 1.6086521004494947e-07,
      "loss": 0.1933,
      "step": 10925,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4457831325301205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5895806861499364,
      "success_rate.epoch.env.math": 0.980544747081712,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.9614801990911058,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6048377190800384,
      "success_rate.epoch.global": 0.8600558659217877,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9961163294797688,
      "tokens_p.mean_below_band": 2.455635694786906e-10,
      "tokens_p.mean_in_band": 0.703515625,
      "tokens_rate.above_band": 0.9914040114613181,
      "tokens_rate.below_band": 0.0014326647564469914,
      "tokens_rate.in_band": 0.0071633237822349575
    },
    {
      "epoch": 1.8168218085106385,
      "grad_norm": 0.0,
      "learning_rate": 1.6085747506712074e-07,
      "loss": 0.1365,
      "step": 10930,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4457831325301205,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5895806861499364,
      "success_rate.epoch.env.math": 0.9805825242718447,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.9612805537529743,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6048230037938566,
      "success_rate.epoch.global": 0.8599944165270799,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9955143540669856,
      "tokens_p.mean_below_band": 5.617039278149605e-09,
      "tokens_p.mean_in_band": 0.8411458333333334,
      "tokens_rate.above_band": 0.9812206572769953,
      "tokens_rate.below_band": 0.004694835680751174,
      "tokens_rate.in_band": 0.014084507042253521
    },
    {
      "epoch": 1.817652925531915,
      "grad_norm": 60.493922895028234,
      "learning_rate": 1.6084977406258405e-07,
      "loss": 0.4037,
      "step": 10935,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4491017964071856,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5893536121673004,
      "success_rate.epoch.env.math": 0.9806013579049466,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.9613140263669765,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6051088125339961,
      "success_rate.epoch.global": 0.8600111544896821,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9978181306306306,
      "tokens_p.mean_in_band": 0.4605263157894737,
      "tokens_rate.above_band": 0.9790518191841234,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.020948180815876516
    },
    {
      "epoch": 1.8184840425531914,
      "grad_norm": 33.669398942371046,
      "learning_rate": 1.6084210704500683e-07,
      "loss": 0.3771,
      "step": 10940,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4491017964071856,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5886075949367089,
      "success_rate.epoch.env.math": 0.9806013579049466,
      "success_rate.epoch.env.sat": 0.10927152317880795,
      "success_rate.epoch.env.science": 0.9613390928725702,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6050432715589963,
      "success_rate.epoch.global": 0.8599498327759197,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9945158850226928,
      "tokens_p.mean_in_band": 0.60703125,
      "tokens_rate.above_band": 0.9850968703427719,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014903129657228018
    },
    {
      "epoch": 1.819315159574468,
      "grad_norm": 58.64294875807672,
      "learning_rate": 1.608344740279961e-07,
      "loss": 0.1743,
      "step": 10945,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.4491017964071856,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5294117647058824,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5886075949367089,
      "success_rate.epoch.env.math": 0.9806201550387597,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9613807982740021,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6050159870540459,
      "success_rate.epoch.global": 0.8599470973131004,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99140625,
      "tokens_p.mean_in_band": 0.7513020833333334,
      "tokens_rate.above_band": 0.9142857142857143,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08571428571428572
    },
    {
      "epoch": 1.8201462765957448,
      "grad_norm": 54.43821157244045,
      "learning_rate": 1.6082687502509866e-07,
      "loss": 0.1773,
      "step": 10950,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5896464646464646,
      "success_rate.epoch.env.math": 0.9806389157792836,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9613891285591026,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.602196075331399,
      "success_rate.epoch.global": 0.8597857838364168,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.55,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9972001445086706,
      "tokens_p.mean_in_band": 0.7367838541666667,
      "tokens_rate.above_band": 0.9787835926449788,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021216407355021217
    },
    {
      "epoch": 1.8209773936170213,
      "grad_norm": 45.255446428147536,
      "learning_rate": 1.6081931004980082e-07,
      "loss": 0.2126,
      "step": 10955,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5901639344262295,
      "success_rate.epoch.env.math": 0.9806576402321083,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9614224137931034,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.602247846191998,
      "success_rate.epoch.global": 0.8599027102154274,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9979258849557522,
      "tokens_p.mean_in_band": 0.7408854166666666,
      "tokens_rate.above_band": 0.9912280701754386,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008771929824561403
    },
    {
      "epoch": 1.8218085106382977,
      "grad_norm": 44.74315336913736,
      "learning_rate": 1.6081177911552861e-07,
      "loss": 0.1868,
      "step": 10960,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5901639344262295,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9614473400818436,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6022518111519115,
      "success_rate.epoch.global": 0.8599805528545631,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9886275272161742,
      "tokens_p.mean_in_band": 0.8136488970588235,
      "tokens_rate.above_band": 0.9497784342688331,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050221565731166914
    },
    {
      "epoch": 1.8226396276595744,
      "grad_norm": 72.03023618372818,
      "learning_rate": 1.6080428223564754e-07,
      "loss": 0.2472,
      "step": 10965,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5901639344262295,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9614722341799398,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6022540742517384,
      "success_rate.epoch.global": 0.8600388780894196,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9968147382920111,
      "tokens_p.mean_below_band": 1.318767317570746e-10,
      "tokens_p.mean_in_band": 0.732421875,
      "tokens_rate.above_band": 0.966711051930759,
      "tokens_rate.below_band": 0.0013315579227696406,
      "tokens_rate.in_band": 0.03195739014647137
    },
    {
      "epoch": 1.8234707446808511,
      "grad_norm": 39.520413934515865,
      "learning_rate": 1.607968194234628e-07,
      "loss": 0.3274,
      "step": 10970,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5894206549118388,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9615053763440861,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6021895163108071,
      "success_rate.epoch.global": 0.8599972249202165,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9951603982300885,
      "tokens_p.mean_in_band": 0.6002604166666666,
      "tokens_rate.above_band": 0.9658119658119658,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03418803418803419
    },
    {
      "epoch": 1.8243018617021276,
      "grad_norm": 42.713377861446965,
      "learning_rate": 1.60789390692219e-07,
      "loss": 0.2894,
      "step": 10975,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.589937106918239,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9615219260533104,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6022379710122275,
      "success_rate.epoch.global": 0.8600554785020804,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9916193181818181,
      "tokens_p.mean_in_band": 0.6215533088235294,
      "tokens_rate.above_band": 0.9282700421940928,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07172995780590717
    },
    {
      "epoch": 1.8251329787234043,
      "grad_norm": 35.4243584009813,
      "learning_rate": 1.6078199605510034e-07,
      "loss": 0.2489,
      "step": 10980,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5904522613065326,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9615384615384616,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6022863064552678,
      "success_rate.epoch.global": 0.860113683626785,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9936960542540074,
      "tokens_p.mean_in_band": 0.541351073434992,
      "tokens_rate.above_band": 0.8668234288157333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1331765711842668
    },
    {
      "epoch": 1.825964095744681,
      "grad_norm": 37.26417575214121,
      "learning_rate": 1.6077463552523047e-07,
      "loss": 0.2052,
      "step": 10985,
      "success_rate.epoch.env.abd": 0.6,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5904522613065326,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.9615632381361392,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6022885588732386,
      "success_rate.epoch.global": 0.8601718403547672,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9945488721804512,
      "tokens_p.mean_in_band": 0.6325120192307693,
      "tokens_rate.above_band": 0.9808259587020649,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019174041297935103
    },
    {
      "epoch": 1.8267952127659575,
      "grad_norm": 79.18362012473959,
      "learning_rate": 1.6076730911567255e-07,
      "loss": 0.2048,
      "step": 10990,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5909661229611042,
      "success_rate.epoch.env.math": 0.9806763285024155,
      "success_rate.epoch.env.sat": 0.10891089108910891,
      "success_rate.epoch.env.science": 0.961579738141232,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6031272874035639,
      "success_rate.epoch.global": 0.8602493074792243,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.000552398989899,
      "tokens_p.mean_in_band": 0.5372596153846154,
      "tokens_rate.above_band": 0.9682151589242054,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03178484107579462
    },
    {
      "epoch": 1.827626329787234,
      "grad_norm": 26.11528868489864,
      "learning_rate": 1.6076001683942918e-07,
      "loss": 0.2585,
      "step": 10995,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5914786967418546,
      "success_rate.epoch.env.math": 0.9806949806949807,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.9616044616044616,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6031129037361921,
      "success_rate.epoch.global": 0.8601079286010793,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952651515151515,
      "tokens_p.mean_in_band": 0.5737847222222222,
      "tokens_rate.above_band": 0.927710843373494,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07228915662650602
    },
    {
      "epoch": 1.8284574468085106,
      "grad_norm": 109.59843766073364,
      "learning_rate": 1.607527587094423e-07,
      "loss": 0.2208,
      "step": 11000,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5085714285714286,
      "success_rate.epoch.env.logic": 0.5914786967418546,
      "success_rate.epoch.env.math": 0.9807321772639692,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.9616126956894703,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6031170337956465,
      "success_rate.epoch.global": 0.8601659751037345,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9971223747980614,
      "tokens_p.mean_in_band": 0.7125,
      "tokens_rate.above_band": 0.9841017488076311,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01589825119236884
    },
    {
      "epoch": 1.8292885638297873,
      "grad_norm": 18.241799164994678,
      "learning_rate": 1.6074553473859336e-07,
      "loss": 0.158,
      "step": 11005,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5914786967418546,
      "success_rate.epoch.env.math": 0.9807507218479307,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.9614230604372053,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6033553171705469,
      "success_rate.epoch.global": 0.860124395300622,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9912883631713555,
      "tokens_p.mean_in_band": 0.69140625,
      "tokens_rate.above_band": 0.9898734177215189,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010126582278481013
    },
    {
      "epoch": 1.8301196808510638,
      "grad_norm": 33.298036106035156,
      "learning_rate": 1.6073834493970314e-07,
      "loss": 0.1694,
      "step": 11010,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5914786967418546,
      "success_rate.epoch.env.math": 0.9807507218479307,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.961456102783726,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6033583210202306,
      "success_rate.epoch.global": 0.8602016853156513,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9970667870036101,
      "tokens_p.mean_in_band": 0.6428571428571429,
      "tokens_rate.above_band": 0.9518900343642611,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.048109965635738834
    },
    {
      "epoch": 1.8309507978723403,
      "grad_norm": 34.81480994694523,
      "learning_rate": 1.6073118932553174e-07,
      "loss": 0.3051,
      "step": 11015,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5919899874843555,
      "success_rate.epoch.env.math": 0.9807877041306436,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.961472602739726,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6034096640185228,
      "success_rate.epoch.global": 0.8602981778023192,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9934039792387543,
      "tokens_p.mean_in_band": 0.6845128676470589,
      "tokens_rate.above_band": 0.9444444444444444,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05555555555555555
    },
    {
      "epoch": 1.831781914893617,
      "grad_norm": 612.05505873045,
      "learning_rate": 1.6072406790877867e-07,
      "loss": 0.239,
      "step": 11020,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5925,
      "success_rate.epoch.env.math": 0.980806142034549,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.9615055603079555,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6034607011083208,
      "success_rate.epoch.global": 0.8604137931034482,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9962251529051988,
      "tokens_p.mean_in_band": 0.752734375,
      "tokens_rate.above_band": 0.9849397590361446,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015060240963855422
    },
    {
      "epoch": 1.8326130319148937,
      "grad_norm": 51.62770093542465,
      "learning_rate": 1.6071698070208264e-07,
      "loss": 0.27,
      "step": 11025,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5925,
      "success_rate.epoch.env.math": 0.980806142034549,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.9615466780602435,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6034644390858016,
      "success_rate.epoch.global": 0.8605099931082012,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9900990099009901,
      "tokens_p.mean_in_band": 0.8984375,
      "tokens_rate.above_band": 0.9950738916256158,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0049261083743842365
    },
    {
      "epoch": 1.8334441489361701,
      "grad_norm": 122.07471596513099,
      "learning_rate": 1.6070992771802177e-07,
      "loss": 0.2251,
      "step": 11030,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5925,
      "success_rate.epoch.env.math": 0.980806142034549,
      "success_rate.epoch.env.sat": 0.10819672131147541,
      "success_rate.epoch.env.science": 0.9615959035630467,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.603468914131511,
      "success_rate.epoch.global": 0.8606252582288941,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.4444444444444444,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9960056390977443,
      "tokens_p.mean_in_band": 0.7534877232142857,
      "tokens_rate.above_band": 0.95,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05
    },
    {
      "epoch": 1.8342752659574468,
      "grad_norm": 22.147860824478556,
      "learning_rate": 1.607029089691133e-07,
      "loss": 0.1586,
      "step": 11035,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5925,
      "success_rate.epoch.env.math": 0.9808245445829339,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9616286506075463,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6034414200893574,
      "success_rate.epoch.global": 0.8606027246456585,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9950520833333333,
      "tokens_p.mean_in_band": 0.7241683467741935,
      "tokens_rate.above_band": 0.8856088560885609,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.11439114391143912
    },
    {
      "epoch": 1.8351063829787235,
      "grad_norm": 82.00360133905485,
      "learning_rate": 1.6069592446781388e-07,
      "loss": 0.247,
      "step": 11040,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5930087390761548,
      "success_rate.epoch.env.math": 0.9808429118773946,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9616776665956994,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6034937948492455,
      "success_rate.epoch.global": 0.8607560137457044,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9965572033898306,
      "tokens_p.mean_in_band": 0.58935546875,
      "tokens_rate.above_band": 0.9365079365079365,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06349206349206349
    },
    {
      "epoch": 1.8359375,
      "grad_norm": 37.888279525927594,
      "learning_rate": 1.6068897422651924e-07,
      "loss": 0.2422,
      "step": 11045,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5935162094763092,
      "success_rate.epoch.env.math": 0.9808429118773946,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9617102744097,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6035428928687141,
      "success_rate.epoch.global": 0.8608516483516484,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9952928870292888,
      "tokens_p.mean_in_band": 0.6259765625,
      "tokens_rate.above_band": 0.9227799227799228,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07722007722007722
    },
    {
      "epoch": 1.8367686170212765,
      "grad_norm": 333.8432768339014,
      "learning_rate": 1.6068205825756436e-07,
      "loss": 0.2513,
      "step": 11050,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5940224159402242,
      "success_rate.epoch.env.math": 0.9808612440191388,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9617184176945981,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6035913184951285,
      "success_rate.epoch.global": 0.8609089660854043,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.agentgym:textcraft": 0.5,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9965490797546013,
      "tokens_p.mean_in_band": 0.7579308712121212,
      "tokens_rate.above_band": 0.9718909710391823,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028109028960817718
    },
    {
      "epoch": 1.8375997340425532,
      "grad_norm": 76.47095503580229,
      "learning_rate": 1.6067517657322338e-07,
      "loss": 0.2439,
      "step": 11055,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5113636363636364,
      "success_rate.epoch.env.logic": 0.5940224159402242,
      "success_rate.epoch.env.math": 0.9808795411089866,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9617509562260943,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6035959399152507,
      "success_rate.epoch.global": 0.8610043907793633,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9956373292867982,
      "tokens_p.mean_in_band": 0.67333984375,
      "tokens_rate.above_band": 0.9880059970014993,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01199400299850075
    },
    {
      "epoch": 1.8384308510638299,
      "grad_norm": 192.78289713320643,
      "learning_rate": 1.6066832918570961e-07,
      "loss": 0.2801,
      "step": 11060,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5940224159402242,
      "success_rate.epoch.env.math": 0.9808795411089866,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9617915516875398,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038505992682615,
      "success_rate.epoch.global": 0.8611187277214148,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.9583333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9960801393728222,
      "tokens_p.mean_below_band": 1.7497114868092467e-13,
      "tokens_p.mean_in_band": 0.8275669642857143,
      "tokens_rate.above_band": 0.9728813559322034,
      "tokens_rate.below_band": 0.003389830508474576,
      "tokens_rate.in_band": 0.023728813559322035
    },
    {
      "epoch": 1.8392619680851063,
      "grad_norm": 1.2774234209587938,
      "learning_rate": 1.606615161071755e-07,
      "loss": 0.2572,
      "step": 11065,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5945273631840796,
      "success_rate.epoch.env.math": 0.9808795411089866,
      "success_rate.epoch.env.sat": 0.10784313725490197,
      "success_rate.epoch.env.science": 0.9618401526393895,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6039009218315075,
      "success_rate.epoch.global": 0.861251883303657,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.99375,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.840093085106383,
      "grad_norm": 89.0119652729704,
      "learning_rate": 1.606547373497126e-07,
      "loss": 0.3023,
      "step": 11070,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44642857142857145,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5945273631840796,
      "success_rate.epoch.env.math": 0.9808795411089866,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9618886301079822,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038733942761634,
      "success_rate.epoch.global": 0.861247947454844,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9915149006622517,
      "tokens_p.mean_in_band": 0.725,
      "tokens_rate.above_band": 0.9096385542168675,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09036144578313253
    },
    {
      "epoch": 1.8409242021276597,
      "grad_norm": 72.14111264105186,
      "learning_rate": 1.6064799292535151e-07,
      "loss": 0.142,
      "step": 11075,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4437869822485207,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5945273631840796,
      "success_rate.epoch.env.math": 0.9808795411089866,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617012272534913,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6036162131821141,
      "success_rate.epoch.global": 0.8610503282275711,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9974708504801097,
      "tokens_p.mean_below_band": 2.7830537874251604e-10,
      "tokens_p.mean_in_band": 0.74375,
      "tokens_rate.above_band": 0.9851351351351352,
      "tokens_rate.below_band": 0.0013513513513513514,
      "tokens_rate.in_band": 0.013513513513513514
    },
    {
      "epoch": 1.8417553191489362,
      "grad_norm": 446.3812188637191,
      "learning_rate": 1.6064128284606196e-07,
      "loss": 0.3202,
      "step": 11080,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4437869822485207,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5937888198757764,
      "success_rate.epoch.env.math": 0.9808978032473734,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617174280879864,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.603552205878894,
      "success_rate.epoch.global": 0.8609896118097321,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9995199692780338,
      "tokens_p.mean_in_band": 0.6077008928571429,
      "tokens_rate.above_band": 0.9789473684210527,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021052631578947368
    },
    {
      "epoch": 1.8425864361702127,
      "grad_norm": 60.80709227869134,
      "learning_rate": 1.6063460712375266e-07,
      "loss": 0.249,
      "step": 11085,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4437869822485207,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5942928039702233,
      "success_rate.epoch.env.math": 0.9809160305343512,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617417036567322,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6036018865107278,
      "success_rate.epoch.global": 0.8610845512908073,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937776548672567,
      "tokens_p.mean_in_band": 0.7161458333333334,
      "tokens_rate.above_band": 0.9495798319327731,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05042016806722689
    },
    {
      "epoch": 1.8434175531914894,
      "grad_norm": 78.75678670068612,
      "learning_rate": 1.6062796577027144e-07,
      "loss": 0.2917,
      "step": 11090,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5935563816604709,
      "success_rate.epoch.env.math": 0.9809342230695901,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617578702725544,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038355027036549,
      "success_rate.epoch.global": 0.8610428610428611,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982323232323232,
      "tokens_p.mean_in_band": 0.5229867788461539,
      "tokens_rate.above_band": 0.9870388833499502,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01296111665004985
    },
    {
      "epoch": 1.844248670212766,
      "grad_norm": 30.982905189855895,
      "learning_rate": 1.6062135879740507e-07,
      "loss": 0.1606,
      "step": 11095,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5141242937853108,
      "success_rate.epoch.env.logic": 0.5935563816604709,
      "success_rate.epoch.env.math": 0.9809342230695901,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617740232312566,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038369711544461,
      "success_rate.epoch.global": 0.8610807860262009,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9952664796633941,
      "tokens_p.mean_below_band": 6.344635039567947e-09,
      "tokens_p.mean_in_band": 0.6653645833333334,
      "tokens_rate.above_band": 0.9820936639118457,
      "tokens_rate.below_band": 0.0013774104683195593,
      "tokens_rate.in_band": 0.01652892561983471
    },
    {
      "epoch": 1.8450797872340425,
      "grad_norm": 58.56957262009416,
      "learning_rate": 1.6061478621687922e-07,
      "loss": 0.3042,
      "step": 11100,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.594059405940594,
      "success_rate.epoch.env.math": 0.9809342230695901,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617901625501373,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6041323168269881,
      "success_rate.epoch.global": 0.8611565739225314,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9936577490774908,
      "tokens_p.mean_in_band": 0.888671875,
      "tokens_rate.above_band": 0.9963235294117647,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003676470588235294
    },
    {
      "epoch": 1.845910904255319,
      "grad_norm": 32.52784351638375,
      "learning_rate": 1.6060824804035872e-07,
      "loss": 0.16,
      "step": 11105,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5945611866501854,
      "success_rate.epoch.env.math": 0.9809342230695901,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9616114743724953,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6041616888753472,
      "success_rate.epoch.global": 0.8611148970969061,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4523809523809524,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9954651680391721,
      "tokens_p.mean_below_band": 2.9976945370435715e-09,
      "tokens_p.mean_in_band": 0.5656887755102041,
      "tokens_rate.above_band": 0.9014847512038523,
      "tokens_rate.below_band": 0.00020064205457463884,
      "tokens_rate.in_band": 0.09831460674157304
    },
    {
      "epoch": 1.8467420212765957,
      "grad_norm": 16.01149184544124,
      "learning_rate": 1.6060174427944715e-07,
      "loss": 0.2007,
      "step": 11110,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5955610357583231,
      "success_rate.epoch.env.math": 0.9809523809523809,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9616357504215851,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6042564418789852,
      "success_rate.epoch.global": 0.8612283807708021,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9923155737704918,
      "tokens_p.mean_in_band": 0.75,
      "tokens_rate.above_band": 0.9807073954983923,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01929260450160772
    },
    {
      "epoch": 1.8475731382978724,
      "grad_norm": 257.7137592163602,
      "learning_rate": 1.6059527494568714e-07,
      "loss": 0.3892,
      "step": 11115,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5960591133004927,
      "success_rate.epoch.env.math": 0.9809523809523809,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9616438356164384,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.60430245667326,
      "success_rate.epoch.global": 0.8612661674608577,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9977302922940655,
      "tokens_p.mean_in_band": 0.4939152644230769,
      "tokens_rate.above_band": 0.9774891774891775,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.022510822510822513
    },
    {
      "epoch": 1.8484042553191489,
      "grad_norm": 71.67974653821472,
      "learning_rate": 1.6058884005056018e-07,
      "loss": 0.3051,
      "step": 11120,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4470588235294118,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5960591133004927,
      "success_rate.epoch.env.math": 0.9809523809523809,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.961676142345757,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6043053936486525,
      "success_rate.epoch.global": 0.861341679140019,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9988924050632911,
      "tokens_p.mean_in_band": 0.6510416666666666,
      "tokens_rate.above_band": 0.9850374064837906,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014962593516209476
    },
    {
      "epoch": 1.8492353723404256,
      "grad_norm": 63.31737710973163,
      "learning_rate": 1.6058243960548658e-07,
      "loss": 0.3134,
      "step": 11125,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5953259532595326,
      "success_rate.epoch.env.math": 0.9809885931558935,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.961692275310461,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6037709233499365,
      "success_rate.epoch.global": 0.8610657966286025,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9968039772727273,
      "tokens_p.mean_in_band": 0.66796875,
      "tokens_rate.above_band": 0.9832402234636871,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01675977653631285
    },
    {
      "epoch": 1.8500664893617023,
      "grad_norm": 94.36367572639328,
      "learning_rate": 1.6057607362182562e-07,
      "loss": 0.2235,
      "step": 11130,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5953259532595326,
      "success_rate.epoch.env.math": 0.9809885931558935,
      "success_rate.epoch.env.sat": 0.10749185667752444,
      "success_rate.epoch.env.science": 0.9617245005257623,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.603773852914964,
      "success_rate.epoch.global": 0.8611413043478261,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9966738861386139,
      "tokens_p.mean_in_band": 0.6981026785714286,
      "tokens_rate.above_band": 0.9914110429447853,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008588957055214725
    },
    {
      "epoch": 1.8508976063829787,
      "grad_norm": 21.907886986195273,
      "learning_rate": 1.605697421108753e-07,
      "loss": 0.2361,
      "step": 11135,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5958230958230958,
      "success_rate.epoch.env.math": 0.9810066476733144,
      "success_rate.epoch.env.sat": 0.10714285714285714,
      "success_rate.epoch.env.science": 0.9617486338797814,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6037911557240854,
      "success_rate.epoch.global": 0.8611186532717893,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9955645161290323,
      "tokens_p.mean_in_band": 0.635546875,
      "tokens_rate.above_band": 0.950920245398773,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.049079754601226995
    },
    {
      "epoch": 1.8517287234042552,
      "grad_norm": 46.32505353708447,
      "learning_rate": 1.6056344508387257e-07,
      "loss": 0.3269,
      "step": 11140,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5958230958230958,
      "success_rate.epoch.env.math": 0.9810066476733144,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9615788368675204,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6037441977558795,
      "success_rate.epoch.global": 0.8609603906673902,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.5833333333333334,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9955673758865248,
      "tokens_p.mean_below_band": 3.5943231776330853e-09,
      "tokens_p.mean_in_band": 0.5859375,
      "tokens_rate.above_band": 0.9644322845417237,
      "tokens_rate.below_band": 0.0027359781121751026,
      "tokens_rate.in_band": 0.03283173734610123
    },
    {
      "epoch": 1.852559840425532,
      "grad_norm": 122.98574198193228,
      "learning_rate": 1.6055718255199305e-07,
      "loss": 0.33,
      "step": 11145,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.596319018404908,
      "success_rate.epoch.env.math": 0.9810246679316889,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9613932018464121,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6037740439212503,
      "success_rate.epoch.global": 0.8609190727938186,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8,
      "success_rate.window.env_macro_mean": 0.76,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9975453172205438,
      "tokens_p.mean_below_band": 3.4051481634378433e-09,
      "tokens_p.mean_in_band": 0.6827651515151515,
      "tokens_rate.above_band": 0.9068493150684932,
      "tokens_rate.below_band": 0.0027397260273972603,
      "tokens_rate.in_band": 0.09041095890410959
    },
    {
      "epoch": 1.8533909574468086,
      "grad_norm": 44.922002995643176,
      "learning_rate": 1.6055095452635126e-07,
      "loss": 0.207,
      "step": 11150,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5955882352941176,
      "success_rate.epoch.env.math": 0.9810785241248817,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9614093959731543,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6037139773038999,
      "success_rate.epoch.global": 0.8609154929577465,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9989804964539007,
      "tokens_p.mean_in_band": 0.5790178571428571,
      "tokens_rate.above_band": 0.9757785467128027,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02422145328719723
    },
    {
      "epoch": 1.854222074468085,
      "grad_norm": 24.858581889020314,
      "learning_rate": 1.6054476101800034e-07,
      "loss": 0.2904,
      "step": 11155,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5955882352941176,
      "success_rate.epoch.env.math": 0.9810964083175804,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9614255765199161,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6037170740983963,
      "success_rate.epoch.global": 0.8609719777988358,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9925223214285714,
      "tokens_p.mean_in_band": 0.71484375,
      "tokens_rate.above_band": 0.9893992932862191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01060070671378092
    },
    {
      "epoch": 1.8550531914893615,
      "grad_norm": 111.33303799431422,
      "learning_rate": 1.6053860203793232e-07,
      "loss": 0.2037,
      "step": 11160,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5960832313341493,
      "success_rate.epoch.env.math": 0.9810964083175804,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9614659685863874,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.603765745744442,
      "success_rate.epoch.global": 0.8610848099553632,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9969967532467533,
      "tokens_p.mean_in_band": 0.5687040441176471,
      "tokens_rate.above_band": 0.9783989834815756,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021601016518424398
    },
    {
      "epoch": 1.8558843085106385,
      "grad_norm": 77.84022231131404,
      "learning_rate": 1.6053247759707787e-07,
      "loss": 0.225,
      "step": 11165,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5965770171149144,
      "success_rate.epoch.env.math": 0.9811142587346553,
      "success_rate.epoch.env.sat": 0.10679611650485436,
      "success_rate.epoch.env.science": 0.9614740368509213,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038129916046577,
      "success_rate.epoch.global": 0.8611411573823688,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9903748647917794,
      "tokens_p.mean_below_band": 6.258487701416016e-07,
      "tokens_p.mean_in_band": 0.5283040364583333,
      "tokens_rate.above_band": 0.8366515837104073,
      "tokens_rate.below_band": 0.00045248868778280545,
      "tokens_rate.in_band": 0.16289592760180996
    },
    {
      "epoch": 1.856715425531915,
      "grad_norm": 28.457786221125268,
      "learning_rate": 1.6052638770630633e-07,
      "loss": 0.2012,
      "step": 11170,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5970695970695971,
      "success_rate.epoch.env.math": 0.9811320754716981,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.9615143275465384,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038317355851772,
      "success_rate.epoch.global": 0.8611561318206374,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9942660550458715,
      "tokens_p.mean_in_band": 0.620361328125,
      "tokens_rate.above_band": 0.9316239316239316,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06837606837606838
    },
    {
      "epoch": 1.8575465425531914,
      "grad_norm": 202.00326093856438,
      "learning_rate": 1.605203323764258e-07,
      "loss": 0.2977,
      "step": 11175,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5970695970695971,
      "success_rate.epoch.env.math": 0.9811320754716981,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.9615223755750731,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.603832467224135,
      "success_rate.epoch.global": 0.8611748818365969,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.2916666666666667,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9949583333333333,
      "tokens_p.mean_below_band": 9.549694368615746e-12,
      "tokens_p.mean_in_band": 0.4678308823529412,
      "tokens_rate.above_band": 0.9765625,
      "tokens_rate.below_band": 0.0013020833333333333,
      "tokens_rate.in_band": 0.022135416666666668
    },
    {
      "epoch": 1.858377659574468,
      "grad_norm": 26.559728022777445,
      "learning_rate": 1.60514311618183e-07,
      "loss": 0.2024,
      "step": 11180,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5168539325842697,
      "success_rate.epoch.env.logic": 0.5975609756097561,
      "success_rate.epoch.env.math": 0.981203007518797,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.9615384615384616,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6038850487287392,
      "success_rate.epoch.global": 0.8613059902860226,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9947465195692146,
      "tokens_p.mean_in_band": 0.5190096263277694,
      "tokens_rate.above_band": 0.8524406627854904,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14755933721450962
    },
    {
      "epoch": 1.8592087765957448,
      "grad_norm": 71.0598117766657,
      "learning_rate": 1.605083254422633e-07,
      "loss": 0.2666,
      "step": 11185,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5139664804469274,
      "success_rate.epoch.env.logic": 0.5975609756097561,
      "success_rate.epoch.env.math": 0.9812206572769953,
      "success_rate.epoch.env.sat": 0.1064516129032258,
      "success_rate.epoch.env.science": 0.9615705931495405,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6036270786589151,
      "success_rate.epoch.global": 0.8612833647883527,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9926447451227187,
      "tokens_p.mean_below_band": 2.2032431193760464e-07,
      "tokens_p.mean_in_band": 0.4401719252950644,
      "tokens_rate.above_band": 0.771921301918873,
      "tokens_rate.below_band": 0.0017002671848433326,
      "tokens_rate.in_band": 0.2263784308962837
    },
    {
      "epoch": 1.8600398936170213,
      "grad_norm": 17.965782810363788,
      "learning_rate": 1.6050237385929072e-07,
      "loss": 0.286,
      "step": 11190,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5111111111111111,
      "success_rate.epoch.env.logic": 0.5980511571254568,
      "success_rate.epoch.env.math": 0.9812382739212008,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9615786176654834,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6057756199924909,
      "success_rate.epoch.global": 0.8611260775862069,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9976018396846255,
      "tokens_p.mean_below_band": 2.5331974029541016e-07,
      "tokens_p.mean_in_band": 0.5321607268258427,
      "tokens_rate.above_band": 0.9140043238049483,
      "tokens_rate.below_band": 0.00048042277203939464,
      "tokens_rate.in_band": 0.08551525342301225
    },
    {
      "epoch": 1.8608710106382977,
      "grad_norm": 60.293293328870845,
      "learning_rate": 1.6049645687982784e-07,
      "loss": 0.2481,
      "step": 11195,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5111111111111111,
      "success_rate.epoch.env.logic": 0.5985401459854015,
      "success_rate.epoch.env.math": 0.9812558575445174,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9616026711185309,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058238587139736,
      "success_rate.epoch.global": 0.8612195450262485,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9936538461538461,
      "tokens_p.mean_in_band": 0.58125,
      "tokens_rate.above_band": 0.9154929577464789,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08450704225352113
    },
    {
      "epoch": 1.8617021276595744,
      "grad_norm": 100.32767598264614,
      "learning_rate": 1.6049057451437579e-07,
      "loss": 0.2486,
      "step": 11200,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5111111111111111,
      "success_rate.epoch.env.logic": 0.5985401459854015,
      "success_rate.epoch.env.math": 0.9812734082397003,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9616186900292032,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.605826910496324,
      "success_rate.epoch.global": 0.861275565123789,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9990727002967359,
      "tokens_p.mean_in_band": 0.7513020833333334,
      "tokens_rate.above_band": 0.9825072886297376,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01749271137026239
    },
    {
      "epoch": 1.8625332446808511,
      "grad_norm": 48.68398984170237,
      "learning_rate": 1.6048472677337444e-07,
      "loss": 0.2288,
      "step": 11205,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5111111111111111,
      "success_rate.epoch.env.logic": 0.5985401459854015,
      "success_rate.epoch.env.math": 0.9812734082397003,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9616426933500104,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058290926163974,
      "success_rate.epoch.global": 0.8613315400134499,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.6875,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9971915121255349,
      "tokens_p.mean_below_band": 2.514570951461792e-08,
      "tokens_p.mean_in_band": 0.5790441176470589,
      "tokens_rate.above_band": 0.9749652294853964,
      "tokens_rate.below_band": 0.0013908205841446453,
      "tokens_rate.in_band": 0.02364394993045897
    },
    {
      "epoch": 1.8633643617021276,
      "grad_norm": 162.5659880122399,
      "learning_rate": 1.6047891366720202e-07,
      "loss": 0.2419,
      "step": 11210,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5111111111111111,
      "success_rate.epoch.env.logic": 0.5990279465370595,
      "success_rate.epoch.env.math": 0.9812909260991581,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9616746511143511,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058779359050752,
      "success_rate.epoch.global": 0.8614433543878511,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9965234375,
      "tokens_p.mean_below_band": 1.6589183360338211e-09,
      "tokens_p.mean_in_band": 0.746875,
      "tokens_rate.above_band": 0.9918175055789735,
      "tokens_rate.below_band": 0.0007438631291842301,
      "tokens_rate.in_band": 0.007438631291842301
    },
    {
      "epoch": 1.8641954787234043,
      "grad_norm": 32.32806014290728,
      "learning_rate": 1.604731352061754e-07,
      "loss": 0.18,
      "step": 11215,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.5990279465370595,
      "success_rate.epoch.env.math": 0.9813084112149533,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9617145235122764,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6061286996413244,
      "success_rate.epoch.global": 0.8615735767991407,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9936655405405406,
      "tokens_p.mean_in_band": 0.87890625,
      "tokens_rate.above_band": 0.9966329966329966,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003367003367003367
    },
    {
      "epoch": 1.865026595744681,
      "grad_norm": 86.18835233329912,
      "learning_rate": 1.604673914005499e-07,
      "loss": 0.3505,
      "step": 11220,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.5995145631067961,
      "success_rate.epoch.env.math": 0.9813606710158435,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9617384071532543,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6061798596423794,
      "success_rate.epoch.global": 0.8617035546613011,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9898574561403509,
      "tokens_p.mean_in_band": 0.729375,
      "tokens_rate.above_band": 0.9011857707509882,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09881422924901186
    },
    {
      "epoch": 1.8658577127659575,
      "grad_norm": 198.82987104670391,
      "learning_rate": 1.6046168226051942e-07,
      "loss": 0.2742,
      "step": 11225,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.4418604651162791,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9813780260707635,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.961770205692915,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6062284587776327,
      "success_rate.epoch.global": 0.8618147701380512,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9990079365079365,
      "tokens_p.mean_in_band": 0.69384765625,
      "tokens_rate.above_band": 0.9895287958115183,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010471204188481676
    },
    {
      "epoch": 1.866688829787234,
      "grad_norm": 186.0056977156713,
      "learning_rate": 1.6045600779621625e-07,
      "loss": 0.2211,
      "step": 11230,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44508670520231214,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9813953488372092,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9618019514220469,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6065262141032336,
      "success_rate.epoch.global": 0.8619258068836213,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9996056050482554,
      "tokens_p.mean_in_band": 0.6617838541666666,
      "tokens_rate.above_band": 0.9739696312364425,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026030368763557483
    },
    {
      "epoch": 1.8675199468085106,
      "grad_norm": 65.54784536311597,
      "learning_rate": 1.6045036801771116e-07,
      "loss": 0.1235,
      "step": 11235,
      "success_rate.epoch.env.abd": 0.6086956521739131,
      "success_rate.epoch.env.agentgym:alfworld": 0.44508670520231214,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9814126394052045,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9618415595188718,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6065313867091263,
      "success_rate.epoch.global": 0.862036665328516,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9861111111111112,
      "tokens_p.mean_in_band": 0.8697916666666666,
      "tokens_rate.above_band": 0.972972972972973,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02702702702702703
    },
    {
      "epoch": 1.8683510638297873,
      "grad_norm": 200.75192461161555,
      "learning_rate": 1.604447629350134e-07,
      "loss": 0.208,
      "step": 11240,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44508670520231214,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9814126394052045,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9618810855603894,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6053576189562779,
      "success_rate.epoch.global": 0.8620136381869233,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959706303724928,
      "tokens_p.mean_in_band": 0.10093788735667802,
      "tokens_rate.above_band": 0.1778343949044586,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.8221656050955414
    },
    {
      "epoch": 1.8691821808510638,
      "grad_norm": 23.235407406377817,
      "learning_rate": 1.6043919255807063e-07,
      "loss": 0.1883,
      "step": 11245,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44508670520231214,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9814126394052045,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9619047619047619,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.605359771351221,
      "success_rate.epoch.global": 0.8620689655172413,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9995725034199726,
      "tokens_p.mean_in_band": 0.696533203125,
      "tokens_rate.above_band": 0.9785809906291834,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0214190093708166
    },
    {
      "epoch": 1.8700132978723403,
      "grad_norm": 30.66713997302514,
      "learning_rate": 1.6043365689676888e-07,
      "loss": 0.2502,
      "step": 11250,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44508670520231214,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9814643188137164,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9619205298013245,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6053659029244095,
      "success_rate.epoch.global": 0.8621610792039536,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9802631578947368,
      "tokens_p.mean_in_band": 0.849609375,
      "tokens_rate.above_band": 0.9884393063583815,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011560693641618497
    },
    {
      "epoch": 1.870844414893617,
      "grad_norm": 67.76901205467126,
      "learning_rate": 1.6042815596093259e-07,
      "loss": 0.3457,
      "step": 11255,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44508670520231214,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5138121546961326,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9619598924953483,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6053710415936631,
      "success_rate.epoch.global": 0.862271453356466,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9842641843971631,
      "tokens_p.mean_below_band": 8.003553375601768e-11,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.9791666666666666,
      "tokens_rate.below_band": 0.006944444444444444,
      "tokens_rate.in_band": 0.013888888888888888
    },
    {
      "epoch": 1.8716755319148937,
      "grad_norm": 56.42043560569765,
      "learning_rate": 1.6042268976032464e-07,
      "loss": 0.2009,
      "step": 11260,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.4482758620689655,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.599758162031439,
      "success_rate.epoch.env.math": 0.9814814814814815,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9619834710743802,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058839742540729,
      "success_rate.epoch.global": 0.8622666666666666,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9166666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9969491332116789,
      "tokens_p.mean_in_band": 0.5971354166666667,
      "tokens_rate.above_band": 0.9864986498649865,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013501350135013501
    },
    {
      "epoch": 1.8725066489361701,
      "grad_norm": 95.31555178768237,
      "learning_rate": 1.6041725830464608e-07,
      "loss": 0.2012,
      "step": 11265,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44571428571428573,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007237635705669,
      "success_rate.epoch.env.math": 0.9814986123959297,
      "success_rate.epoch.env.sat": 0.10610932475884244,
      "success_rate.epoch.env.science": 0.9619913241065895,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6057411569023553,
      "success_rate.epoch.global": 0.8622251832111926,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.996482683982684,
      "tokens_p.mean_in_band": 0.6136300223214286,
      "tokens_rate.above_band": 0.9705882352941176,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029411764705882353
    },
    {
      "epoch": 1.8733377659574468,
      "grad_norm": 107.83403861715247,
      "learning_rate": 1.6041186160353648e-07,
      "loss": 0.2631,
      "step": 11270,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44571428571428573,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007237635705669,
      "success_rate.epoch.env.math": 0.9814986123959297,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.9620070204418749,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6057116662065074,
      "success_rate.epoch.global": 0.8621470431539691,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949404761904762,
      "tokens_p.mean_in_band": 0.6298828125,
      "tokens_rate.above_band": 0.9292035398230089,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07079646017699115
    },
    {
      "epoch": 1.8741688829787235,
      "grad_norm": 29.44704603586585,
      "learning_rate": 1.604064996665737e-07,
      "loss": 0.2217,
      "step": 11275,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44571428571428573,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007237635705669,
      "success_rate.epoch.env.math": 0.9815157116451017,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.9620462046204621,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6057167828817582,
      "success_rate.epoch.global": 0.8622571200425871,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9886744966442953,
      "tokens_p.mean_in_band": 0.869140625,
      "tokens_rate.above_band": 0.9867549668874173,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013245033112582781
    },
    {
      "epoch": 1.875,
      "grad_norm": 47.11825716294459,
      "learning_rate": 1.6040117250327378e-07,
      "loss": 0.236,
      "step": 11280,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007237635705669,
      "success_rate.epoch.env.math": 0.981549815498155,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.962061855670103,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060076106592169,
      "success_rate.epoch.global": 0.8623487165846522,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9979104291417166,
      "tokens_p.mean_in_band": 0.6842672413793104,
      "tokens_rate.above_band": 0.9718719689621726,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.028128031037827354
    },
    {
      "epoch": 1.8758311170212765,
      "grad_norm": 62.69377819187668,
      "learning_rate": 1.603958801230912e-07,
      "loss": 0.275,
      "step": 11285,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007237635705669,
      "success_rate.epoch.env.math": 0.981549815498155,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.9620853080568721,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060097426943777,
      "success_rate.epoch.global": 0.8624036160595586,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9853987068965517,
      "tokens_p.mean_in_band": 0.85302734375,
      "tokens_rate.above_band": 0.9863945578231292,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013605442176870748
    },
    {
      "epoch": 1.8766622340425532,
      "grad_norm": 89.13788747062225,
      "learning_rate": 1.6039062253541858e-07,
      "loss": 0.2578,
      "step": 11290,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6,
      "success_rate.epoch.env.math": 0.9815837937384899,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.9621087314662273,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6059491643379343,
      "success_rate.epoch.global": 0.8623804463336876,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9972696799307958,
      "tokens_p.mean_in_band": 0.5565518465909091,
      "tokens_rate.above_band": 0.9633333333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03666666666666667
    },
    {
      "epoch": 1.8774933510638299,
      "grad_norm": 58.58675618014322,
      "learning_rate": 1.603853997495869e-07,
      "loss": 0.3193,
      "step": 11295,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.5992779783393501,
      "success_rate.epoch.env.math": 0.9816007359705612,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.9621243310004117,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058864843475349,
      "success_rate.epoch.global": 0.8623207647371216,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9941793893129771,
      "tokens_p.mean_in_band": 0.5371942934782609,
      "tokens_rate.above_band": 0.9660766961651918,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03392330383480826
    },
    {
      "epoch": 1.8783244680851063,
      "grad_norm": 85.73088210912971,
      "learning_rate": 1.603802117748653e-07,
      "loss": 0.3214,
      "step": 11300,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.5992779783393501,
      "success_rate.epoch.env.math": 0.9816007359705612,
      "success_rate.epoch.env.sat": 0.10576923076923077,
      "success_rate.epoch.env.science": 0.9621554915672563,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058893171263389,
      "success_rate.epoch.global": 0.8623938428874734,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9936868686868687,
      "tokens_p.mean_in_band": 0.6192555147058824,
      "tokens_rate.above_band": 0.9209302325581395,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07906976744186046
    },
    {
      "epoch": 1.879155585106383,
      "grad_norm": 8.608370218210926,
      "learning_rate": 1.6037505862046114e-07,
      "loss": 0.1815,
      "step": 11305,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6002400960384153,
      "success_rate.epoch.env.math": 0.9816176470588235,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9621788283658788,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6059497211918727,
      "success_rate.epoch.global": 0.862388969905873,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959239130434783,
      "tokens_p.mean_in_band": 0.6294270833333333,
      "tokens_rate.above_band": 0.9608355091383812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0391644908616188
    },
    {
      "epoch": 1.8799867021276597,
      "grad_norm": 103.69552313615101,
      "learning_rate": 1.603699402955201e-07,
      "loss": 0.4362,
      "step": 11310,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007194244604317,
      "success_rate.epoch.env.math": 0.9816345270890725,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622021364009861,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6059969499634522,
      "success_rate.epoch.global": 0.8624801271860095,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.9523809523809524,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9931768558951966,
      "tokens_p.mean_below_band": 5.20230969414115e-10,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9870689655172413,
      "tokens_rate.below_band": 0.004310344827586207,
      "tokens_rate.in_band": 0.008620689655172414
    },
    {
      "epoch": 1.8808178191489362,
      "grad_norm": 130.46109651089287,
      "learning_rate": 1.6036485680912584e-07,
      "loss": 0.3604,
      "step": 11315,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007194244604317,
      "success_rate.epoch.env.math": 0.981651376146789,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622021364009861,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6059984816959717,
      "success_rate.epoch.global": 0.8624983441515433,
      "success_rate.window.env.logic": 0.25,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.998152359295054,
      "tokens_p.mean_in_band": 0.6106770833333334,
      "tokens_rate.above_band": 0.9865395401009535,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01346045989904655
    },
    {
      "epoch": 1.8816489361702127,
      "grad_norm": 326.2092933475463,
      "learning_rate": 1.6035980817030035e-07,
      "loss": 0.2834,
      "step": 11320,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007194244604317,
      "success_rate.epoch.env.math": 0.9816849816849816,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622098993633189,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060022424687468,
      "success_rate.epoch.global": 0.862552966101695,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.6190476190476191,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9948863636363636,
      "tokens_p.mean_below_band": 1.4915713109076023e-10,
      "tokens_p.mean_in_band": 0.6549479166666666,
      "tokens_rate.above_band": 0.990990990990991,
      "tokens_rate.below_band": 0.0022522522522522522,
      "tokens_rate.in_band": 0.006756756756756757
    },
    {
      "epoch": 1.8824800531914894,
      "grad_norm": 127.88686231043508,
      "learning_rate": 1.6035479438800375e-07,
      "loss": 0.3034,
      "step": 11325,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6007194244604317,
      "success_rate.epoch.env.math": 0.9817184643510055,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622254157257236,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060066969258767,
      "success_rate.epoch.global": 0.8626257278983589,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9989740082079344,
      "tokens_p.mean_in_band": 0.6335227272727273,
      "tokens_rate.above_band": 0.9707835325365206,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029216467463479414
    },
    {
      "epoch": 1.883311170212766,
      "grad_norm": 60.87590487575993,
      "learning_rate": 1.6034981547113425e-07,
      "loss": 0.1766,
      "step": 11330,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6011976047904192,
      "success_rate.epoch.env.math": 0.9817184643510055,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622409193515288,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060515772854942,
      "success_rate.epoch.global": 0.8626802487101468,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9984217171717171,
      "tokens_p.mean_in_band": 0.7094089673913043,
      "tokens_rate.above_band": 0.9717791411042945,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02822085889570552
    },
    {
      "epoch": 1.8841422872340425,
      "grad_norm": 97.77985017579189,
      "learning_rate": 1.603448714285282e-07,
      "loss": 0.2305,
      "step": 11335,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6016746411483254,
      "success_rate.epoch.env.math": 0.9817184643510055,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622641509433962,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060970561900191,
      "success_rate.epoch.global": 0.8627528758429195,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9933986371379898,
      "tokens_p.mean_in_band": 0.7799479166666666,
      "tokens_rate.above_band": 0.9949152542372881,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005084745762711864
    },
    {
      "epoch": 1.884973404255319,
      "grad_norm": 103.29748197465557,
      "learning_rate": 1.603399622689601e-07,
      "loss": 0.3439,
      "step": 11340,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6014319809069213,
      "success_rate.epoch.env.math": 0.9817184643510055,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9622796227962279,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.606076402700149,
      "success_rate.epoch.global": 0.8626932734240782,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9949142156862745,
      "tokens_p.mean_in_band": 0.5248825328162291,
      "tokens_rate.above_band": 0.9068681929317626,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09313180706823738
    },
    {
      "epoch": 1.8858045212765957,
      "grad_norm": 52.62326960446603,
      "learning_rate": 1.6033508800114245e-07,
      "loss": 0.1612,
      "step": 11345,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6014319809069213,
      "success_rate.epoch.env.math": 0.9817184643510055,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.962318246979316,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060799139895205,
      "success_rate.epoch.global": 0.862783940834654,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9957896706586826,
      "tokens_p.mean_in_band": 0.826171875,
      "tokens_rate.above_band": 0.9940476190476191,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005952380952380952
    },
    {
      "epoch": 1.8866356382978724,
      "grad_norm": 53.55374667437642,
      "learning_rate": 1.6033024863372592e-07,
      "loss": 0.2834,
      "step": 11350,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6011904761904762,
      "success_rate.epoch.env.math": 0.9817184643510055,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9623336745138178,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060593615184348,
      "success_rate.epoch.global": 0.8627243928194298,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777778,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9967575571895425,
      "tokens_p.mean_in_band": 0.6988636363636364,
      "tokens_rate.above_band": 0.9823434991974318,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01765650080256822
    },
    {
      "epoch": 1.8874667553191489,
      "grad_norm": 47.18018054912582,
      "learning_rate": 1.603254441752992e-07,
      "loss": 0.2352,
      "step": 11355,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5164835164835165,
      "success_rate.epoch.env.logic": 0.6011904761904762,
      "success_rate.epoch.env.math": 0.9817351598173516,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9623567921440261,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6060629808908488,
      "success_rate.epoch.global": 0.862796833773087,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9967873831775701,
      "tokens_p.mean_in_band": 0.673828125,
      "tokens_rate.above_band": 0.9938080495356038,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006191950464396285
    },
    {
      "epoch": 1.8882978723404256,
      "grad_norm": 40.45229193401803,
      "learning_rate": 1.6032067463438904e-07,
      "loss": 0.2188,
      "step": 11360,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5136612021857924,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9817518248175182,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9623875715453802,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058538298737806,
      "success_rate.epoch.global": 0.8627916172400159,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9984302325581396,
      "tokens_p.mean_in_band": 0.6436941964285714,
      "tokens_rate.above_band": 0.9808394160583942,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01916058394160584
    },
    {
      "epoch": 1.8891289893617023,
      "grad_norm": 26.806448069486844,
      "learning_rate": 1.6031594001946017e-07,
      "loss": 0.235,
      "step": 11365,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5136612021857924,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9817518248175182,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9624029423784226,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058552272222392,
      "success_rate.epoch.global": 0.8628277770457241,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974573490813649,
      "tokens_p.mean_in_band": 0.3175536303630363,
      "tokens_rate.above_band": 0.7154929577464789,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.28450704225352114
    },
    {
      "epoch": 1.8899601063829787,
      "grad_norm": 89.31725038185034,
      "learning_rate": 1.603112403389154e-07,
      "loss": 0.1634,
      "step": 11370,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5136612021857924,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9817850637522769,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9624183006535948,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058596451504147,
      "success_rate.epoch.global": 0.8629000395100751,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974279835390947,
      "tokens_p.mean_in_band": 0.7064732142857143,
      "tokens_rate.above_band": 0.9886086248982913,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011391375101708706
    },
    {
      "epoch": 1.8907912234042552,
      "grad_norm": 62.86644434378806,
      "learning_rate": 1.6030657560109545e-07,
      "loss": 0.3502,
      "step": 11375,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5136612021857924,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9817850637522769,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9624336463862802,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058610402170224,
      "success_rate.epoch.global": 0.862936142198815,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9968387230514096,
      "tokens_p.mean_in_band": 0.6637620192307693,
      "tokens_rate.above_band": 0.9893355209187858,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01066447908121411
    },
    {
      "epoch": 1.891622340425532,
      "grad_norm": 0.0,
      "learning_rate": 1.603019458142792e-07,
      "loss": 0.2206,
      "step": 11380,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.44886363636363635,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5136612021857924,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9818016378525932,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9624566415017344,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058646374184561,
      "success_rate.epoch.global": 0.863008290564548,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959580838323353,
      "tokens_p.mean_in_band": 0.5863970588235294,
      "tokens_rate.above_band": 0.9800469483568075,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01995305164319249
    },
    {
      "epoch": 1.8924534574468086,
      "grad_norm": 49.852831788625586,
      "learning_rate": 1.6029735098668332e-07,
      "loss": 0.2803,
      "step": 11385,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.4519774011299435,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9818016378525932,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9624719559453396,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058953139858662,
      "success_rate.epoch.global": 0.8629488359857951,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9951102418207681,
      "tokens_p.mean_in_band": 0.7209821428571429,
      "tokens_rate.above_band": 0.9525745257452575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04742547425474255
    },
    {
      "epoch": 1.893284574468085,
      "grad_norm": 80.8369620975784,
      "learning_rate": 1.6029279112646247e-07,
      "loss": 0.2365,
      "step": 11390,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.4519774011299435,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6016646848989299,
      "success_rate.epoch.env.math": 0.9818346957311535,
      "success_rate.epoch.env.sat": 0.10543130990415335,
      "success_rate.epoch.env.science": 0.9624796084828712,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6058990149327836,
      "success_rate.epoch.global": 0.8630028924533263,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8888888888888888,
      "tokens_p.mean_above_band": 0.9992982784431138,
      "tokens_p.mean_in_band": 0.7046875,
      "tokens_rate.above_band": 0.9852507374631269,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014749262536873156
    },
    {
      "epoch": 1.8941156914893615,
      "grad_norm": 141.69365597165583,
      "learning_rate": 1.6028826624170935e-07,
      "loss": 0.1629,
      "step": 11395,
      "success_rate.epoch.env.abd": 0.5957446808510638,
      "success_rate.epoch.env.agentgym:alfworld": 0.4519774011299435,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6021377672209026,
      "success_rate.epoch.env.math": 0.9818676337262012,
      "success_rate.epoch.env.sat": 0.10509554140127389,
      "success_rate.epoch.env.science": 0.9625101874490628,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6059172722764502,
      "success_rate.epoch.global": 0.8630154977672708,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99292071197411,
      "tokens_p.mean_in_band": 0.6747532894736842,
      "tokens_rate.above_band": 0.9420731707317073,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.057926829268292686
    },
    {
      "epoch": 1.8949468085106385,
      "grad_norm": 48.5536778056079,
      "learning_rate": 1.6028377634045448e-07,
      "loss": 0.1333,
      "step": 11400,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4519774011299435,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6021377672209026,
      "success_rate.epoch.env.math": 0.9818840579710145,
      "success_rate.epoch.env.sat": 0.10476190476190476,
      "success_rate.epoch.env.science": 0.9625330889839137,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6066561518178956,
      "success_rate.epoch.global": 0.862992125984252,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9967384708737864,
      "tokens_p.mean_in_band": 0.74609375,
      "tokens_rate.above_band": 0.9903846153846154,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009615384615384616
    },
    {
      "epoch": 1.895777925531915,
      "grad_norm": 98.79742863293252,
      "learning_rate": 1.6027932143066636e-07,
      "loss": 0.2673,
      "step": 11405,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6018957345971564,
      "success_rate.epoch.env.math": 0.9818840579710145,
      "success_rate.epoch.env.sat": 0.10476190476190476,
      "success_rate.epoch.env.science": 0.9625483411357623,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069154243791173,
      "success_rate.epoch.global": 0.8629508196721312,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9982861060329068,
      "tokens_p.mean_in_band": 0.6682942708333334,
      "tokens_rate.above_band": 0.9785330948121646,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02146690518783542
    },
    {
      "epoch": 1.8966090425531914,
      "grad_norm": 129.38304186776782,
      "learning_rate": 1.6027490152025135e-07,
      "loss": 0.2258,
      "step": 11410,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6023668639053255,
      "success_rate.epoch.env.math": 0.9818840579710145,
      "success_rate.epoch.env.sat": 0.10476190476190476,
      "success_rate.epoch.env.science": 0.9625788082163921,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069610240508263,
      "success_rate.epoch.global": 0.8630406290956749,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9935109289617486,
      "tokens_p.mean_in_band": 0.8151041666666666,
      "tokens_rate.above_band": 0.9838709677419355,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.016129032258064516
    },
    {
      "epoch": 1.897440159574468,
      "grad_norm": 32.149604529790686,
      "learning_rate": 1.6027051661705372e-07,
      "loss": 0.2143,
      "step": 11415,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5108695652173914,
      "success_rate.epoch.env.logic": 0.6023668639053255,
      "success_rate.epoch.env.math": 0.9818840579710145,
      "success_rate.epoch.env.sat": 0.10725552050473186,
      "success_rate.epoch.env.science": 0.9626092257671205,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071904816229677,
      "success_rate.epoch.global": 0.8630172865374541,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.sat": 0.5,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9870383522727273,
      "tokens_p.mean_in_band": 0.7102864583333334,
      "tokens_rate.above_band": 0.9361702127659575,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06382978723404255
    },
    {
      "epoch": 1.8982712765957448,
      "grad_norm": 22.914581354953942,
      "learning_rate": 1.6026616672885558e-07,
      "loss": 0.2863,
      "step": 11420,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081081081081081,
      "success_rate.epoch.env.logic": 0.6023668639053255,
      "success_rate.epoch.env.math": 0.9819004524886877,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9626092257671205,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069102685227286,
      "success_rate.epoch.global": 0.8628092682288258,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9847608024691358,
      "tokens_p.mean_in_band": 0.7594039351851852,
      "tokens_rate.above_band": 0.8888888888888888,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1111111111111111
    },
    {
      "epoch": 1.8991023936170213,
      "grad_norm": 90.45965953292954,
      "learning_rate": 1.6026185186337692e-07,
      "loss": 0.1591,
      "step": 11425,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081081081081081,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.9819168173598554,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9626471782379212,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069579351472073,
      "success_rate.epoch.global": 0.8629348679047868,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9947604790419161,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.8999335106382977,
      "grad_norm": 21.472755586414458,
      "learning_rate": 1.602575720282756e-07,
      "loss": 0.1883,
      "step": 11430,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081081081081081,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.98193315266486,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9626699127612092,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069614869497794,
      "success_rate.epoch.global": 0.8630065359477124,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8888888888888888,
      "success_rate.window.env_macro_mean": 0.9444444444444444,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9921875,
      "tokens_p.mean_in_band": 0.74609375,
      "tokens_rate.above_band": 0.9428571428571428,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05714285714285714
    },
    {
      "epoch": 1.9007646276595744,
      "grad_norm": 220.3343957923839,
      "learning_rate": 1.6025332723114724e-07,
      "loss": 0.1392,
      "step": 11435,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081081081081081,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.981965734896303,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9627077421970004,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.606967888010437,
      "success_rate.epoch.global": 0.8631317748465457,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9923611111111111,
      "tokens_p.mean_in_band": 0.84375,
      "tokens_rate.above_band": 0.9782608695652174,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021739130434782608
    },
    {
      "epoch": 1.9015957446808511,
      "grad_norm": 16.547993577199946,
      "learning_rate": 1.6024911747952533e-07,
      "loss": 0.1633,
      "step": 11440,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5081081081081081,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.9819819819819819,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.962753036437247,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069734826764303,
      "success_rate.epoch.global": 0.8632567849686847,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9947916666666666,
      "tokens_p.mean_in_band": 0.6449652777777778,
      "tokens_rate.above_band": 0.9032258064516129,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0967741935483871
    },
    {
      "epoch": 1.9024268617021276,
      "grad_norm": 124.53037003467924,
      "learning_rate": 1.6024494278088112e-07,
      "loss": 0.2625,
      "step": 11445,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4550561797752809,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053763440860215,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.9819819819819819,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9627906976744186,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.606728564241438,
      "success_rate.epoch.global": 0.8632333767926988,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9956814472252449,
      "tokens_p.mean_below_band": 4.172325134277344e-07,
      "tokens_p.mean_in_band": 0.5116915287456446,
      "tokens_rate.above_band": 0.9273461150353178,
      "tokens_rate.below_band": 0.0002522704339051463,
      "tokens_rate.in_band": 0.072401614530777
    },
    {
      "epoch": 1.9032579787234043,
      "grad_norm": 41.38374914590418,
      "learning_rate": 1.6024080314262374e-07,
      "loss": 0.1665,
      "step": 11450,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45251396648044695,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053763440860215,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.981998199819982,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9628057408530423,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6065002958525099,
      "success_rate.epoch.global": 0.8631743549648163,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.875,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9958910034602076,
      "tokens_p.mean_below_band": 9.049472282640636e-11,
      "tokens_p.mean_in_band": 0.6884765625,
      "tokens_rate.above_band": 0.9897260273972602,
      "tokens_rate.below_band": 0.003424657534246575,
      "tokens_rate.in_band": 0.00684931506849315
    },
    {
      "epoch": 1.904089095744681,
      "grad_norm": 81.97214940327356,
      "learning_rate": 1.6023669857209997e-07,
      "loss": 0.2303,
      "step": 11455,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45251396648044695,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053763440860215,
      "success_rate.epoch.env.logic": 0.6028368794326241,
      "success_rate.epoch.env.math": 0.9820466786355476,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9626338113512422,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.606489073062852,
      "success_rate.epoch.global": 0.8631688582215857,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.6944444444444443,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9985537190082645,
      "tokens_p.mean_below_band": 1.9744038581848145e-07,
      "tokens_p.mean_in_band": 0.6348586309523809,
      "tokens_rate.above_band": 0.9821428571428571,
      "tokens_rate.below_band": 0.0008116883116883117,
      "tokens_rate.in_band": 0.017045454545454544
    },
    {
      "epoch": 1.9049202127659575,
      "grad_norm": 58.50033841423256,
      "learning_rate": 1.6023262907659447e-07,
      "loss": 0.1489,
      "step": 11460,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45251396648044695,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053763440860215,
      "success_rate.epoch.env.logic": 0.6033057851239669,
      "success_rate.epoch.env.math": 0.9820627802690582,
      "success_rate.epoch.env.sat": 0.1069182389937107,
      "success_rate.epoch.env.science": 0.9626564392410174,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6065352217187274,
      "success_rate.epoch.global": 0.8632578714545928,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.992737676056338,
      "tokens_p.mean_in_band": 0.89453125,
      "tokens_rate.above_band": 0.9964912280701754,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0035087719298245615
    },
    {
      "epoch": 1.905751329787234,
      "grad_norm": 44.43631535460764,
      "learning_rate": 1.6022859466332956e-07,
      "loss": 0.2256,
      "step": 11465,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45251396648044695,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053763440860215,
      "success_rate.epoch.env.logic": 0.6033057851239669,
      "success_rate.epoch.env.math": 0.9820627802690582,
      "success_rate.epoch.env.sat": 0.10658307210031348,
      "success_rate.epoch.env.science": 0.9626715092816788,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6065061220048423,
      "success_rate.epoch.global": 0.8631811679021979,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9969604099678456,
      "tokens_p.mean_in_band": 0.6991458722014925,
      "tokens_rate.above_band": 0.9488939740655988,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05110602593440122
    },
    {
      "epoch": 1.9065824468085106,
      "grad_norm": 53.68976373696804,
      "learning_rate": 1.6022459533946535e-07,
      "loss": 0.169,
      "step": 11470,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45251396648044695,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5053763440860215,
      "success_rate.epoch.env.logic": 0.6033057851239669,
      "success_rate.epoch.env.math": 0.982078853046595,
      "success_rate.epoch.env.sat": 0.10658307210031348,
      "success_rate.epoch.env.science": 0.9626865671641791,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6065089520648457,
      "success_rate.epoch.global": 0.8632345293811753,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9889240506329114,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.9875,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0125
    },
    {
      "epoch": 1.9074135638297873,
      "grad_norm": 108.10591053224735,
      "learning_rate": 1.6022063111209968e-07,
      "loss": 0.2853,
      "step": 11475,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6033057851239669,
      "success_rate.epoch.env.math": 0.9821109123434705,
      "success_rate.epoch.env.sat": 0.10658307210031348,
      "success_rate.epoch.env.science": 0.9627091312235436,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070308846757237,
      "success_rate.epoch.global": 0.8633588777763346,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9988312007874016,
      "tokens_p.mean_in_band": 0.8515625,
      "tokens_rate.above_band": 0.9990167158308751,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0009832841691248771
    },
    {
      "epoch": 1.9082446808510638,
      "grad_norm": 86.67058423284875,
      "learning_rate": 1.6021670198826803e-07,
      "loss": 0.2626,
      "step": 11480,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6033057851239669,
      "success_rate.epoch.env.math": 0.9821587867975022,
      "success_rate.epoch.env.sat": 0.10658307210031348,
      "success_rate.epoch.env.science": 0.9627391742195368,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070379680802716,
      "success_rate.epoch.global": 0.8634830002595381,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9917385057471264,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.9090757978723403,
      "grad_norm": 59.060811380267666,
      "learning_rate": 1.6021280797494365e-07,
      "loss": 0.2623,
      "step": 11485,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6030624263839811,
      "success_rate.epoch.env.math": 0.982174688057041,
      "success_rate.epoch.env.sat": 0.10658307210031348,
      "success_rate.epoch.env.science": 0.962754177571975,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070186540686344,
      "success_rate.epoch.global": 0.8634418363376994,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949776785714286,
      "tokens_p.mean_in_band": 0.5220588235294118,
      "tokens_rate.above_band": 0.978776529338327,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02122347066167291
    },
    {
      "epoch": 1.909906914893617,
      "grad_norm": 51.45124186925617,
      "learning_rate": 1.602089490790375e-07,
      "loss": 0.2935,
      "step": 11490,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6030624263839811,
      "success_rate.epoch.env.math": 0.9821905609973286,
      "success_rate.epoch.env.sat": 0.10658307210031348,
      "success_rate.epoch.env.science": 0.9627766599597586,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070221409166409,
      "success_rate.epoch.global": 0.8635126377187298,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9943321078431373,
      "tokens_p.mean_in_band": 0.8525390625,
      "tokens_rate.above_band": 0.9807692307692307,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019230769230769232
    },
    {
      "epoch": 1.9107380319148937,
      "grad_norm": 67.56799166566323,
      "learning_rate": 1.6020512530739813e-07,
      "loss": 0.1777,
      "step": 11495,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6035294117647059,
      "success_rate.epoch.env.math": 0.9822064056939501,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9627916331456154,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070371164769035,
      "success_rate.epoch.global": 0.8634715025906736,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937707641196013,
      "tokens_p.mean_in_band": 0.6776315789473685,
      "tokens_rate.above_band": 0.940625,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.059375
    },
    {
      "epoch": 1.9115691489361701,
      "grad_norm": 61.428165543795004,
      "learning_rate": 1.6020133666681183e-07,
      "loss": 0.2526,
      "step": 11500,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6035294117647059,
      "success_rate.epoch.env.math": 0.9822222222222222,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9628140703517588,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070405940891231,
      "success_rate.epoch.global": 0.8635422061108234,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9940567484662577,
      "tokens_p.mean_in_band": 0.5244140625,
      "tokens_rate.above_band": 0.9106145251396648,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0893854748603352
    },
    {
      "epoch": 1.9124002659574468,
      "grad_norm": 105.8776534134594,
      "learning_rate": 1.601975831640025e-07,
      "loss": 0.2597,
      "step": 11505,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5080213903743316,
      "success_rate.epoch.env.logic": 0.6039952996474736,
      "success_rate.epoch.env.math": 0.9822380106571936,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9628364805142627,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070864201327816,
      "success_rate.epoch.global": 0.8636304825980075,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9937770562770563,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9829787234042553,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01702127659574468
    },
    {
      "epoch": 1.9132313829787235,
      "grad_norm": 97.11674789639916,
      "learning_rate": 1.6019386480563167e-07,
      "loss": 0.2166,
      "step": 11510,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5106382978723404,
      "success_rate.epoch.env.logic": 0.6039952996474736,
      "success_rate.epoch.env.math": 0.9822380106571936,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9628812199036918,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6073283880316396,
      "success_rate.epoch.global": 0.8637538779731128,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9968505039193729,
      "tokens_p.mean_in_band": 0.65234375,
      "tokens_rate.above_band": 0.9977653631284916,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0022346368715083797
    },
    {
      "epoch": 1.9140625,
      "grad_norm": 318.8521687174014,
      "learning_rate": 1.6019018159829852e-07,
      "loss": 0.1511,
      "step": 11515,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45555555555555555,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5106382978723404,
      "success_rate.epoch.env.logic": 0.6039952996474736,
      "success_rate.epoch.env.math": 0.9822695035460993,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9629109863672815,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6073339570636845,
      "success_rate.epoch.global": 0.863859467837768,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9959446564885496,
      "tokens_p.mean_in_band": 0.791015625,
      "tokens_rate.above_band": 0.9812734082397003,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018726591760299626
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 161.61199187213788,
      "learning_rate": 1.6018653354853984e-07,
      "loss": 0.2166,
      "step": 11520,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4530386740331492,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5106382978723404,
      "success_rate.epoch.env.logic": 0.6039952996474736,
      "success_rate.epoch.env.math": 0.9822695035460993,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9629258517034068,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071065010467499,
      "success_rate.epoch.global": 0.8637830858618464,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9948937908496732,
      "tokens_p.mean_in_band": 0.6067708333333334,
      "tokens_rate.above_band": 0.9902912621359223,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009708737864077669
    },
    {
      "epoch": 1.9157247340425532,
      "grad_norm": 44.21863604748953,
      "learning_rate": 1.6018292066283007e-07,
      "loss": 0.1606,
      "step": 11525,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.4530386740331492,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5132275132275133,
      "success_rate.epoch.env.logic": 0.6037514654161782,
      "success_rate.epoch.env.math": 0.9822852081488043,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9629481273783297,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6073231702650687,
      "success_rate.epoch.global": 0.8637770897832817,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.999214824120603,
      "tokens_p.mean_in_band": 0.7141927083333334,
      "tokens_rate.above_band": 0.996993987975952,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003006012024048096
    },
    {
      "epoch": 1.9165558510638299,
      "grad_norm": 214.8492666990466,
      "learning_rate": 1.601793429475811e-07,
      "loss": 0.2341,
      "step": 11530,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5132275132275133,
      "success_rate.epoch.env.logic": 0.6037514654161782,
      "success_rate.epoch.env.math": 0.9822852081488043,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.962992598519704,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.60710092005213,
      "success_rate.epoch.global": 0.8637711045237788,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9967296511627907,
      "tokens_p.mean_in_band": 0.40625,
      "tokens_rate.above_band": 0.9971014492753624,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.002898550724637681
    },
    {
      "epoch": 1.9173869680851063,
      "grad_norm": 78.69507554428479,
      "learning_rate": 1.601758004091426e-07,
      "loss": 0.372,
      "step": 11535,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5132275132275133,
      "success_rate.epoch.env.logic": 0.6030444964871194,
      "success_rate.epoch.env.math": 0.982316534040672,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.963014794082367,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070415157362639,
      "success_rate.epoch.global": 0.863747585318738,
      "success_rate.window.env.logic": 0.3333333333333333,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5833333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 1.0003210616438356,
      "tokens_p.mean_in_band": 0.6401486280487805,
      "tokens_rate.above_band": 0.9771332961517011,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02286670384829894
    },
    {
      "epoch": 1.918218085106383,
      "grad_norm": 118.88390277179843,
      "learning_rate": 1.6017229305380167e-07,
      "loss": 0.1534,
      "step": 11540,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5132275132275133,
      "success_rate.epoch.env.logic": 0.6030444964871194,
      "success_rate.epoch.env.math": 0.982316534040672,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9630443467838594,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070442023454905,
      "success_rate.epoch.global": 0.8638177371605097,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.98875,
      "tokens_p.mean_in_band": 0.875,
      "tokens_rate.above_band": 0.9868421052631579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013157894736842105
    },
    {
      "epoch": 1.9190492021276597,
      "grad_norm": 112.21795561066655,
      "learning_rate": 1.6016882088778295e-07,
      "loss": 0.4022,
      "step": 11545,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5132275132275133,
      "success_rate.epoch.env.logic": 0.6035087719298246,
      "success_rate.epoch.env.math": 0.9823321554770318,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9630738522954092,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070905116537282,
      "success_rate.epoch.global": 0.8639228295819936,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9840158045977011,
      "tokens_p.mean_below_band": 2.7153227064344617e-07,
      "tokens_p.mean_in_band": 0.09986111862024222,
      "tokens_rate.above_band": 0.13038591232671412,
      "tokens_rate.below_band": 0.0033720494567253652,
      "tokens_rate.in_band": 0.8662420382165605
    },
    {
      "epoch": 1.9198803191489362,
      "grad_norm": 33.87779541816911,
      "learning_rate": 1.601653839172488e-07,
      "loss": 0.2366,
      "step": 11550,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6039719626168224,
      "success_rate.epoch.env.math": 0.982363315696649,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9630738522954092,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6068898892417806,
      "success_rate.epoch.global": 0.8638642499035866,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.75,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.55,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9947751322751323,
      "tokens_p.mean_in_band": 0.6790140086206896,
      "tokens_rate.above_band": 0.942173479561316,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05782652043868395
    },
    {
      "epoch": 1.9207114361702127,
      "grad_norm": 41.07876936972143,
      "learning_rate": 1.6016198214829891e-07,
      "loss": 0.2828,
      "step": 11555,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6039719626168224,
      "success_rate.epoch.env.math": 0.9823788546255506,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9630885873902634,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6068926414257583,
      "success_rate.epoch.global": 0.8639167309175019,
      "success_rate.window.env.abd": 0.0,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9979110962566845,
      "tokens_p.mean_below_band": 1.0477378964424133e-08,
      "tokens_p.mean_in_band": 0.11905679989270386,
      "tokens_rate.above_band": 0.8887832699619772,
      "tokens_rate.below_band": 0.0004752851711026616,
      "tokens_rate.in_band": 0.11074144486692016
    },
    {
      "epoch": 1.9215425531914894,
      "grad_norm": 105.30704816005407,
      "learning_rate": 1.601586155869706e-07,
      "loss": 0.1402,
      "step": 11560,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6039719626168224,
      "success_rate.epoch.env.math": 0.9823943661971831,
      "success_rate.epoch.env.sat": 0.10625,
      "success_rate.epoch.env.science": 0.9631253737293203,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6068973957812754,
      "success_rate.epoch.global": 0.8640215716486903,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.988233024691358,
      "tokens_p.mean_in_band": 0.7971754807692307,
      "tokens_rate.above_band": 0.9614243323442137,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03857566765578635
    },
    {
      "epoch": 1.922373670212766,
      "grad_norm": 67.44575219000683,
      "learning_rate": 1.6015528423923873e-07,
      "loss": 0.3516,
      "step": 11565,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6039719626168224,
      "success_rate.epoch.env.math": 0.9824098504837291,
      "success_rate.epoch.env.sat": 0.1059190031152648,
      "success_rate.epoch.env.science": 0.9631400677425782,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6068700486371909,
      "success_rate.epoch.global": 0.8639630390143738,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.994304906542056,
      "tokens_p.mean_in_band": 0.5813802083333334,
      "tokens_rate.above_band": 0.9469026548672567,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05309734513274336
    },
    {
      "epoch": 1.9232047872340425,
      "grad_norm": 51.755969445858355,
      "learning_rate": 1.6015198811101555e-07,
      "loss": 0.1707,
      "step": 11570,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.45054945054945056,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6044340723453909,
      "success_rate.epoch.env.math": 0.9824253075571178,
      "success_rate.epoch.env.sat": 0.10559006211180125,
      "success_rate.epoch.env.science": 0.9631620868180008,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6068855618075468,
      "success_rate.epoch.global": 0.8639394716593999,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9981449771689498,
      "tokens_p.mean_in_band": 0.6479166666666667,
      "tokens_rate.above_band": 0.8795180722891566,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.12048192771084337
    },
    {
      "epoch": 1.924035904255319,
      "grad_norm": 128.59260443764907,
      "learning_rate": 1.60148727208151e-07,
      "loss": 0.311,
      "step": 11575,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6044340723453909,
      "success_rate.epoch.env.math": 0.9824253075571178,
      "success_rate.epoch.env.sat": 0.10559006211180125,
      "success_rate.epoch.env.science": 0.9631767515923567,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071598460614751,
      "success_rate.epoch.global": 0.8639917959235995,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9957932692307693,
      "tokens_p.mean_in_band": 0.7942708333333334,
      "tokens_rate.above_band": 0.9928400954653938,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007159904534606206
    },
    {
      "epoch": 1.9248670212765957,
      "grad_norm": 419.99941972326997,
      "learning_rate": 1.6014550153643224e-07,
      "loss": 0.1746,
      "step": 11580,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5105263157894737,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824253075571178,
      "success_rate.epoch.env.sat": 0.10559006211180125,
      "success_rate.epoch.env.science": 0.9632279864838005,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6072482302954744,
      "success_rate.epoch.global": 0.8641485275288092,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9939427312775331,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.9256981382978724,
      "grad_norm": 77.10944733958563,
      "learning_rate": 1.6014231110158418e-07,
      "loss": 0.2642,
      "step": 11585,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5078534031413613,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824253075571178,
      "success_rate.epoch.env.sat": 0.10559006211180125,
      "success_rate.epoch.env.science": 0.9632499006754073,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6070072304357921,
      "success_rate.epoch.global": 0.8640900947018173,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.25,
      "success_rate.window.global": 0.5,
      "tokens_p.mean_above_band": 0.9919735599622285,
      "tokens_p.mean_below_band": 2.0256265997886658e-08,
      "tokens_p.mean_in_band": 0.43050080128205126,
      "tokens_rate.above_band": 0.8125839248033762,
      "tokens_rate.below_band": 0.0003836562440053712,
      "tokens_rate.in_band": 0.18703241895261846
    },
    {
      "epoch": 1.9265292553191489,
      "grad_norm": 31.47118614855034,
      "learning_rate": 1.60139155909269e-07,
      "loss": 0.1358,
      "step": 11590,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5078534031413613,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824253075571178,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9632863663425283,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069808269312518,
      "success_rate.epoch.global": 0.8640664961636829,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9908854166666666,
      "tokens_p.mean_in_band": 0.66357421875,
      "tokens_rate.above_band": 0.9310344827586207,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06896551724137931
    },
    {
      "epoch": 1.9273603723404256,
      "grad_norm": 72.91379036386866,
      "learning_rate": 1.6013603596508636e-07,
      "loss": 0.349,
      "step": 11595,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5078534031413613,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824407374890255,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9633009323546915,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6069835538352583,
      "success_rate.epoch.global": 0.8641186245685798,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9949894514767933,
      "tokens_p.mean_in_band": 0.6583180147058824,
      "tokens_rate.above_band": 0.9330708661417323,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06692913385826772
    },
    {
      "epoch": 1.9281914893617023,
      "grad_norm": 136.0583169871391,
      "learning_rate": 1.6013295127457344e-07,
      "loss": 0.2716,
      "step": 11600,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824407374890255,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9633300297324083,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6072192230082603,
      "success_rate.epoch.global": 0.8642054164537557,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9981896551724138,
      "tokens_p.mean_in_band": 0.7078125,
      "tokens_rate.above_band": 0.9931506849315068,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00684931506849315
    },
    {
      "epoch": 1.9290226063829787,
      "grad_norm": 63.76627651321307,
      "learning_rate": 1.601299018432048e-07,
      "loss": 0.1927,
      "step": 11605,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824407374890255,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.963351822503962,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6072212041693106,
      "success_rate.epoch.global": 0.8642574383859022,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953022875816994,
      "tokens_p.mean_in_band": 0.556640625,
      "tokens_rate.above_band": 0.9849785407725322,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015021459227467811
    },
    {
      "epoch": 1.9298537234042552,
      "grad_norm": 100.80777613347965,
      "learning_rate": 1.6012688767639244e-07,
      "loss": 0.2938,
      "step": 11610,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824561403508771,
      "success_rate.epoch.env.sat": 0.10526315789473684,
      "success_rate.epoch.env.science": 0.9633735893882399,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6072245832371406,
      "success_rate.epoch.global": 0.8643267389917039,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.995136186770428,
      "tokens_p.mean_in_band": 0.6026041666666667,
      "tokens_rate.above_band": 0.8509933774834437,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.1490066225165563
    },
    {
      "epoch": 1.930684840425532,
      "grad_norm": 78.38160099594734,
      "learning_rate": 1.6012390877948577e-07,
      "loss": 0.302,
      "step": 11615,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6053550640279395,
      "success_rate.epoch.env.math": 0.9824561403508771,
      "success_rate.epoch.env.sat": 0.10493827160493827,
      "success_rate.epoch.env.science": 0.9633953304313415,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071970245783499,
      "success_rate.epoch.global": 0.8642684015818344,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99231843575419,
      "tokens_p.mean_in_band": 0.54052734375,
      "tokens_rate.above_band": 0.9179487179487179,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08205128205128205
    },
    {
      "epoch": 1.9315159574468086,
      "grad_norm": 36.60540569956556,
      "learning_rate": 1.6012096515777157e-07,
      "loss": 0.2433,
      "step": 11620,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6046511627906976,
      "success_rate.epoch.env.math": 0.9824868651488616,
      "success_rate.epoch.env.sat": 0.10493827160493827,
      "success_rate.epoch.env.science": 0.9634098101265823,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071371430561666,
      "success_rate.epoch.global": 0.8642274349821519,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9979596219931272,
      "tokens_p.mean_in_band": 0.5388849431818182,
      "tokens_rate.above_band": 0.9635761589403974,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03642384105960265
    },
    {
      "epoch": 1.932347074468085,
      "grad_norm": 50.23443645240581,
      "learning_rate": 1.601180568164741e-07,
      "loss": 0.2077,
      "step": 11625,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6046511627906976,
      "success_rate.epoch.env.math": 0.9824868651488616,
      "success_rate.epoch.env.sat": 0.10493827160493827,
      "success_rate.epoch.env.science": 0.9634387351778656,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071397726062832,
      "success_rate.epoch.global": 0.8642966360856269,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9883928571428572,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.9331781914893615,
      "grad_norm": 72.71656781770703,
      "learning_rate": 1.6011518376075492e-07,
      "loss": 0.2095,
      "step": 11630,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5104166666666666,
      "success_rate.epoch.env.logic": 0.6046511627906976,
      "success_rate.epoch.env.math": 0.9824868651488616,
      "success_rate.epoch.env.sat": 0.10493827160493827,
      "success_rate.epoch.env.science": 0.9634748272458046,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6071430537033686,
      "success_rate.epoch.global": 0.8643830383293009,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.99609375,
      "tokens_p.mean_in_band": 0.5020833333333333,
      "tokens_rate.above_band": 0.9180327868852459,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.08196721311475409
    },
    {
      "epoch": 1.9340093085106385,
      "grad_norm": 150.023843346747,
      "learning_rate": 1.60112345995713e-07,
      "loss": 0.3234,
      "step": 11635,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5129533678756477,
      "success_rate.epoch.env.logic": 0.6046511627906976,
      "success_rate.epoch.env.math": 0.9825021872265967,
      "success_rate.epoch.env.sat": 0.10493827160493827,
      "success_rate.epoch.env.science": 0.9634964483030781,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.607377021371004,
      "success_rate.epoch.global": 0.864469330618478,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9958433014354067,
      "tokens_p.mean_in_band": 0.6865530303030303,
      "tokens_rate.above_band": 0.9693877551020408,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030612244897959183
    },
    {
      "epoch": 1.934840425531915,
      "grad_norm": 43.87504898626464,
      "learning_rate": 1.6010954352638469e-07,
      "loss": 0.2944,
      "step": 11640,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5129533678756477,
      "success_rate.epoch.env.logic": 0.6046511627906976,
      "success_rate.epoch.env.math": 0.9825174825174825,
      "success_rate.epoch.env.sat": 0.10461538461538461,
      "success_rate.epoch.env.science": 0.9635108481262328,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6073503675641393,
      "success_rate.epoch.global": 0.8644110913253625,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9957275390625,
      "tokens_p.mean_in_band": 0.6526041666666667,
      "tokens_rate.above_band": 0.8504983388704319,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.14950166112956811
    },
    {
      "epoch": 1.9356715425531914,
      "grad_norm": 39.30108798018139,
      "learning_rate": 1.6010677635774368e-07,
      "loss": 0.3328,
      "step": 11645,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5129533678756477,
      "success_rate.epoch.env.logic": 0.6051103368176539,
      "success_rate.epoch.env.math": 0.982532751091703,
      "success_rate.epoch.env.sat": 0.10461538461538461,
      "success_rate.epoch.env.science": 0.9635252365930599,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6073948067521395,
      "success_rate.epoch.global": 0.8644800406814137,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9943379790940766,
      "tokens_p.mean_in_band": 0.69873046875,
      "tokens_rate.above_band": 0.9728813559322034,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02711864406779661
    },
    {
      "epoch": 1.936502659574468,
      "grad_norm": 131.2609116536188,
      "learning_rate": 1.60104044494701e-07,
      "loss": 0.2113,
      "step": 11650,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5129533678756477,
      "success_rate.epoch.env.logic": 0.6060254924681344,
      "success_rate.epoch.env.math": 0.982532751091703,
      "success_rate.epoch.env.sat": 0.10429447852760736,
      "success_rate.epoch.env.science": 0.9635539795114263,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6074514424322368,
      "success_rate.epoch.global": 0.8644735170837038,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9931837248322147,
      "tokens_p.mean_in_band": 0.48583984375,
      "tokens_rate.above_band": 0.9490445859872612,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050955414012738856
    },
    {
      "epoch": 1.9373337765957448,
      "grad_norm": 44.578036732586504,
      "learning_rate": 1.6010134794210506e-07,
      "loss": 0.3518,
      "step": 11655,
      "success_rate.epoch.env.abd": 0.6041666666666666,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5129533678756477,
      "success_rate.epoch.env.logic": 0.6060254924681344,
      "success_rate.epoch.env.math": 0.982532751091703,
      "success_rate.epoch.env.sat": 0.10429447852760736,
      "success_rate.epoch.env.science": 0.9635755069895648,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6074533994757039,
      "success_rate.epoch.global": 0.8645251396648045,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 0.8571428571428571,
      "success_rate.window.env_macro_mean": 0.4642857142857143,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9953880407124682,
      "tokens_p.mean_in_band": 0.67171875,
      "tokens_rate.above_band": 0.9401913875598086,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05980861244019139
    },
    {
      "epoch": 1.9381648936170213,
      "grad_norm": 29.562613054775344,
      "learning_rate": 1.6009868670474159e-07,
      "loss": 0.2624,
      "step": 11660,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5129533678756477,
      "success_rate.epoch.env.logic": 0.6060254924681344,
      "success_rate.epoch.env.math": 0.982532751091703,
      "success_rate.epoch.env.sat": 0.10397553516819572,
      "success_rate.epoch.env.science": 0.9636113296616837,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6081620458943606,
      "success_rate.epoch.global": 0.864518584295319,
      "success_rate.window.env.abd": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.985440797940798,
      "tokens_p.mean_in_band": 0.6666165865384616,
      "tokens_rate.above_band": 0.9372738238841978,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06272617611580217
    },
    {
      "epoch": 1.9389960106382977,
      "grad_norm": 18.754887507071533,
      "learning_rate": 1.600960607873336e-07,
      "loss": 0.3717,
      "step": 11665,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6064814814814815,
      "success_rate.epoch.env.math": 0.982532751091703,
      "success_rate.epoch.env.sat": 0.10397553516819572,
      "success_rate.epoch.env.science": 0.9636399371069182,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079657283428561,
      "success_rate.epoch.global": 0.8644948662694891,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9929395151800423,
      "tokens_p.mean_below_band": 1.8533319234848022e-07,
      "tokens_p.mean_in_band": 0.5500758725341427,
      "tokens_rate.above_band": 0.8655530657975148,
      "tokens_rate.below_band": 0.00020370747606437156,
      "tokens_rate.in_band": 0.13424322672642086
    },
    {
      "epoch": 1.9398271276595744,
      "grad_norm": 205.29775223353275,
      "learning_rate": 1.6009347019454146e-07,
      "loss": 0.2074,
      "step": 11670,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6064814814814815,
      "success_rate.epoch.env.math": 0.982532751091703,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.963668499607227,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079395068808087,
      "success_rate.epoch.global": 0.8644540157081327,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9897388059701493,
      "tokens_p.mean_in_band": 0.7215909090909091,
      "tokens_rate.above_band": 0.9481132075471698,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05188679245283019
    },
    {
      "epoch": 1.9406582446808511,
      "grad_norm": 101.35100395200453,
      "learning_rate": 1.6009091493096285e-07,
      "loss": 0.3524,
      "step": 11675,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6064814814814815,
      "success_rate.epoch.env.math": 0.9825479930191972,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.963682764036121,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.607942189276844,
      "success_rate.epoch.global": 0.8645055084209193,
      "success_rate.window.env.agentgym:textcraft": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9959211847389559,
      "tokens_p.mean_in_band": 0.657608695652174,
      "tokens_rate.above_band": 0.9352112676056338,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0647887323943662
    },
    {
      "epoch": 1.9414893617021276,
      "grad_norm": 589.0290952972535,
      "learning_rate": 1.6008839500113275e-07,
      "loss": 0.304,
      "step": 11680,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6064814814814815,
      "success_rate.epoch.env.math": 0.9825479930191972,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.9636970172684458,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079434850252372,
      "success_rate.epoch.global": 0.8645398151664768,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9952554744525547,
      "tokens_p.mean_in_band": 0.82763671875,
      "tokens_rate.above_band": 0.9884559884559885,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011544011544011544
    },
    {
      "epoch": 1.9423204787234043,
      "grad_norm": 34.78099548310638,
      "learning_rate": 1.600859104095234e-07,
      "loss": 0.137,
      "step": 11685,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6069364161849711,
      "success_rate.epoch.env.math": 0.9825632083696599,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.9637183761521867,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079881676559366,
      "success_rate.epoch.global": 0.8646255060728745,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9943181818181818,
      "tokens_p.mean_below_band": 1.3445969671010971e-08,
      "tokens_p.mean_in_band": 0.814453125,
      "tokens_rate.above_band": 0.98828125,
      "tokens_rate.below_band": 0.00390625,
      "tokens_rate.in_band": 0.0078125
    },
    {
      "epoch": 1.943151595744681,
      "grad_norm": 40.322712040613666,
      "learning_rate": 1.6008346116054432e-07,
      "loss": 0.2363,
      "step": 11690,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6069364161849711,
      "success_rate.epoch.env.math": 0.9817391304347826,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.9637397099176793,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079151909132652,
      "success_rate.epoch.global": 0.8646017699115044,
      "success_rate.window.env.math": 0.6666666666666666,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9856459330143541,
      "tokens_p.mean_below_band": 2.066371962428093e-09,
      "tokens_p.mean_in_band": 0.7113095238095238,
      "tokens_rate.above_band": 0.9047619047619048,
      "tokens_rate.below_band": 0.004329004329004329,
      "tokens_rate.in_band": 0.09090909090909091
    },
    {
      "epoch": 1.9439827127659575,
      "grad_norm": 37.90494366317641,
      "learning_rate": 1.6008104725854236e-07,
      "loss": 0.172,
      "step": 11695,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6069364161849711,
      "success_rate.epoch.env.math": 0.9817549956559514,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.9637610186092067,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079185703598738,
      "success_rate.epoch.global": 0.8646702047005307,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959761705685619,
      "tokens_p.mean_in_band": 0.6684782608695652,
      "tokens_rate.above_band": 0.9811320754716981,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.018867924528301886
    },
    {
      "epoch": 1.944813829787234,
      "grad_norm": 1320.1959759929207,
      "learning_rate": 1.600786687078016e-07,
      "loss": 0.275,
      "step": 11700,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9817549956559514,
      "success_rate.epoch.env.sat": 0.10365853658536585,
      "success_rate.epoch.env.science": 0.9637823022709475,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079617674242118,
      "success_rate.epoch.global": 0.864738570346047,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9984772978959026,
      "tokens_p.mean_in_band": 0.6607142857142857,
      "tokens_rate.above_band": 0.9699248120300752,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03007518796992481
    },
    {
      "epoch": 1.9456449468085106,
      "grad_norm": 110.81681174003866,
      "learning_rate": 1.6007632551254337e-07,
      "loss": 0.3102,
      "step": 11705,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.453551912568306,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9817549956559514,
      "success_rate.epoch.env.sat": 0.1033434650455927,
      "success_rate.epoch.env.science": 0.9638177195384314,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079363443085491,
      "success_rate.epoch.global": 0.8647147905098436,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9974137931034482,
      "tokens_p.mean_in_band": 0.6421440972222222,
      "tokens_rate.above_band": 0.9602649006622517,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.039735099337748346
    },
    {
      "epoch": 1.9464760638297873,
      "grad_norm": 145.76844776322204,
      "learning_rate": 1.6007401767692628e-07,
      "loss": 0.2198,
      "step": 11710,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9817708333333334,
      "success_rate.epoch.env.sat": 0.1033434650455927,
      "success_rate.epoch.env.science": 0.9638318670576735,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6077149833221908,
      "success_rate.epoch.global": 0.864656912209889,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937900641025641,
      "tokens_p.mean_in_band": 0.46875,
      "tokens_rate.above_band": 0.9968051118210862,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003194888178913738
    },
    {
      "epoch": 1.9473071808510638,
      "grad_norm": 109.81470120783514,
      "learning_rate": 1.6007174520504617e-07,
      "loss": 0.2408,
      "step": 11715,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5103092783505154,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9817708333333334,
      "success_rate.epoch.env.sat": 0.1033434650455927,
      "success_rate.epoch.env.science": 0.9638389366692729,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6077156260141543,
      "success_rate.epoch.global": 0.8646739815865809,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9896472392638037,
      "tokens_p.mean_in_band": 0.80859375,
      "tokens_rate.above_band": 0.9969418960244648,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0030581039755351682
    },
    {
      "epoch": 1.9481382978723403,
      "grad_norm": 47.76625958989531,
      "learning_rate": 1.6006950810093612e-07,
      "loss": 0.3269,
      "step": 11720,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.5263157894736842,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9817708333333334,
      "success_rate.epoch.env.sat": 0.10303030303030303,
      "success_rate.epoch.env.science": 0.9638742433118531,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6079186604775442,
      "success_rate.epoch.global": 0.8646673387096774,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9905660377358491,
      "tokens_p.mean_in_band": 0.685546875,
      "tokens_rate.above_band": 0.9675456389452333,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.032454361054766734
    },
    {
      "epoch": 1.948969414893617,
      "grad_norm": 146.06397793830362,
      "learning_rate": 1.6006730636856645e-07,
      "loss": 0.1794,
      "step": 11725,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5128205128205128,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9818024263431543,
      "success_rate.epoch.env.sat": 0.10303030303030303,
      "success_rate.epoch.env.science": 0.9639024390243902,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6100772058637872,
      "success_rate.epoch.global": 0.864786604557472,
      "success_rate.window.env.agentgym:sciworld": 1.0,
      "success_rate.window.env.agentgym:textcraft": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9962732160312805,
      "tokens_p.mean_in_band": 0.69140625,
      "tokens_rate.above_band": 0.9980487804878049,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.001951219512195122
    },
    {
      "epoch": 1.9498005319148937,
      "grad_norm": 49.50932154641662,
      "learning_rate": 1.6006514001184467e-07,
      "loss": 0.2456,
      "step": 11730,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9818024263431543,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9639376218323586,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.61027807155822,
      "success_rate.epoch.global": 0.8647798742138365,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9963461538461539,
      "tokens_p.mean_in_band": 0.6413845486111112,
      "tokens_rate.above_band": 0.9730538922155688,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02694610778443114
    },
    {
      "epoch": 1.9506316489361701,
      "grad_norm": 43.47013685341931,
      "learning_rate": 1.6006300903461556e-07,
      "loss": 0.1934,
      "step": 11735,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9818024263431543,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9639657187378262,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6102806258223533,
      "success_rate.epoch.global": 0.8648478752828765,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0004615952732645,
      "tokens_p.mean_in_band": 0.6046875,
      "tokens_rate.above_band": 0.9442119944211994,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05578800557880056
    },
    {
      "epoch": 1.9514627659574468,
      "grad_norm": 113.79882856081655,
      "learning_rate": 1.6006091344066105e-07,
      "loss": 0.3311,
      "step": 11740,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9818181818181818,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9639867627019661,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.610283971225914,
      "success_rate.epoch.global": 0.8649158079919578,
      "success_rate.window.env.agentgym:alfworld": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333334,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9964759535655058,
      "tokens_p.mean_in_band": 0.5126953125,
      "tokens_rate.above_band": 0.996694214876033,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003305785123966942
    },
    {
      "epoch": 1.9522938829787235,
      "grad_norm": 245.4709719178445,
      "learning_rate": 1.6005885323370037e-07,
      "loss": 0.2172,
      "step": 11745,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6073903002309469,
      "success_rate.epoch.env.math": 0.9818339100346021,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9640077821011673,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6102873119182433,
      "success_rate.epoch.global": 0.8649836724441096,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9847808441558441,
      "tokens_p.mean_in_band": 0.8671875,
      "tokens_rate.above_band": 0.9746835443037974,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02531645569620253
    },
    {
      "epoch": 1.953125,
      "grad_norm": 64.98334378571631,
      "learning_rate": 1.600568284173898e-07,
      "loss": 0.2389,
      "step": 11750,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6078431372549019,
      "success_rate.epoch.env.math": 0.9818496110630942,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9640287769784173,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6103318149118521,
      "success_rate.epoch.global": 0.8650684071796159,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9915966386554622,
      "tokens_p.mean_in_band": 0.88671875,
      "tokens_rate.above_band": 0.9916666666666667,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.008333333333333333
    },
    {
      "epoch": 1.9539561170212765,
      "grad_norm": 7.218737346416608,
      "learning_rate": 1.6005483899532296e-07,
      "loss": 0.2972,
      "step": 11755,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45108695652173914,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6071428571428571,
      "success_rate.epoch.env.math": 0.9818496110630942,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9640427599611273,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6102694242637308,
      "success_rate.epoch.global": 0.8649937264742785,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9965909090909091,
      "tokens_p.mean_in_band": 0.6580882352941176,
      "tokens_rate.above_band": 0.9748892171344166,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025110782865583457
    },
    {
      "epoch": 1.9547872340425532,
      "grad_norm": 161.62315135336982,
      "learning_rate": 1.6005288497103056e-07,
      "loss": 0.2477,
      "step": 11760,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5153061224489796,
      "success_rate.epoch.env.logic": 0.6075949367088608,
      "success_rate.epoch.env.math": 0.9818809318377912,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.964063714063714,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6100936103155669,
      "success_rate.epoch.global": 0.8649868371568259,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.000062625250501,
      "tokens_p.mean_in_band": 0.7887834821428571,
      "tokens_rate.above_band": 0.9930348258706467,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006965174129353234
    },
    {
      "epoch": 1.9556183510638299,
      "grad_norm": 103.27120675218588,
      "learning_rate": 1.600509663479805e-07,
      "loss": 0.3003,
      "step": 11765,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6080459770114942,
      "success_rate.epoch.env.math": 0.9818965517241379,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.964063714063714,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6103597044248331,
      "success_rate.epoch.global": 0.8650375939849624,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.9,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9959896347482725,
      "tokens_p.mean_in_band": 0.62890625,
      "tokens_rate.above_band": 0.9921645445641528,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.007835455435847209
    },
    {
      "epoch": 1.9564494680851063,
      "grad_norm": 12.478963346983374,
      "learning_rate": 1.6004908312957787e-07,
      "loss": 0.0726,
      "step": 11770,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6080459770114942,
      "success_rate.epoch.env.math": 0.9819121447028424,
      "success_rate.epoch.env.sat": 0.1027190332326284,
      "success_rate.epoch.env.science": 0.9640846437584935,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6103630246678772,
      "success_rate.epoch.global": 0.8651052104208417,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9879629629629629,
      "tokens_p.mean_in_band": 0.8515625,
      "tokens_rate.above_band": 0.9854014598540146,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014598540145985401
    },
    {
      "epoch": 1.957280585106383,
      "grad_norm": 2.6370722818089543,
      "learning_rate": 1.6004723531916496e-07,
      "loss": 0.2143,
      "step": 11775,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6080459770114942,
      "success_rate.epoch.env.math": 0.9819121447028424,
      "success_rate.epoch.env.sat": 0.10240963855421686,
      "success_rate.epoch.env.science": 0.9640985833495052,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6103361651144771,
      "success_rate.epoch.global": 0.8650306748466258,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9977235099337748,
      "tokens_p.mean_in_band": 0.5949519230769231,
      "tokens_rate.above_band": 0.9508816120906801,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0491183879093199
    },
    {
      "epoch": 1.9581117021276597,
      "grad_norm": 114.88816234701625,
      "learning_rate": 1.600454229200211e-07,
      "loss": 0.3689,
      "step": 11780,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6080459770114942,
      "success_rate.epoch.env.math": 0.9819277108433735,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641125121241513,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6103108886111192,
      "success_rate.epoch.global": 0.864973094731573,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9991858717434869,
      "tokens_p.mean_in_band": 0.6026335685483871,
      "tokens_rate.above_band": 0.9698736637512148,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.03012633624878523
    },
    {
      "epoch": 1.9589428191489362,
      "grad_norm": 31.75549408991279,
      "learning_rate": 1.6004364593536298e-07,
      "loss": 0.2189,
      "step": 11785,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6084959816303099,
      "success_rate.epoch.env.math": 0.9819277108433735,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641333850329585,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6103536956590849,
      "success_rate.epoch.global": 0.865040650406504,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 1.00037147102526,
      "tokens_p.mean_in_band": 0.751171875,
      "tokens_rate.above_band": 0.9853587115666179,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014641288433382138
    },
    {
      "epoch": 1.9597739361702127,
      "grad_norm": 105.39213209811822,
      "learning_rate": 1.6004190436834418e-07,
      "loss": 0.1621,
      "step": 11790,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6093928980526919,
      "success_rate.epoch.env.math": 0.9819277108433735,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641611778380472,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104377601343095,
      "success_rate.epoch.global": 0.8651418572678415,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.997300392670157,
      "tokens_p.mean_in_band": 0.84296875,
      "tokens_rate.above_band": 0.9934980494148244,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006501950585175552
    },
    {
      "epoch": 1.9606050531914894,
      "grad_norm": 63.19142893154268,
      "learning_rate": 1.6004019822205567e-07,
      "loss": 0.3089,
      "step": 11795,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6093928980526919,
      "success_rate.epoch.env.math": 0.9819277108433735,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641819941916747,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104396525300939,
      "success_rate.epoch.global": 0.8651924037981009,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9905,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.961436170212766,
      "grad_norm": 37.94166674320429,
      "learning_rate": 1.6003852749952535e-07,
      "loss": 0.4199,
      "step": 11800,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6093928980526919,
      "success_rate.epoch.env.math": 0.9819587628865979,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.964202786377709,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104443656418447,
      "success_rate.epoch.global": 0.8652765638656511,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9946808510638298,
      "tokens_p.mean_in_band": 0.7001953125,
      "tokens_rate.above_band": 0.9362549800796812,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06374501992031872
    },
    {
      "epoch": 1.9622672872340425,
      "grad_norm": 106.78956689707896,
      "learning_rate": 1.6003689220371838e-07,
      "loss": 0.2297,
      "step": 11805,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6093928980526919,
      "success_rate.epoch.env.math": 0.9819897084048027,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.964230471771075,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104496957247147,
      "success_rate.epoch.global": 0.8653774173424829,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937185929648241,
      "tokens_p.mean_in_band": 0.6875,
      "tokens_rate.above_band": 0.9342723004694836,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06572769953051644
    },
    {
      "epoch": 1.963098404255319,
      "grad_norm": 31.97744419065312,
      "learning_rate": 1.60035292337537e-07,
      "loss": 0.1721,
      "step": 11810,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6098398169336384,
      "success_rate.epoch.env.math": 0.9820205479452054,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9642512077294686,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104950133956004,
      "success_rate.epoch.global": 0.8654781199351702,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9931848404255319,
      "tokens_p.mean_in_band": 0.6116071428571429,
      "tokens_rate.above_band": 0.9306930693069307,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.06930693069306931
    },
    {
      "epoch": 1.9639295212765957,
      "grad_norm": 98.05815317194478,
      "learning_rate": 1.600337279038206e-07,
      "loss": 0.2481,
      "step": 11815,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6091428571428571,
      "success_rate.epoch.env.math": 0.9820205479452054,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.964278818304692,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104341634669134,
      "success_rate.epoch.global": 0.8654373286817842,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9944769637462235,
      "tokens_p.mean_in_band": 0.5785845588235294,
      "tokens_rate.above_band": 0.9749631811487481,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.025036818851251842
    },
    {
      "epoch": 1.9647606382978724,
      "grad_norm": 208.6761857898844,
      "learning_rate": 1.6003219890534568e-07,
      "loss": 0.2379,
      "step": 11820,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6095890410958904,
      "success_rate.epoch.env.math": 0.9820359281437125,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9642926076047095,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.610477377417055,
      "success_rate.epoch.global": 0.8655043586550436,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 0.9898196920583469,
      "tokens_p.mean_in_band": 0.6818773674242424,
      "tokens_rate.above_band": 0.9033674963396779,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09663250366032211
    },
    {
      "epoch": 1.9655917553191489,
      "grad_norm": 33.96308190594352,
      "learning_rate": 1.600307053448258e-07,
      "loss": 0.223,
      "step": 11825,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6104783599088838,
      "success_rate.epoch.env.math": 0.982051282051282,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9643063862627822,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.610560872996931,
      "success_rate.epoch.global": 0.865588052271313,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9976892605633803,
      "tokens_p.mean_in_band": 0.74609375,
      "tokens_rate.above_band": 0.993006993006993,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006993006993006993
    },
    {
      "epoch": 1.9664228723404256,
      "grad_norm": 30.886291072415105,
      "learning_rate": 1.6002924722491166e-07,
      "loss": 0.2455,
      "step": 11830,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6109215017064846,
      "success_rate.epoch.env.math": 0.982066609735269,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9643270343231778,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6106044291371112,
      "success_rate.epoch.global": 0.8656716417910447,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.875,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9948501872659176,
      "tokens_p.mean_in_band": 0.7961805555555556,
      "tokens_rate.above_band": 0.9595687331536388,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04043126684636118
    },
    {
      "epoch": 1.9672539893617023,
      "grad_norm": 24.43642020438126,
      "learning_rate": 1.6002782454819107e-07,
      "loss": 0.1401,
      "step": 11835,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6109215017064846,
      "success_rate.epoch.env.math": 0.982066609735269,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9643751203543232,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6106088005944881,
      "success_rate.epoch.global": 0.8657884926059402,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9953125,
      "tokens_p.mean_in_band": 0.5866268382352942,
      "tokens_rate.above_band": 0.89171974522293,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.10828025477707007
    },
    {
      "epoch": 1.9680851063829787,
      "grad_norm": 44.48580741880131,
      "learning_rate": 1.6002643731718896e-07,
      "loss": 0.1751,
      "step": 11840,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6111111111111112,
      "success_rate.epoch.env.math": 0.9820971867007673,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9643751203543232,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6106288175372266,
      "success_rate.epoch.global": 0.8657643114367316,
      "success_rate.window.env.babyai": 1.0,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.7777777777777777,
      "success_rate.window.global": 0.8,
      "tokens_p.mean_above_band": 1.0000259929299231,
      "tokens_p.mean_in_band": 0.6502403846153846,
      "tokens_rate.above_band": 0.994622543950362,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.005377456049638056
    },
    {
      "epoch": 1.9689162234042552,
      "grad_norm": 902.3799061009368,
      "learning_rate": 1.6002508553436733e-07,
      "loss": 0.2256,
      "step": 11845,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6108597285067874,
      "success_rate.epoch.env.math": 0.9820971867007673,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.964017702520685,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6105734720428665,
      "success_rate.epoch.global": 0.8654919965256235,
      "success_rate.window.env.logic": 0.5,
      "success_rate.window.env.science": 0.75,
      "success_rate.window.env_macro_mean": 0.625,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9941605839416059,
      "tokens_p.mean_below_band": 1.0870182531874661e-10,
      "tokens_p.mean_in_band": 0.4701450892857143,
      "tokens_rate.above_band": 0.9771754636233951,
      "tokens_rate.below_band": 0.0028530670470756064,
      "tokens_rate.in_band": 0.019971469329529243
    },
    {
      "epoch": 1.969747340425532,
      "grad_norm": 38.5737958106681,
      "learning_rate": 1.6002376920212524e-07,
      "loss": 0.2954,
      "step": 11850,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6101694915254238,
      "success_rate.epoch.env.math": 0.9821124361158433,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9640315445277938,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6105133679011231,
      "success_rate.epoch.global": 0.8654347017239241,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.5,
      "success_rate.window.global": 0.7,
      "tokens_p.mean_above_band": 0.9974804941482445,
      "tokens_p.mean_in_band": 0.6920731707317073,
      "tokens_rate.above_band": 0.9493827160493827,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.050617283950617285
    },
    {
      "epoch": 1.9705784574468086,
      "grad_norm": 45.23147280803937,
      "learning_rate": 1.6002248832279885e-07,
      "loss": 0.3795,
      "step": 11855,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6094808126410836,
      "success_rate.epoch.env.math": 0.9821124361158433,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9640453758892521,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104520181263156,
      "success_rate.epoch.global": 0.8653607736176544,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.3333333333333333,
      "success_rate.window.global": 0.6,
      "tokens_p.mean_above_band": 0.9998293515358362,
      "tokens_p.mean_in_band": 0.564520474137931,
      "tokens_rate.above_band": 0.9805890227576974,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019410977242302542
    },
    {
      "epoch": 1.971409574468085,
      "grad_norm": 218.1468518277248,
      "learning_rate": 1.600212428986614e-07,
      "loss": 0.2677,
      "step": 11860,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6094808126410836,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9640591966173362,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104560401040517,
      "success_rate.epoch.global": 0.8654275092936803,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9939903846153846,
      "tokens_p.mean_in_band": 0.65732421875,
      "tokens_rate.above_band": 0.9212598425196851,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.07874015748031496
    },
    {
      "epoch": 1.9722406914893615,
      "grad_norm": 180.57155675960868,
      "learning_rate": 1.600200329319233e-07,
      "loss": 0.2924,
      "step": 11865,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6099210822998873,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.964086806222393,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6104985745825845,
      "success_rate.epoch.global": 0.8655108359133127,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9937267657992565,
      "tokens_p.mean_in_band": 0.5,
      "tokens_rate.above_band": 0.9438596491228071,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.056140350877192984
    },
    {
      "epoch": 1.9730718085106385,
      "grad_norm": 49.95463616318855,
      "learning_rate": 1.600188584247318e-07,
      "loss": 0.1861,
      "step": 11870,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6103603603603603,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641143734407983,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6105410150624825,
      "success_rate.epoch.global": 0.8655940594059406,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9973387096774193,
      "tokens_p.mean_in_band": 0.8828125,
      "tokens_rate.above_band": 0.9987113402061856,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.001288659793814433
    },
    {
      "epoch": 1.973902925531915,
      "grad_norm": 41.06240945683496,
      "learning_rate": 1.6001771937917145e-07,
      "loss": 0.3976,
      "step": 11875,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6103603603603603,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641418983700862,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6105435173287815,
      "success_rate.epoch.global": 0.8656605640771895,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.99125,
      "tokens_p.mean_in_band": 0.76953125,
      "tokens_rate.above_band": 0.9868421052631579,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.013157894736842105
    },
    {
      "epoch": 1.9747340425531914,
      "grad_norm": 44.796388427524,
      "learning_rate": 1.6001661579726378e-07,
      "loss": 0.1294,
      "step": 11880,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4486486486486487,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6103603603603603,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.1021021021021021,
      "success_rate.epoch.env.science": 0.9641556450067088,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6105447670230199,
      "success_rate.epoch.global": 0.8656937917388078,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8333333333333333,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954879679144385,
      "tokens_p.mean_in_band": 0.61015625,
      "tokens_rate.above_band": 0.9739583333333334,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.026041666666666668
    },
    {
      "epoch": 1.975565159574468,
      "grad_norm": 259.56449823520194,
      "learning_rate": 1.6001554768096737e-07,
      "loss": 0.1811,
      "step": 11885,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6103603603603603,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.9641693811074918,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6107877030013351,
      "success_rate.epoch.global": 0.8656365883807169,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.998688352570829,
      "tokens_p.mean_in_band": 0.6942085597826086,
      "tokens_rate.above_band": 0.9764344262295082,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0235655737704918
    },
    {
      "epoch": 1.9763962765957448,
      "grad_norm": 2.042692115642958,
      "learning_rate": 1.6001451503217784e-07,
      "loss": 0.1616,
      "step": 11890,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6103603603603603,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.9642105263157895,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6107914434748167,
      "success_rate.epoch.global": 0.8657361660079052,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9888888888888889,
      "tokens_p.mean_in_band": 0.8125,
      "tokens_rate.above_band": 0.9782608695652174,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.021739130434782608
    },
    {
      "epoch": 1.9772273936170213,
      "grad_norm": 48.656632719206854,
      "learning_rate": 1.600135178527279e-07,
      "loss": 0.2001,
      "step": 11895,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6103603603603603,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.9642379039969401,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6107939323549213,
      "success_rate.epoch.global": 0.8658024691358025,
      "success_rate.window.env.ded": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963219501718213,
      "tokens_p.mean_in_band": 0.5242147125322998,
      "tokens_rate.above_band": 0.9002320185614849,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.09976798143851508
    },
    {
      "epoch": 1.9780585106382977,
      "grad_norm": 264.6661843641287,
      "learning_rate": 1.6001255614438732e-07,
      "loss": 0.4194,
      "step": 11900,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6107986501687289,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.9642515771363028,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6108350198956242,
      "success_rate.epoch.global": 0.8658521535233864,
      "success_rate.window.env.logic": 0.6666666666666666,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8888888888888888,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9988215214564369,
      "tokens_p.mean_in_band": 0.6479166666666667,
      "tokens_rate.above_band": 0.9808673469387755,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01913265306122449
    },
    {
      "epoch": 1.9788896276595744,
      "grad_norm": 49.17219293096067,
      "learning_rate": 1.600116299088629e-07,
      "loss": 0.1593,
      "step": 11905,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6112359550561798,
      "success_rate.epoch.env.math": 0.9821428571428571,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.9642857142857143,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6108778782626116,
      "success_rate.epoch.global": 0.8659514120113454,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9980006954102921,
      "tokens_p.mean_in_band": 0.688125,
      "tokens_rate.above_band": 0.9663978494623656,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.033602150537634407
    },
    {
      "epoch": 1.9797207446808511,
      "grad_norm": 71.9051328825867,
      "learning_rate": 1.6001073914779846e-07,
      "loss": 0.2129,
      "step": 11910,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6112359550561798,
      "success_rate.epoch.env.math": 0.9821731748726655,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.964299350897289,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6108818741118283,
      "success_rate.epoch.global": 0.8660175027733268,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9926330798479087,
      "tokens_p.mean_in_band": 0.8515625,
      "tokens_rate.above_band": 0.9962121212121212,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003787878787878788
    },
    {
      "epoch": 1.9805518617021276,
      "grad_norm": 38.53772234575872,
      "learning_rate": 1.6000988386277486e-07,
      "loss": 0.1646,
      "step": 11915,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.611672278338945,
      "success_rate.epoch.env.math": 0.9821882951653944,
      "success_rate.epoch.env.sat": 0.10179640718562874,
      "success_rate.epoch.env.science": 0.9643129770992367,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6109241531825048,
      "success_rate.epoch.global": 0.866083528397191,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9920520231213873,
      "tokens_p.mean_in_band": 0.888671875,
      "tokens_rate.above_band": 0.9885714285714285,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011428571428571429
    },
    {
      "epoch": 1.9813829787234043,
      "grad_norm": 52.66855415226529,
      "learning_rate": 1.6000906405531004e-07,
      "loss": 0.1282,
      "step": 11920,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.611672278338945,
      "success_rate.epoch.env.math": 0.9822033898305085,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.964333396910166,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6111711276580242,
      "success_rate.epoch.global": 0.8661659689731593,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9942715458276333,
      "tokens_p.mean_in_band": 0.80126953125,
      "tokens_rate.above_band": 0.9891745602165088,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.010825439783491205
    },
    {
      "epoch": 1.982214095744681,
      "grad_norm": 381.1455252332628,
      "learning_rate": 1.60008279726859e-07,
      "loss": 0.3417,
      "step": 11925,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.611672278338945,
      "success_rate.epoch.env.math": 0.9822033898305085,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9643605870020965,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6111735994845634,
      "success_rate.epoch.global": 0.8662318483878907,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9961721224920802,
      "tokens_p.mean_in_band": 0.7563344594594594,
      "tokens_rate.above_band": 0.9808389435525634,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019161056447436563
    },
    {
      "epoch": 1.9830452127659575,
      "grad_norm": 57.3916124603512,
      "learning_rate": 1.6000753087881368e-07,
      "loss": 0.2661,
      "step": 11930,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6121076233183856,
      "success_rate.epoch.env.math": 0.9822033898305085,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9643877356693963,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6112156443615397,
      "success_rate.epoch.global": 0.8663141065059649,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9981884057971014,
      "tokens_p.mean_in_band": 0.8489583333333334,
      "tokens_rate.above_band": 0.9960629921259843,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.003937007874015748
    },
    {
      "epoch": 1.983876329787234,
      "grad_norm": 252.33691947630146,
      "learning_rate": 1.6000681751250312e-07,
      "loss": 0.2123,
      "step": 11935,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6121076233183856,
      "success_rate.epoch.env.math": 0.9822335025380711,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9643877356693963,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.611218381880409,
      "success_rate.epoch.global": 0.8663469814336653,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9945436507936508,
      "tokens_p.mean_in_band": 0.875,
      "tokens_rate.above_band": 0.9882352941176471,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011764705882352941
    },
    {
      "epoch": 1.9847074468085106,
      "grad_norm": 34.148575748884376,
      "learning_rate": 1.6000613962919334e-07,
      "loss": 0.2007,
      "step": 11940,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6121076233183856,
      "success_rate.epoch.env.math": 0.9822784810126582,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9644080700418729,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6112243194119603,
      "success_rate.epoch.global": 0.8664455092763239,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9923930921052632,
      "tokens_rate.above_band": 1.0,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0
    },
    {
      "epoch": 1.9855385638297873,
      "grad_norm": 311.49618416577687,
      "learning_rate": 1.6000549723008746e-07,
      "loss": 0.1462,
      "step": 11945,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6121076233183856,
      "success_rate.epoch.env.math": 0.9822934232715008,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9644419091081955,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6112287540778844,
      "success_rate.epoch.global": 0.8665438919582567,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9976817507418397,
      "tokens_p.mean_in_band": 0.5458984375,
      "tokens_rate.above_band": 0.9825072886297376,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01749271137026239
    },
    {
      "epoch": 1.9863696808510638,
      "grad_norm": 126.06556815060515,
      "learning_rate": 1.6000489031632557e-07,
      "loss": 0.1991,
      "step": 11950,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823083403538332,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9644554267249572,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.611310227066938,
      "success_rate.epoch.global": 0.8666257668711657,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9980184511434511,
      "tokens_p.mean_in_band": 0.6692708333333334,
      "tokens_rate.above_band": 0.993801652892562,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.006198347107438017
    },
    {
      "epoch": 1.9872007978723403,
      "grad_norm": 66.6505551853555,
      "learning_rate": 1.600043188889848e-07,
      "loss": 0.223,
      "step": 11955,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823232323232324,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9644756838905775,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6113134224428489,
      "success_rate.epoch.global": 0.866691194505764,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.992070895522388,
      "tokens_p.mean_in_band": 0.890625,
      "tokens_rate.above_band": 0.9852941176470589,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.014705882352941176
    },
    {
      "epoch": 1.988031914893617,
      "grad_norm": 17.263431324826506,
      "learning_rate": 1.6000378294907925e-07,
      "loss": 0.2385,
      "step": 11960,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45161290322580644,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823380992430614,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9644959179798747,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6113166134436786,
      "success_rate.epoch.global": 0.866756557979897,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9945454545454545,
      "tokens_p.mean_in_band": 0.6960018382352942,
      "tokens_rate.above_band": 0.9417808219178082,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.05821917808219178
    },
    {
      "epoch": 1.9888630319148937,
      "grad_norm": 67.10608484627082,
      "learning_rate": 1.6000328249756015e-07,
      "loss": 0.237,
      "step": 11965,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823825503355704,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9645228609372035,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6115896993863591,
      "success_rate.epoch.global": 0.866887092823904,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.000484785202864,
      "tokens_p.mean_in_band": 0.6617647058823529,
      "tokens_rate.above_band": 0.9801169590643275,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.019883040935672516
    },
    {
      "epoch": 1.9896941489361701,
      "grad_norm": 79.86265263468553,
      "learning_rate": 1.6000281753531564e-07,
      "loss": 0.1332,
      "step": 11970,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45454545454545453,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823825503355704,
      "success_rate.epoch.env.sat": 0.1044776119402985,
      "success_rate.epoch.env.science": 0.9645295902883156,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6115903111455512,
      "success_rate.epoch.global": 0.866903391698298,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.992446682464455,
      "tokens_p.mean_in_band": 0.86328125,
      "tokens_rate.above_band": 0.9906103286384976,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.009389671361502348
    },
    {
      "epoch": 1.9905252659574468,
      "grad_norm": 51.38539418045454,
      "learning_rate": 1.600023880631709e-07,
      "loss": 0.1783,
      "step": 11975,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4574468085106383,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823825503355704,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.9645430413348502,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6118270256671954,
      "success_rate.epoch.global": 0.8668461632603108,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9992461622807017,
      "tokens_p.mean_in_band": 0.6575520833333334,
      "tokens_rate.above_band": 0.9743589743589743,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.02564102564102564
    },
    {
      "epoch": 1.9913563829787235,
      "grad_norm": 69.30176794063327,
      "learning_rate": 1.6000199408188814e-07,
      "loss": 0.267,
      "step": 11980,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4574468085106383,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6129753914988815,
      "success_rate.epoch.env.math": 0.9823973176865046,
      "success_rate.epoch.env.sat": 0.10416666666666667,
      "success_rate.epoch.env.science": 0.9645631987871897,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6118302006493112,
      "success_rate.epoch.global": 0.8669113149847095,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9872063758389261,
      "tokens_p.mean_in_band": 0.7751116071428571,
      "tokens_rate.above_band": 0.9551282051282052,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.04487179487179487
    },
    {
      "epoch": 1.9921875,
      "grad_norm": 28.87783423063378,
      "learning_rate": 1.6000163559216661e-07,
      "loss": 0.2138,
      "step": 11985,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6134078212290502,
      "success_rate.epoch.env.math": 0.9824267782426779,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9645699128457749,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6121056693993713,
      "success_rate.epoch.global": 0.8668866886688669,
      "success_rate.window.env.agentgym:alfworld": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.8,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9991379310344828,
      "tokens_p.mean_in_band": 0.6820913461538461,
      "tokens_rate.above_band": 0.9709821428571429,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.029017857142857144
    },
    {
      "epoch": 1.9930186170212765,
      "grad_norm": 87.3391163672724,
      "learning_rate": 1.6000131259464254e-07,
      "loss": 0.2637,
      "step": 11990,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6138392857142857,
      "success_rate.epoch.env.math": 0.9824414715719063,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.964590039765196,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6121480589206335,
      "success_rate.epoch.global": 0.8669679941363303,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9983431516936672,
      "tokens_p.mean_in_band": 0.7299107142857143,
      "tokens_rate.above_band": 0.9897959183673469,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.01020408163265306
    },
    {
      "epoch": 1.9938497340425532,
      "grad_norm": 58.57139015982192,
      "learning_rate": 1.6000102508988916e-07,
      "loss": 0.1188,
      "step": 11995,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5177664974619289,
      "success_rate.epoch.env.logic": 0.6138392857142857,
      "success_rate.epoch.env.math": 0.9824414715719063,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9646235338630345,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6121511038386188,
      "success_rate.epoch.global": 0.8670492003418386,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.sat": 0.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9954971181556196,
      "tokens_p.mean_in_band": 0.646484375,
      "tokens_rate.above_band": 0.9692737430167597,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.030726256983240222
    },
    {
      "epoch": 1.9946808510638299,
      "grad_norm": 41.188555198370956,
      "learning_rate": 1.600007730784167e-07,
      "loss": 0.1612,
      "step": 12000,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6142697881828316,
      "success_rate.epoch.env.math": 0.9824561403508771,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9646435999243713,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6124148092976138,
      "success_rate.epoch.global": 0.8671465170184214,
      "success_rate.window.env.ded": 1.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9971076458752515,
      "tokens_p.mean_in_band": 0.7760416666666666,
      "tokens_rate.above_band": 0.9880715705765407,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.011928429423459244
    },
    {
      "epoch": 1.9955119680851063,
      "grad_norm": 340.9179509805603,
      "learning_rate": 1.6000055656067245e-07,
      "loss": 0.261,
      "step": 12005,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.4603174603174603,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6146993318485523,
      "success_rate.epoch.env.math": 0.9824561403508771,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9646569646569647,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6124550736974606,
      "success_rate.epoch.global": 0.8671951219512195,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 0.8333333333333334,
      "success_rate.window.env_macro_mean": 0.9444444444444445,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9963910761154856,
      "tokens_p.mean_below_band": 2.877698079828406e-13,
      "tokens_p.mean_in_band": 0.7782451923076923,
      "tokens_rate.above_band": 0.9819587628865979,
      "tokens_rate.below_band": 0.001288659793814433,
      "tokens_rate.in_band": 0.01675257731958763
    },
    {
      "epoch": 1.996343085106383,
      "grad_norm": 5.60976331122218,
      "learning_rate": 1.6000037553704063e-07,
      "loss": 0.1842,
      "step": 12010,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45789473684210524,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6151279199110122,
      "success_rate.epoch.env.math": 0.9824561403508771,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9646836638338054,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6122762158578192,
      "success_rate.epoch.global": 0.8671703631489154,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.75,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9974578373015873,
      "tokens_p.mean_in_band": 0.498046875,
      "tokens_rate.above_band": 0.998019801980198,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0019801980198019802
    },
    {
      "epoch": 1.9971742021276597,
      "grad_norm": 117.33582973237931,
      "learning_rate": 1.600002300078426e-07,
      "loss": 0.2275,
      "step": 12015,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45789473684210524,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6151279199110122,
      "success_rate.epoch.env.math": 0.9824561403508771,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.964696998300925,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6122774280821028,
      "success_rate.epoch.global": 0.8672027290448343,
      "success_rate.window.env.agentgym:alfworld": 0.0,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 1.0,
      "tokens_p.mean_in_band": 0.73984375,
      "tokens_rate.above_band": 0.9950592885375494,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.004940711462450593
    },
    {
      "epoch": 1.9980053191489362,
      "grad_norm": 34.35684008035993,
      "learning_rate": 1.6000011997333656e-07,
      "loss": 0.2069,
      "step": 12020,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45789473684210524,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6151279199110122,
      "success_rate.epoch.env.math": 0.9825145711906744,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9647236370496133,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6122851616810561,
      "success_rate.epoch.global": 0.867332035053554,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 0.9885110294117647,
      "tokens_p.mean_in_band": 0.83984375,
      "tokens_rate.above_band": 0.9927007299270073,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.0072992700729927005
    },
    {
      "epoch": 1.9988364361702127,
      "grad_norm": 57.501124933761375,
      "learning_rate": 1.600000454337178e-07,
      "loss": 0.291,
      "step": 12025,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45789473684210524,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6151279199110122,
      "success_rate.epoch.env.math": 0.9825436408977556,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.9647568790049001,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.612290826377635,
      "success_rate.epoch.global": 0.8674449714216222,
      "success_rate.window.env.logic": 0.0,
      "success_rate.window.env.math": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 0.6666666666666666,
      "success_rate.window.global": 0.9,
      "tokens_p.mean_above_band": 0.9979516006097561,
      "tokens_p.mean_in_band": 0.740625,
      "tokens_rate.above_band": 0.984984984984985,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.015015015015015015
    },
    {
      "epoch": 1.9996675531914894,
      "grad_norm": 118.56216423802522,
      "learning_rate": 1.6000000638911862e-07,
      "loss": 0.2603,
      "step": 12030,
      "success_rate.epoch.env.abd": 0.6122448979591837,
      "success_rate.epoch.env.agentgym:alfworld": 0.45789473684210524,
      "success_rate.epoch.env.agentgym:sciworld": 0.42857142857142855,
      "success_rate.epoch.env.agentgym:textcraft": 0.55,
      "success_rate.epoch.env.babyai": 1.0,
      "success_rate.epoch.env.ded": 0.5202020202020202,
      "success_rate.epoch.env.logic": 0.6151279199110122,
      "success_rate.epoch.env.math": 0.9825436408977556,
      "success_rate.epoch.env.sat": 0.10385756676557864,
      "success_rate.epoch.env.science": 0.964790058369422,
      "success_rate.epoch.env.webshop": 0.5,
      "success_rate.epoch.env_macro_mean": 0.6122938426835006,
      "success_rate.epoch.global": 0.8675255226057365,
      "success_rate.window.env.logic": 1.0,
      "success_rate.window.env.science": 1.0,
      "success_rate.window.env_macro_mean": 1.0,
      "success_rate.window.global": 1.0,
      "tokens_p.mean_above_band": 1.000187969924812,
      "tokens_p.mean_in_band": 0.7552083333333334,
      "tokens_rate.above_band": 0.9910581222056631,
      "tokens_rate.below_band": 0.0,
      "tokens_rate.in_band": 0.00894187779433681
    }
  ],
  "logging_steps": 5,
  "max_steps": 12032,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 170545431364608.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}