{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5037593984962406,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "cache_hit_rate": 0.2987321466207504,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.8671875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 809.9,
      "completions/mean_length": 961.46875,
      "completions/mean_terminated_length": 563.5086151123047,
      "completions/min_length": 327.9,
      "completions/min_terminated_length": 327.9,
      "entropy": 0.7783569753170013,
      "epoch": 0.02506265664160401,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.19229525327682495,
      "kl": 0.025735817663371564,
      "learning_rate": 9e-05,
      "loss": 0.03023299276828766,
      "num_tokens": 773884.0,
      "reward": 0.2986815273761749,
      "reward_std": 0.021126844733953477,
      "rewards/cache_reward/mean": 0.2986815273761749,
      "rewards/cache_reward/std": 0.021126844733953477,
      "step": 10,
      "step_time": 90.0082708384376
    },
    {
      "cache_hit_rate": 0.3069839864969254,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.8828125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 821.6,
      "completions/mean_length": 971.9640625,
      "completions/mean_terminated_length": 570.3135467529297,
      "completions/min_length": 287.1,
      "completions/min_terminated_length": 287.1,
      "entropy": 0.754186350107193,
      "epoch": 0.05012531328320802,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 1.0587414503097534,
      "kl": 0.028826666437089442,
      "learning_rate": 0.0001,
      "loss": -0.013258826732635499,
      "num_tokens": 1581589.0,
      "reward": 0.306694495677948,
      "reward_std": 0.021151169389486312,
      "rewards/cache_reward/mean": 0.306694495677948,
      "rewards/cache_reward/std": 0.021151169389486312,
      "step": 20,
      "step_time": 90.82258757026867
    },
    {
      "cache_hit_rate": 0.3231631815433502,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9515625,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 664.1,
      "completions/mean_length": 1000.9328125,
      "completions/mean_terminated_length": 459.4166717529297,
      "completions/min_length": 412.7,
      "completions/min_terminated_length": 310.3,
      "entropy": 0.5696786761283874,
      "epoch": 0.07518796992481203,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.1489810347557068,
      "kl": 0.5070431146770715,
      "learning_rate": 0.0001,
      "loss": 0.052439266443252565,
      "num_tokens": 2390842.0,
      "reward": 0.3228506237268448,
      "reward_std": 0.02563070598989725,
      "rewards/cache_reward/mean": 0.3228506237268448,
      "rewards/cache_reward/std": 0.02563070598989725,
      "step": 30,
      "step_time": 90.69367619913537
    },
    {
      "cache_hit_rate": 0.3287877798080444,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9921875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 150.8,
      "completions/mean_length": 1018.8375,
      "completions/mean_terminated_length": 93.1,
      "completions/min_length": 752.2,
      "completions/min_terminated_length": 35.4,
      "entropy": 0.5493248522281646,
      "epoch": 0.10025062656641603,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.15555262565612793,
      "kl": 0.04194357730448246,
      "learning_rate": 0.0001,
      "loss": 0.004945866391062736,
      "num_tokens": 3234082.0,
      "reward": 0.3287609279155731,
      "reward_std": 0.024521841667592525,
      "rewards/cache_reward/mean": 0.3287609279155731,
      "rewards/cache_reward/std": 0.024521841667592525,
      "step": 40,
      "step_time": 90.52190033134539
    },
    {
      "cache_hit_rate": 0.3247293561697006,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9921875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 361.6,
      "completions/mean_length": 1021.65,
      "completions/mean_terminated_length": 361.6,
      "completions/min_length": 873.6,
      "completions/min_terminated_length": 361.6,
      "entropy": 0.6632817029953003,
      "epoch": 0.12531328320802004,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.18938110768795013,
      "kl": 0.054390712082386015,
      "learning_rate": 0.0001,
      "loss": 0.008095483481884002,
      "num_tokens": 4060218.0,
      "reward": 0.32472453713417054,
      "reward_std": 0.025068807974457742,
      "rewards/cache_reward/mean": 0.32472453713417054,
      "rewards/cache_reward/std": 0.025068807974457742,
      "step": 50,
      "step_time": 90.76908840958495
    },
    {
      "cache_hit_rate": 0.33069254755973815,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.98125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 455.7,
      "completions/mean_length": 1014.6015625,
      "completions/mean_terminated_length": 384.475,
      "completions/min_length": 629.5,
      "completions/min_terminated_length": 322.3,
      "entropy": 0.6398827135562897,
      "epoch": 0.15037593984962405,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.1729903519153595,
      "kl": 0.04443241953849793,
      "learning_rate": 0.0001,
      "loss": -1.8284097313880922e-05,
      "num_tokens": 4852611.0,
      "reward": 0.3305449992418289,
      "reward_std": 0.02162333866581321,
      "rewards/cache_reward/mean": 0.3305449992418289,
      "rewards/cache_reward/std": 0.02162333866581321,
      "step": 60,
      "step_time": 90.52109750902746
    },
    {
      "cache_hit_rate": 0.3291244089603424,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9953125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 118.3,
      "completions/mean_length": 1021.0484375,
      "completions/mean_terminated_length": 118.3,
      "completions/min_length": 835.1,
      "completions/min_terminated_length": 118.3,
      "entropy": 0.6163755863904953,
      "epoch": 0.17543859649122806,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.6231634020805359,
      "kl": 0.04733915701508522,
      "learning_rate": 0.0001,
      "loss": -0.0013297975063323974,
      "num_tokens": 5682834.0,
      "reward": 0.3290934026241302,
      "reward_std": 0.025694792345166206,
      "rewards/cache_reward/mean": 0.3290934026241302,
      "rewards/cache_reward/std": 0.025694792345166206,
      "step": 70,
      "step_time": 91.40459936279804
    },
    {
      "cache_hit_rate": 0.32914042472839355,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9859375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 280.2,
      "completions/mean_length": 1016.7546875,
      "completions/mean_terminated_length": 271.95,
      "completions/min_length": 673.3,
      "completions/min_terminated_length": 263.7,
      "entropy": 0.6250631839036942,
      "epoch": 0.20050125313283207,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.14358767867088318,
      "kl": 0.04605277068912983,
      "learning_rate": 0.0001,
      "loss": 0.0016001952812075616,
      "num_tokens": 6469845.0,
      "reward": 0.3290808916091919,
      "reward_std": 0.027931400947272776,
      "rewards/cache_reward/mean": 0.3290808916091919,
      "rewards/cache_reward/std": 0.027931400947272776,
      "step": 80,
      "step_time": 90.27690456421115
    },
    {
      "cache_hit_rate": 0.3384521096944809,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.990625,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 164.9,
      "completions/mean_length": 1017.1234375,
      "completions/mean_terminated_length": 164.3,
      "completions/min_length": 675.7,
      "completions/min_terminated_length": 163.7,
      "entropy": 0.44799884855747224,
      "epoch": 0.22556390977443608,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.19581231474876404,
      "kl": 0.042757127434015274,
      "learning_rate": 0.0001,
      "loss": -0.004632307216525078,
      "num_tokens": 7271556.0,
      "reward": 0.3383351147174835,
      "reward_std": 0.023683687672019005,
      "rewards/cache_reward/mean": 0.3383351147174835,
      "rewards/cache_reward/std": 0.023683687672019005,
      "step": 90,
      "step_time": 91.19093074775301
    },
    {
      "cache_hit_rate": 0.3332447409629822,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9921875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 279.5,
      "completions/mean_length": 1020.3671875,
      "completions/mean_terminated_length": 279.5,
      "completions/min_length": 791.5,
      "completions/min_terminated_length": 279.5,
      "entropy": 0.5914906859397888,
      "epoch": 0.2506265664160401,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.22322462499141693,
      "kl": 0.04192206896841526,
      "learning_rate": 0.0001,
      "loss": 0.004385053366422653,
      "num_tokens": 8067287.0,
      "reward": 0.33321733176708224,
      "reward_std": 0.02411998054012656,
      "rewards/cache_reward/mean": 0.33321733176708224,
      "rewards/cache_reward/std": 0.02411998054012656,
      "step": 100,
      "step_time": 90.90292567885481
    },
    {
      "cache_hit_rate": 0.33464895784854887,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.98125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 373.3,
      "completions/mean_length": 1013.3484375,
      "completions/mean_terminated_length": 336.025,
      "completions/min_length": 503.6,
      "completions/min_terminated_length": 298.8,
      "entropy": 0.4564924329519272,
      "epoch": 0.2756892230576441,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.1496705561876297,
      "kl": 0.0379826420918107,
      "learning_rate": 0.0001,
      "loss": 0.0033605631440877916,
      "num_tokens": 8892334.0,
      "reward": 0.33460802435874937,
      "reward_std": 0.024270175583660604,
      "rewards/cache_reward/mean": 0.33460802435874937,
      "rewards/cache_reward/std": 0.024270175583660604,
      "step": 110,
      "step_time": 91.2041310617933
    },
    {
      "cache_hit_rate": 0.3374886929988861,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9828125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 459.2,
      "completions/mean_length": 1015.209375,
      "completions/mean_terminated_length": 380.6,
      "completions/min_length": 506.8,
      "completions/min_terminated_length": 302.0,
      "entropy": 0.5316164076328278,
      "epoch": 0.3007518796992481,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.16703373193740845,
      "kl": 0.0434085251763463,
      "learning_rate": 0.0001,
      "loss": 0.008729323744773865,
      "num_tokens": 9680356.0,
      "reward": 0.33764258623123167,
      "reward_std": 0.024684826284646987,
      "rewards/cache_reward/mean": 0.33764258623123167,
      "rewards/cache_reward/std": 0.024684826284646987,
      "step": 120,
      "step_time": 91.07375006200746
    },
    {
      "cache_hit_rate": 0.33408362567424776,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9859375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 328.1,
      "completions/mean_length": 1015.221875,
      "completions/mean_terminated_length": 301.4,
      "completions/min_length": 581.9,
      "completions/min_terminated_length": 274.7,
      "entropy": 0.5473819822072983,
      "epoch": 0.3258145363408521,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.17018599808216095,
      "kl": 0.08177528716623783,
      "learning_rate": 0.0001,
      "loss": 0.008963721990585326,
      "num_tokens": 10495674.0,
      "reward": 0.3341580301523209,
      "reward_std": 0.024980502761900426,
      "rewards/cache_reward/mean": 0.3341580301523209,
      "rewards/cache_reward/std": 0.024980502761900426,
      "step": 130,
      "step_time": 90.68363874959759
    },
    {
      "cache_hit_rate": 0.33405864536762236,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9859375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 253.5,
      "completions/mean_length": 1015.403125,
      "completions/mean_terminated_length": 207.71666870117187,
      "completions/min_length": 675.1,
      "completions/min_terminated_length": 163.1,
      "entropy": 0.5471912950277329,
      "epoch": 0.3508771929824561,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.20733150839805603,
      "kl": 0.35445162318646906,
      "learning_rate": 0.0001,
      "loss": 0.04615514874458313,
      "num_tokens": 11295188.0,
      "reward": 0.3339251846075058,
      "reward_std": 0.02682190975174308,
      "rewards/cache_reward/mean": 0.3339251846075058,
      "rewards/cache_reward/std": 0.02682190975174308,
      "step": 140,
      "step_time": 91.03833641626406
    },
    {
      "cache_hit_rate": 0.33871919512748716,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.978125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 519.8,
      "completions/mean_length": 1013.0640625,
      "completions/mean_terminated_length": 432.925,
      "completions/min_length": 537.9,
      "completions/min_terminated_length": 333.1,
      "entropy": 0.49129725992679596,
      "epoch": 0.37593984962406013,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.1506304144859314,
      "kl": 0.045265543088316915,
      "learning_rate": 0.0001,
      "loss": -0.0007558207958936692,
      "num_tokens": 12104301.0,
      "reward": 0.3386825680732727,
      "reward_std": 0.025650268793106078,
      "rewards/cache_reward/mean": 0.3386825680732727,
      "rewards/cache_reward/std": 0.025650268793106078,
      "step": 150,
      "step_time": 91.25925274270121
    },
    {
      "cache_hit_rate": 0.33684642016887667,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.98125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 453.5,
      "completions/mean_length": 1014.05,
      "completions/mean_terminated_length": 370.8833374023437,
      "completions/min_length": 471.5,
      "completions/min_terminated_length": 266.7,
      "entropy": 0.5017873764038085,
      "epoch": 0.40100250626566414,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 2.4631996154785156,
      "kl": 24.154931166768073,
      "learning_rate": 0.0001,
      "loss": 3.8478744506835936,
      "num_tokens": 12925005.0,
      "reward": 0.3366888463497162,
      "reward_std": 0.02669309824705124,
      "rewards/cache_reward/mean": 0.3366888463497162,
      "rewards/cache_reward/std": 0.02669309824705124,
      "step": 160,
      "step_time": 90.7307717730524
    },
    {
      "cache_hit_rate": 0.3352246254682541,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.984375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 195.4,
      "completions/mean_length": 1014.4828125,
      "completions/mean_terminated_length": 127.05000305175781,
      "completions/min_length": 784.3,
      "completions/min_terminated_length": 67.5,
      "entropy": 0.5599089354276657,
      "epoch": 0.42606516290726815,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.6771759390830994,
      "kl": 0.057728367298841475,
      "learning_rate": 0.0001,
      "loss": -0.005303345993161202,
      "num_tokens": 13762762.0,
      "reward": 0.33506683707237245,
      "reward_std": 0.022994110081344842,
      "rewards/cache_reward/mean": 0.33506683707237245,
      "rewards/cache_reward/std": 0.022994110081344842,
      "step": 170,
      "step_time": 91.37958506643773
    },
    {
      "cache_hit_rate": 0.33833766877651217,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.99375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 346.8,
      "completions/mean_length": 1023.01875,
      "completions/mean_terminated_length": 346.8,
      "completions/min_length": 961.2,
      "completions/min_terminated_length": 346.8,
      "entropy": 0.5654248386621475,
      "epoch": 0.45112781954887216,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.14284838736057281,
      "kl": 2.4538527205586433,
      "learning_rate": 0.0001,
      "loss": 0.39122982025146485,
      "num_tokens": 14591590.0,
      "reward": 0.33830906450748444,
      "reward_std": 0.02580958418548107,
      "rewards/cache_reward/mean": 0.33830906450748444,
      "rewards/cache_reward/std": 0.02580958418548107,
      "step": 180,
      "step_time": 91.57028467489872
    },
    {
      "cache_hit_rate": 0.3408436506986618,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9890625,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 202.6,
      "completions/mean_length": 1016.6109375,
      "completions/mean_terminated_length": 183.8,
      "completions/min_length": 677.0,
      "completions/min_terminated_length": 165.0,
      "entropy": 0.5419578611850738,
      "epoch": 0.47619047619047616,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.13886591792106628,
      "kl": 0.07005284689366817,
      "learning_rate": 0.0001,
      "loss": 0.008208285272121429,
      "num_tokens": 15394349.0,
      "reward": 0.3408004969358444,
      "reward_std": 0.025611967965960502,
      "rewards/cache_reward/mean": 0.3408004969358444,
      "rewards/cache_reward/std": 0.025611967965960502,
      "step": 190,
      "step_time": 91.14261374084745
    },
    {
      "cache_hit_rate": 0.3391114443540573,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.9921875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 179.6,
      "completions/mean_length": 1019.0921875,
      "completions/mean_terminated_length": 179.0,
      "completions/min_length": 792.8,
      "completions/min_terminated_length": 178.4,
      "entropy": 0.5290060758590698,
      "epoch": 0.5012531328320802,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.1409655660390854,
      "kl": 0.0499697394669056,
      "learning_rate": 0.0001,
      "loss": 0.004792223125696183,
      "num_tokens": 16176376.0,
      "reward": 0.33905126750469206,
      "reward_std": 0.026329115405678748,
      "rewards/cache_reward/mean": 0.33905126750469206,
      "rewards/cache_reward/std": 0.026329115405678748,
      "step": 200,
      "step_time": 90.93274403410032
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 16261463,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}