{
  "best_metric": 0.42480990290641785,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.4241781548250265,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0042417815482502655,
      "grad_norm": 2.440074920654297,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.3247,
      "step": 1
    },
    {
      "epoch": 0.0042417815482502655,
      "eval_loss": 2.892012119293213,
      "eval_runtime": 8.3575,
      "eval_samples_per_second": 47.502,
      "eval_steps_per_second": 5.983,
      "step": 1
    },
    {
      "epoch": 0.008483563096500531,
      "grad_norm": 3.9008901119232178,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.4604,
      "step": 2
    },
    {
      "epoch": 0.012725344644750796,
      "grad_norm": 3.8679404258728027,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.5737,
      "step": 3
    },
    {
      "epoch": 0.016967126193001062,
      "grad_norm": 4.003969192504883,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.5677,
      "step": 4
    },
    {
      "epoch": 0.021208907741251327,
      "grad_norm": 5.167972087860107,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.6147,
      "step": 5
    },
    {
      "epoch": 0.02545068928950159,
      "grad_norm": 4.082551956176758,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.5965,
      "step": 6
    },
    {
      "epoch": 0.029692470837751856,
      "grad_norm": 4.586578369140625,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 0.646,
      "step": 7
    },
    {
      "epoch": 0.033934252386002124,
      "grad_norm": 10.951172828674316,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.765,
      "step": 8
    },
    {
      "epoch": 0.03817603393425239,
      "grad_norm": 4.923064231872559,
      "learning_rate": 1.5e-06,
      "loss": 0.6751,
      "step": 9
    },
    {
      "epoch": 0.042417815482502653,
      "grad_norm": 4.684195518493652,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.7466,
      "step": 10
    },
    {
      "epoch": 0.04665959703075292,
      "grad_norm": 9.586348533630371,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 0.8434,
      "step": 11
    },
    {
      "epoch": 0.05090137857900318,
      "grad_norm": 15.056419372558594,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.0154,
      "step": 12
    },
    {
      "epoch": 0.05514316012725345,
      "grad_norm": 6.797557830810547,
      "learning_rate": 2.166666666666667e-06,
      "loss": 0.8514,
      "step": 13
    },
    {
      "epoch": 0.05938494167550371,
      "grad_norm": 3.789074659347534,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.7579,
      "step": 14
    },
    {
      "epoch": 0.06362672322375397,
      "grad_norm": 4.713261604309082,
      "learning_rate": 2.5e-06,
      "loss": 0.8242,
      "step": 15
    },
    {
      "epoch": 0.06786850477200425,
      "grad_norm": 3.963026285171509,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.8754,
      "step": 16
    },
    {
      "epoch": 0.07211028632025451,
      "grad_norm": 3.974591016769409,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 0.9025,
      "step": 17
    },
    {
      "epoch": 0.07635206786850478,
      "grad_norm": 4.688375473022461,
      "learning_rate": 3e-06,
      "loss": 1.0425,
      "step": 18
    },
    {
      "epoch": 0.08059384941675504,
      "grad_norm": 5.0737690925598145,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 1.2042,
      "step": 19
    },
    {
      "epoch": 0.08483563096500531,
      "grad_norm": 8.627097129821777,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.7189,
      "step": 20
    },
    {
      "epoch": 0.08907741251325557,
      "grad_norm": 11.974156379699707,
      "learning_rate": 3.5e-06,
      "loss": 1.9111,
      "step": 21
    },
    {
      "epoch": 0.09331919406150584,
      "grad_norm": 13.727147102355957,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 2.2629,
      "step": 22
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 19.623498916625977,
      "learning_rate": 3.833333333333334e-06,
      "loss": 2.8472,
      "step": 23
    },
    {
      "epoch": 0.10180275715800637,
      "grad_norm": 17.45310401916504,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.7759,
      "step": 24
    },
    {
      "epoch": 0.10604453870625663,
      "grad_norm": 22.359373092651367,
      "learning_rate": 4.166666666666667e-06,
      "loss": 2.3388,
      "step": 25
    },
    {
      "epoch": 0.1102863202545069,
      "grad_norm": 13.022788047790527,
      "learning_rate": 4.333333333333334e-06,
      "loss": 2.2261,
      "step": 26
    },
    {
      "epoch": 0.11452810180275716,
      "grad_norm": 18.914791107177734,
      "learning_rate": 4.5e-06,
      "loss": 2.9993,
      "step": 27
    },
    {
      "epoch": 0.11876988335100742,
      "grad_norm": 18.410812377929688,
      "learning_rate": 4.666666666666667e-06,
      "loss": 2.4895,
      "step": 28
    },
    {
      "epoch": 0.12301166489925769,
      "grad_norm": 14.935495376586914,
      "learning_rate": 4.833333333333333e-06,
      "loss": 2.3596,
      "step": 29
    },
    {
      "epoch": 0.12725344644750794,
      "grad_norm": 17.543804168701172,
      "learning_rate": 5e-06,
      "loss": 2.7266,
      "step": 30
    },
    {
      "epoch": 0.13149522799575822,
      "grad_norm": 15.843499183654785,
      "learning_rate": 4.997482666353287e-06,
      "loss": 2.292,
      "step": 31
    },
    {
      "epoch": 0.1357370095440085,
      "grad_norm": 16.629941940307617,
      "learning_rate": 4.989935734988098e-06,
      "loss": 2.4197,
      "step": 32
    },
    {
      "epoch": 0.13997879109225875,
      "grad_norm": 15.72042465209961,
      "learning_rate": 4.977374404419838e-06,
      "loss": 2.3473,
      "step": 33
    },
    {
      "epoch": 0.14422057264050903,
      "grad_norm": 13.605842590332031,
      "learning_rate": 4.959823971496575e-06,
      "loss": 2.0056,
      "step": 34
    },
    {
      "epoch": 0.14846235418875928,
      "grad_norm": 11.888983726501465,
      "learning_rate": 4.937319780454559e-06,
      "loss": 1.7911,
      "step": 35
    },
    {
      "epoch": 0.15270413573700956,
      "grad_norm": 18.208675384521484,
      "learning_rate": 4.909907151739634e-06,
      "loss": 2.2271,
      "step": 36
    },
    {
      "epoch": 0.1569459172852598,
      "grad_norm": 18.528289794921875,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 2.0293,
      "step": 37
    },
    {
      "epoch": 0.16118769883351008,
      "grad_norm": 17.24335479736328,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 2.087,
      "step": 38
    },
    {
      "epoch": 0.16542948038176034,
      "grad_norm": 14.06977367401123,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 1.897,
      "step": 39
    },
    {
      "epoch": 0.16967126193001061,
      "grad_norm": 21.608551025390625,
      "learning_rate": 4.752422169756048e-06,
      "loss": 1.8175,
      "step": 40
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 16.8688907623291,
      "learning_rate": 4.701488829641845e-06,
      "loss": 1.8707,
      "step": 41
    },
    {
      "epoch": 0.17815482502651114,
      "grad_norm": 13.121498107910156,
      "learning_rate": 4.646121984004666e-06,
      "loss": 1.6978,
      "step": 42
    },
    {
      "epoch": 0.1823966065747614,
      "grad_norm": 13.48686408996582,
      "learning_rate": 4.586433134303257e-06,
      "loss": 1.6308,
      "step": 43
    },
    {
      "epoch": 0.18663838812301167,
      "grad_norm": 14.717817306518555,
      "learning_rate": 4.522542485937369e-06,
      "loss": 1.9161,
      "step": 44
    },
    {
      "epoch": 0.19088016967126192,
      "grad_norm": 14.173543930053711,
      "learning_rate": 4.454578706170075e-06,
      "loss": 1.3766,
      "step": 45
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 15.915189743041992,
      "learning_rate": 4.382678665009028e-06,
      "loss": 1.4068,
      "step": 46
    },
    {
      "epoch": 0.19936373276776245,
      "grad_norm": 12.305916786193848,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 1.1608,
      "step": 47
    },
    {
      "epoch": 0.20360551431601273,
      "grad_norm": 21.32429313659668,
      "learning_rate": 4.227656622467162e-06,
      "loss": 1.3466,
      "step": 48
    },
    {
      "epoch": 0.20784729586426298,
      "grad_norm": 17.543088912963867,
      "learning_rate": 4.144846814849282e-06,
      "loss": 1.2793,
      "step": 49
    },
    {
      "epoch": 0.21208907741251326,
      "grad_norm": 29.9601993560791,
      "learning_rate": 4.058724504646834e-06,
      "loss": 1.4011,
      "step": 50
    },
    {
      "epoch": 0.21208907741251326,
      "eval_loss": 0.8299828171730042,
      "eval_runtime": 8.0354,
      "eval_samples_per_second": 49.406,
      "eval_steps_per_second": 6.222,
      "step": 50
    },
    {
      "epoch": 0.2163308589607635,
      "grad_norm": 1.2941735982894897,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.2063,
      "step": 51
    },
    {
      "epoch": 0.2205726405090138,
      "grad_norm": 1.8185893297195435,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 0.2909,
      "step": 52
    },
    {
      "epoch": 0.22481442205726404,
      "grad_norm": 2.4603350162506104,
      "learning_rate": 3.782248193514766e-06,
      "loss": 0.297,
      "step": 53
    },
    {
      "epoch": 0.22905620360551432,
      "grad_norm": 2.465657949447632,
      "learning_rate": 3.684671656182497e-06,
      "loss": 0.3119,
      "step": 54
    },
    {
      "epoch": 0.23329798515376457,
      "grad_norm": 2.5236356258392334,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 0.2771,
      "step": 55
    },
    {
      "epoch": 0.23753976670201485,
      "grad_norm": 3.519874095916748,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 0.3052,
      "step": 56
    },
    {
      "epoch": 0.2417815482502651,
      "grad_norm": 2.217327356338501,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 0.2883,
      "step": 57
    },
    {
      "epoch": 0.24602332979851538,
      "grad_norm": 2.3429453372955322,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.3006,
      "step": 58
    },
    {
      "epoch": 0.25026511134676566,
      "grad_norm": 3.1694295406341553,
      "learning_rate": 3.165092113916688e-06,
      "loss": 0.3607,
      "step": 59
    },
    {
      "epoch": 0.2545068928950159,
      "grad_norm": 2.1960690021514893,
      "learning_rate": 3.056302334890786e-06,
      "loss": 0.2782,
      "step": 60
    },
    {
      "epoch": 0.25874867444326616,
      "grad_norm": 2.5143775939941406,
      "learning_rate": 2.946392236996592e-06,
      "loss": 0.327,
      "step": 61
    },
    {
      "epoch": 0.26299045599151644,
      "grad_norm": 2.0972142219543457,
      "learning_rate": 2.835583164544139e-06,
      "loss": 0.2211,
      "step": 62
    },
    {
      "epoch": 0.2672322375397667,
      "grad_norm": 1.8701742887496948,
      "learning_rate": 2.724098272258584e-06,
      "loss": 0.2287,
      "step": 63
    },
    {
      "epoch": 0.271474019088017,
      "grad_norm": 2.386495351791382,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 0.2951,
      "step": 64
    },
    {
      "epoch": 0.2757158006362672,
      "grad_norm": 2.3010129928588867,
      "learning_rate": 2.5e-06,
      "loss": 0.2169,
      "step": 65
    },
    {
      "epoch": 0.2799575821845175,
      "grad_norm": 2.422025442123413,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 0.2676,
      "step": 66
    },
    {
      "epoch": 0.2841993637327678,
      "grad_norm": 2.306940793991089,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 0.2568,
      "step": 67
    },
    {
      "epoch": 0.28844114528101805,
      "grad_norm": 2.8453123569488525,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 0.3003,
      "step": 68
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 3.1190452575683594,
      "learning_rate": 2.053607763003409e-06,
      "loss": 0.3167,
      "step": 69
    },
    {
      "epoch": 0.29692470837751855,
      "grad_norm": 4.037975788116455,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 0.4344,
      "step": 70
    },
    {
      "epoch": 0.30116648992576883,
      "grad_norm": 4.7273454666137695,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 0.4892,
      "step": 71
    },
    {
      "epoch": 0.3054082714740191,
      "grad_norm": 8.596299171447754,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.7955,
      "step": 72
    },
    {
      "epoch": 0.30965005302226933,
      "grad_norm": 6.555408954620361,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 0.7031,
      "step": 73
    },
    {
      "epoch": 0.3138918345705196,
      "grad_norm": 7.657025337219238,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 0.6821,
      "step": 74
    },
    {
      "epoch": 0.3181336161187699,
      "grad_norm": 7.3240227699279785,
      "learning_rate": 1.415290652206105e-06,
      "loss": 0.7677,
      "step": 75
    },
    {
      "epoch": 0.32237539766702017,
      "grad_norm": 9.968438148498535,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 0.6359,
      "step": 76
    },
    {
      "epoch": 0.3266171792152704,
      "grad_norm": 7.8202338218688965,
      "learning_rate": 1.217751806485235e-06,
      "loss": 0.6877,
      "step": 77
    },
    {
      "epoch": 0.33085896076352067,
      "grad_norm": 7.387623310089111,
      "learning_rate": 1.122757546369744e-06,
      "loss": 0.6521,
      "step": 78
    },
    {
      "epoch": 0.33510074231177095,
      "grad_norm": 8.559468269348145,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.7261,
      "step": 79
    },
    {
      "epoch": 0.33934252386002123,
      "grad_norm": 7.285356044769287,
      "learning_rate": 9.412754953531664e-07,
      "loss": 0.6358,
      "step": 80
    },
    {
      "epoch": 0.34358430540827145,
      "grad_norm": 9.018921852111816,
      "learning_rate": 8.551531851507186e-07,
      "loss": 0.6657,
      "step": 81
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 5.554042816162109,
      "learning_rate": 7.723433775328385e-07,
      "loss": 0.5567,
      "step": 82
    },
    {
      "epoch": 0.352067868504772,
      "grad_norm": 11.054597854614258,
      "learning_rate": 6.930128404315214e-07,
      "loss": 0.8462,
      "step": 83
    },
    {
      "epoch": 0.3563096500530223,
      "grad_norm": 6.244119644165039,
      "learning_rate": 6.17321334990973e-07,
      "loss": 0.6058,
      "step": 84
    },
    {
      "epoch": 0.3605514316012725,
      "grad_norm": 10.842486381530762,
      "learning_rate": 5.454212938299256e-07,
      "loss": 0.7793,
      "step": 85
    },
    {
      "epoch": 0.3647932131495228,
      "grad_norm": 7.651045322418213,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.5938,
      "step": 86
    },
    {
      "epoch": 0.36903499469777307,
      "grad_norm": 10.755373001098633,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 0.6908,
      "step": 87
    },
    {
      "epoch": 0.37327677624602335,
      "grad_norm": 8.134658813476562,
      "learning_rate": 3.538780159953348e-07,
      "loss": 0.7198,
      "step": 88
    },
    {
      "epoch": 0.37751855779427357,
      "grad_norm": 8.481114387512207,
      "learning_rate": 2.98511170358155e-07,
      "loss": 0.7024,
      "step": 89
    },
    {
      "epoch": 0.38176033934252385,
      "grad_norm": 9.80128288269043,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 0.6167,
      "step": 90
    },
    {
      "epoch": 0.3860021208907741,
      "grad_norm": 11.155387878417969,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 0.8483,
      "step": 91
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 7.825685501098633,
      "learning_rate": 1.59412823400657e-07,
      "loss": 0.6448,
      "step": 92
    },
    {
      "epoch": 0.3944856839872747,
      "grad_norm": 7.912622928619385,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.6102,
      "step": 93
    },
    {
      "epoch": 0.3987274655355249,
      "grad_norm": 11.073833465576172,
      "learning_rate": 9.00928482603669e-08,
      "loss": 0.562,
      "step": 94
    },
    {
      "epoch": 0.4029692470837752,
      "grad_norm": 7.491645336151123,
      "learning_rate": 6.268021954544095e-08,
      "loss": 0.4042,
      "step": 95
    },
    {
      "epoch": 0.40721102863202546,
      "grad_norm": 9.142674446105957,
      "learning_rate": 4.017602850342584e-08,
      "loss": 0.4681,
      "step": 96
    },
    {
      "epoch": 0.41145281018027574,
      "grad_norm": 15.355952262878418,
      "learning_rate": 2.262559558016325e-08,
      "loss": 0.7407,
      "step": 97
    },
    {
      "epoch": 0.41569459172852596,
      "grad_norm": 13.96410083770752,
      "learning_rate": 1.006426501190233e-08,
      "loss": 0.5351,
      "step": 98
    },
    {
      "epoch": 0.41993637327677624,
      "grad_norm": 29.766155242919922,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 0.7461,
      "step": 99
    },
    {
      "epoch": 0.4241781548250265,
      "grad_norm": 28.113073348999023,
      "learning_rate": 0.0,
      "loss": 0.8913,
      "step": 100
    },
    {
      "epoch": 0.4241781548250265,
      "eval_loss": 0.42480990290641785,
      "eval_runtime": 8.0387,
      "eval_samples_per_second": 49.386,
      "eval_steps_per_second": 6.22,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.13314785247232e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}