{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5012531328320802,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "cache_hit_rate": 0.6549899518489838,
      "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": 0.275,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1008.8,
      "completions/mean_length": 722.45625,
      "completions/mean_terminated_length": 618.7799621582031,
      "completions/min_length": 145.7,
      "completions/min_terminated_length": 145.7,
      "entropy": 0.6699666887521744,
      "epoch": 0.02506265664160401,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.2841879725456238,
      "kl": 0.0036152674234472214,
      "learning_rate": 9e-05,
      "loss": -0.082733154296875,
      "num_tokens": 636060.0,
      "reward": 0.6506388366222382,
      "reward_std": 0.08262495435774327,
      "rewards/cache_reward/mean": 0.6506388366222382,
      "rewards/cache_reward/std": 0.08262495435774327,
      "step": 10,
      "step_time": 110.74446128769777
    },
    {
      "cache_hit_rate": 0.673021137714386,
      "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": 0.2453125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 994.9,
      "completions/mean_length": 733.9203125,
      "completions/mean_terminated_length": 644.366357421875,
      "completions/min_length": 140.3,
      "completions/min_terminated_length": 140.3,
      "entropy": 0.6534600198268891,
      "epoch": 0.05012531328320802,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.28635698556900024,
      "kl": 0.007895444217137993,
      "learning_rate": 0.0001,
      "loss": -0.10327683687210083,
      "num_tokens": 1241305.0,
      "reward": 0.6619674026966095,
      "reward_std": 0.08552395924925804,
      "rewards/cache_reward/mean": 0.6619674026966095,
      "rewards/cache_reward/std": 0.08552395924925804,
      "step": 20,
      "step_time": 109.56399042648263
    },
    {
      "cache_hit_rate": 0.6839983344078064,
      "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": 0.38125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1015.2,
      "completions/mean_length": 817.7609375,
      "completions/mean_terminated_length": 695.7103820800781,
      "completions/min_length": 234.8,
      "completions/min_terminated_length": 234.8,
      "entropy": 0.6154806256294251,
      "epoch": 0.07518796992481203,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.2883661985397339,
      "kl": 0.013737109955400229,
      "learning_rate": 0.0001,
      "loss": -0.07992171049118042,
      "num_tokens": 1935048.0,
      "reward": 0.6798466205596924,
      "reward_std": 0.08526109047234058,
      "rewards/cache_reward/mean": 0.6798466205596924,
      "rewards/cache_reward/std": 0.08526109047234058,
      "step": 30,
      "step_time": 110.41349991224706
    },
    {
      "cache_hit_rate": 0.688771378993988,
      "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": 0.2796875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 996.9,
      "completions/mean_length": 731.2515625,
      "completions/mean_terminated_length": 618.9319946289063,
      "completions/min_length": 141.9,
      "completions/min_terminated_length": 141.9,
      "entropy": 0.5641923353075982,
      "epoch": 0.10025062656641603,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.2640427052974701,
      "kl": 0.05390605996362865,
      "learning_rate": 0.0001,
      "loss": -0.0670427918434143,
      "num_tokens": 2538881.0,
      "reward": 0.680696839094162,
      "reward_std": 0.0919536855071783,
      "rewards/cache_reward/mean": 0.680696839094162,
      "rewards/cache_reward/std": 0.0919536855071783,
      "step": 40,
      "step_time": 109.29437069590203
    },
    {
      "cache_hit_rate": 0.6866635918617249,
      "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": 0.2890625,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1011.7,
      "completions/mean_length": 760.3578125,
      "completions/mean_terminated_length": 656.3232849121093,
      "completions/min_length": 45.7,
      "completions/min_terminated_length": 45.7,
      "entropy": 0.6070283114910126,
      "epoch": 0.12531328320802004,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.2869623005390167,
      "kl": 0.023429812863469124,
      "learning_rate": 0.0001,
      "loss": -0.09718080759048461,
      "num_tokens": 3192326.0,
      "reward": 0.6855185449123382,
      "reward_std": 0.10149984136223793,
      "rewards/cache_reward/mean": 0.6855185449123382,
      "rewards/cache_reward/std": 0.10149984136223793,
      "step": 50,
      "step_time": 110.27378524087835
    },
    {
      "cache_hit_rate": 0.6925897181034089,
      "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": 0.309375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 995.9,
      "completions/mean_length": 738.384375,
      "completions/mean_terminated_length": 613.4844848632813,
      "completions/min_length": 86.8,
      "completions/min_terminated_length": 86.8,
      "entropy": 0.6024186447262764,
      "epoch": 0.15037593984962405,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.25169217586517334,
      "kl": 3.6625402928330004,
      "learning_rate": 0.0001,
      "loss": 0.5570495128631592,
      "num_tokens": 3844932.0,
      "reward": 0.6902015984058381,
      "reward_std": 0.08153984323143959,
      "rewards/cache_reward/mean": 0.6902015984058381,
      "rewards/cache_reward/std": 0.08153984323143959,
      "step": 60,
      "step_time": 110.143448051624
    },
    {
      "cache_hit_rate": 0.707024896144867,
      "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": 0.3875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1012.0,
      "completions/mean_length": 803.928125,
      "completions/mean_terminated_length": 670.2502990722656,
      "completions/min_length": 146.8,
      "completions/min_terminated_length": 146.8,
      "entropy": 0.6164677605032921,
      "epoch": 0.17543859649122806,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.29885679483413696,
      "kl": 0.02769087813794613,
      "learning_rate": 0.0001,
      "loss": -0.08792343139648437,
      "num_tokens": 4508430.0,
      "reward": 0.7026471257209778,
      "reward_std": 0.08549872897565365,
      "rewards/cache_reward/mean": 0.7026471257209778,
      "rewards/cache_reward/std": 0.08549872897565365,
      "step": 70,
      "step_time": 109.93217876499985
    },
    {
      "cache_hit_rate": 0.6787703096866607,
      "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": 0.2984375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1011.0,
      "completions/mean_length": 742.275,
      "completions/mean_terminated_length": 631.2970550537109,
      "completions/min_length": 173.1,
      "completions/min_terminated_length": 173.1,
      "entropy": 0.6354820564389229,
      "epoch": 0.20050125313283207,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.3051297068595886,
      "kl": 0.027491158153861762,
      "learning_rate": 0.0001,
      "loss": -0.05539093017578125,
      "num_tokens": 5126438.0,
      "reward": 0.6731199264526367,
      "reward_std": 0.0984181858599186,
      "rewards/cache_reward/mean": 0.6731199264526367,
      "rewards/cache_reward/std": 0.0984181858599186,
      "step": 80,
      "step_time": 109.76294787270017
    },
    {
      "cache_hit_rate": 0.7168771982192993,
      "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": 0.3703125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1001.6,
      "completions/mean_length": 781.2203125,
      "completions/mean_terminated_length": 644.1493225097656,
      "completions/min_length": 124.9,
      "completions/min_terminated_length": 124.9,
      "entropy": 0.510772630572319,
      "epoch": 0.22556390977443608,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.22160571813583374,
      "kl": 0.028083418030291796,
      "learning_rate": 0.0001,
      "loss": -0.10533699989318848,
      "num_tokens": 5793339.0,
      "reward": 0.7083093225955963,
      "reward_std": 0.08305367790162563,
      "rewards/cache_reward/mean": 0.7083093225955963,
      "rewards/cache_reward/std": 0.08305367790162563,
      "step": 90,
      "step_time": 110.1031208519591
    },
    {
      "cache_hit_rate": 0.6966540038585662,
      "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": 0.3078125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 997.4,
      "completions/mean_length": 690.071875,
      "completions/mean_terminated_length": 542.2264129638672,
      "completions/min_length": 38.7,
      "completions/min_terminated_length": 38.7,
      "entropy": 0.5484601214528084,
      "epoch": 0.2506265664160401,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.28518208861351013,
      "kl": 0.027807974442839622,
      "learning_rate": 0.0001,
      "loss": -0.08660122156143188,
      "num_tokens": 6417249.0,
      "reward": 0.6993527948856354,
      "reward_std": 0.09250091910362243,
      "rewards/cache_reward/mean": 0.6993527948856354,
      "rewards/cache_reward/std": 0.09250091910362243,
      "step": 100,
      "step_time": 110.59711477749515
    },
    {
      "cache_hit_rate": 0.6942323863506317,
      "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": 0.2796875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1012.6,
      "completions/mean_length": 738.9765625,
      "completions/mean_terminated_length": 637.4039031982422,
      "completions/min_length": 102.2,
      "completions/min_terminated_length": 102.2,
      "entropy": 0.5651590198278427,
      "epoch": 0.2756892230576441,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.278904527425766,
      "kl": 0.029639831464737653,
      "learning_rate": 0.0001,
      "loss": -0.06971979141235352,
      "num_tokens": 7058914.0,
      "reward": 0.6939837038516998,
      "reward_std": 0.08437503017485141,
      "rewards/cache_reward/mean": 0.6939837038516998,
      "rewards/cache_reward/std": 0.08437503017485141,
      "step": 110,
      "step_time": 109.98037863150239
    },
    {
      "cache_hit_rate": 0.7087398171424866,
      "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": 0.38125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1012.8,
      "completions/mean_length": 794.7265625,
      "completions/mean_terminated_length": 661.2110961914062,
      "completions/min_length": 177.9,
      "completions/min_terminated_length": 177.9,
      "entropy": 0.49859170615673065,
      "epoch": 0.3007518796992481,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.23720738291740417,
      "kl": 0.12654243744909763,
      "learning_rate": 0.0001,
      "loss": -0.07652193903923035,
      "num_tokens": 7725699.0,
      "reward": 0.7066135585308075,
      "reward_std": 0.0815408643335104,
      "rewards/cache_reward/mean": 0.7066135585308075,
      "rewards/cache_reward/std": 0.0815408643335104,
      "step": 120,
      "step_time": 110.21964054489509
    },
    {
      "cache_hit_rate": 0.7066302120685577,
      "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": 0.303125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1010.1,
      "completions/mean_length": 719.2859375,
      "completions/mean_terminated_length": 589.672817993164,
      "completions/min_length": 51.7,
      "completions/min_terminated_length": 51.7,
      "entropy": 0.5097475752234459,
      "epoch": 0.3258145363408521,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.2551797330379486,
      "kl": 0.03401126619428396,
      "learning_rate": 0.0001,
      "loss": -0.029747769236564636,
      "num_tokens": 8359146.0,
      "reward": 0.7066013753414154,
      "reward_std": 0.08856594860553742,
      "rewards/cache_reward/mean": 0.7066013753414154,
      "rewards/cache_reward/std": 0.08856594860553742,
      "step": 130,
      "step_time": 110.3610016158782
    },
    {
      "cache_hit_rate": 0.7057172179222106,
      "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": 0.2875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1012.4,
      "completions/mean_length": 718.9546875,
      "completions/mean_terminated_length": 599.3654174804688,
      "completions/min_length": 45.5,
      "completions/min_terminated_length": 45.5,
      "entropy": 0.5367702215909957,
      "epoch": 0.3508771929824561,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.28203365206718445,
      "kl": 0.028053219616413116,
      "learning_rate": 0.0001,
      "loss": -0.09814745783805848,
      "num_tokens": 8960389.0,
      "reward": 0.6947050273418427,
      "reward_std": 0.092516228556633,
      "rewards/cache_reward/mean": 0.6947050273418427,
      "rewards/cache_reward/std": 0.092516228556633,
      "step": 140,
      "step_time": 109.26147313890979
    },
    {
      "cache_hit_rate": 0.7100595355033874,
      "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": 0.259375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1010.9,
      "completions/mean_length": 643.5265625,
      "completions/mean_terminated_length": 526.2732879638672,
      "completions/min_length": 65.3,
      "completions/min_terminated_length": 65.3,
      "entropy": 0.4884163364768028,
      "epoch": 0.37593984962406013,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.3192034065723419,
      "kl": 0.03535754019394517,
      "learning_rate": 0.0001,
      "loss": -0.015955117344856263,
      "num_tokens": 9533782.0,
      "reward": 0.7072697579860687,
      "reward_std": 0.08281751312315463,
      "rewards/cache_reward/mean": 0.7072697579860687,
      "rewards/cache_reward/std": 0.08281751312315463,
      "step": 150,
      "step_time": 109.54034506990574
    },
    {
      "cache_hit_rate": 0.7135620355606079,
      "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": 0.29375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 995.1,
      "completions/mean_length": 684.2015625,
      "completions/mean_terminated_length": 545.6471801757813,
      "completions/min_length": 68.3,
      "completions/min_terminated_length": 68.3,
      "entropy": 0.5298304185271263,
      "epoch": 0.40100250626566414,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.3209550082683563,
      "kl": 0.03265416445210576,
      "learning_rate": 0.0001,
      "loss": -0.011588484048843384,
      "num_tokens": 10162439.0,
      "reward": 0.7117338001728057,
      "reward_std": 0.09532129615545273,
      "rewards/cache_reward/mean": 0.7117338001728057,
      "rewards/cache_reward/std": 0.09532129615545273,
      "step": 160,
      "step_time": 109.83968829209917
    },
    {
      "cache_hit_rate": 0.7009754419326782,
      "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": 0.271875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1007.0,
      "completions/mean_length": 694.5515625,
      "completions/mean_terminated_length": 572.3542327880859,
      "completions/min_length": 100.0,
      "completions/min_terminated_length": 100.0,
      "entropy": 0.5273847237229348,
      "epoch": 0.42606516290726815,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.3118448257446289,
      "kl": 0.03259017681702971,
      "learning_rate": 0.0001,
      "loss": -0.07569116950035096,
      "num_tokens": 10744440.0,
      "reward": 0.6976909101009369,
      "reward_std": 0.09229764454066754,
      "rewards/cache_reward/mean": 0.6976909101009369,
      "rewards/cache_reward/std": 0.09229764454066754,
      "step": 170,
      "step_time": 109.6869213941507
    },
    {
      "cache_hit_rate": 0.7058276951313018,
      "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": 0.315625,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 994.5,
      "completions/mean_length": 709.8875,
      "completions/mean_terminated_length": 568.6204956054687,
      "completions/min_length": 65.8,
      "completions/min_terminated_length": 65.8,
      "entropy": 0.5262452140450478,
      "epoch": 0.45112781954887216,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.27938130497932434,
      "kl": 0.03458747547119856,
      "learning_rate": 0.0001,
      "loss": -0.045800769329071046,
      "num_tokens": 11370640.0,
      "reward": 0.7100380957126617,
      "reward_std": 0.10111712664365768,
      "rewards/cache_reward/mean": 0.7100380957126617,
      "rewards/cache_reward/std": 0.10111712664365768,
      "step": 180,
      "step_time": 110.07354199965485
    },
    {
      "cache_hit_rate": 0.7054557979106904,
      "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": 0.2421875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1007.8,
      "completions/mean_length": 614.809375,
      "completions/mean_terminated_length": 490.51698608398436,
      "completions/min_length": 56.3,
      "completions/min_terminated_length": 56.3,
      "entropy": 0.5158756494522094,
      "epoch": 0.47619047619047616,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.26570478081703186,
      "kl": 0.037209075130522254,
      "learning_rate": 0.0001,
      "loss": 0.009295095503330231,
      "num_tokens": 11911350.0,
      "reward": 0.708037257194519,
      "reward_std": 0.09269837327301503,
      "rewards/cache_reward/mean": 0.708037257194519,
      "rewards/cache_reward/std": 0.09269837327301503,
      "step": 190,
      "step_time": 109.52065962508786
    },
    {
      "cache_hit_rate": 0.718935352563858,
      "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": 0.2359375,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 965.0,
      "completions/mean_length": 572.43125,
      "completions/mean_terminated_length": 443.49492797851565,
      "completions/min_length": 24.7,
      "completions/min_terminated_length": 24.7,
      "entropy": 0.48532100319862365,
      "epoch": 0.5012531328320802,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.2529448866844177,
      "kl": 0.0392603786662221,
      "learning_rate": 0.0001,
      "loss": -0.06291077136993409,
      "num_tokens": 12414762.0,
      "reward": 0.7250898122787476,
      "reward_std": 0.0879605084657669,
      "rewards/cache_reward/mean": 0.7250898122787476,
      "rewards/cache_reward/std": 0.0879605084657669,
      "step": 200,
      "step_time": 109.23635325629729
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 12414762,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}