{
  "best_metric": 0.18355341255664825,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.015958826228330905,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015958826228330906,
      "grad_norm": 43.736854553222656,
      "learning_rate": 5.000000000000001e-07,
      "loss": 12.1116,
      "step": 1
    },
    {
      "epoch": 0.00015958826228330906,
      "eval_loss": 12.323148727416992,
      "eval_runtime": 845.2945,
      "eval_samples_per_second": 12.486,
      "eval_steps_per_second": 3.122,
      "step": 1
    },
    {
      "epoch": 0.0003191765245666181,
      "grad_norm": 50.650611877441406,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 11.9574,
      "step": 2
    },
    {
      "epoch": 0.0004787647868499272,
      "grad_norm": 50.548484802246094,
      "learning_rate": 1.5e-06,
      "loss": 11.5063,
      "step": 3
    },
    {
      "epoch": 0.0006383530491332362,
      "grad_norm": 50.47951126098633,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 11.9538,
      "step": 4
    },
    {
      "epoch": 0.0007979413114165454,
      "grad_norm": 50.52406311035156,
      "learning_rate": 2.5e-06,
      "loss": 12.166,
      "step": 5
    },
    {
      "epoch": 0.0009575295736998544,
      "grad_norm": 53.469520568847656,
      "learning_rate": 3e-06,
      "loss": 12.1688,
      "step": 6
    },
    {
      "epoch": 0.0011171178359831635,
      "grad_norm": 52.03275680541992,
      "learning_rate": 3.5e-06,
      "loss": 12.0868,
      "step": 7
    },
    {
      "epoch": 0.0012767060982664725,
      "grad_norm": 45.10970687866211,
      "learning_rate": 4.000000000000001e-06,
      "loss": 11.7541,
      "step": 8
    },
    {
      "epoch": 0.0014362943605497815,
      "grad_norm": 46.315494537353516,
      "learning_rate": 4.5e-06,
      "loss": 12.0005,
      "step": 9
    },
    {
      "epoch": 0.0015958826228330907,
      "grad_norm": 53.98945236206055,
      "learning_rate": 5e-06,
      "loss": 11.6276,
      "step": 10
    },
    {
      "epoch": 0.0017554708851163997,
      "grad_norm": 48.429481506347656,
      "learning_rate": 4.99847706754774e-06,
      "loss": 11.6075,
      "step": 11
    },
    {
      "epoch": 0.0019150591473997087,
      "grad_norm": 47.879478454589844,
      "learning_rate": 4.993910125649561e-06,
      "loss": 11.6263,
      "step": 12
    },
    {
      "epoch": 0.0020746474096830178,
      "grad_norm": 51.92265701293945,
      "learning_rate": 4.986304738420684e-06,
      "loss": 11.106,
      "step": 13
    },
    {
      "epoch": 0.002234235671966327,
      "grad_norm": 51.57489776611328,
      "learning_rate": 4.975670171853926e-06,
      "loss": 10.845,
      "step": 14
    },
    {
      "epoch": 0.0023938239342496358,
      "grad_norm": 50.46339416503906,
      "learning_rate": 4.962019382530521e-06,
      "loss": 10.5991,
      "step": 15
    },
    {
      "epoch": 0.002553412196532945,
      "grad_norm": 49.37790298461914,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 9.8602,
      "step": 16
    },
    {
      "epoch": 0.0027130004588162542,
      "grad_norm": 48.29505157470703,
      "learning_rate": 4.925739315689991e-06,
      "loss": 9.8981,
      "step": 17
    },
    {
      "epoch": 0.002872588721099563,
      "grad_norm": 50.35626983642578,
      "learning_rate": 4.903154239845798e-06,
      "loss": 9.4826,
      "step": 18
    },
    {
      "epoch": 0.0030321769833828722,
      "grad_norm": 49.06550979614258,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 9.2918,
      "step": 19
    },
    {
      "epoch": 0.0031917652456661815,
      "grad_norm": 46.6195068359375,
      "learning_rate": 4.849231551964771e-06,
      "loss": 9.0255,
      "step": 20
    },
    {
      "epoch": 0.0033513535079494903,
      "grad_norm": 44.751346588134766,
      "learning_rate": 4.817959636416969e-06,
      "loss": 8.4435,
      "step": 21
    },
    {
      "epoch": 0.0035109417702327995,
      "grad_norm": 41.83870315551758,
      "learning_rate": 4.783863644106502e-06,
      "loss": 8.1362,
      "step": 22
    },
    {
      "epoch": 0.0036705300325161083,
      "grad_norm": 43.00385665893555,
      "learning_rate": 4.746985115747918e-06,
      "loss": 7.519,
      "step": 23
    },
    {
      "epoch": 0.0038301182947994175,
      "grad_norm": 45.05305099487305,
      "learning_rate": 4.707368982147318e-06,
      "loss": 7.0324,
      "step": 24
    },
    {
      "epoch": 0.003989706557082726,
      "grad_norm": 46.236839294433594,
      "learning_rate": 4.665063509461098e-06,
      "loss": 5.9956,
      "step": 25
    },
    {
      "epoch": 0.0041492948193660355,
      "grad_norm": 45.36016845703125,
      "learning_rate": 4.620120240391065e-06,
      "loss": 5.8249,
      "step": 26
    },
    {
      "epoch": 0.004308883081649345,
      "grad_norm": 46.748207092285156,
      "learning_rate": 4.572593931387604e-06,
      "loss": 5.1073,
      "step": 27
    },
    {
      "epoch": 0.004468471343932654,
      "grad_norm": 45.68260192871094,
      "learning_rate": 4.522542485937369e-06,
      "loss": 4.5708,
      "step": 28
    },
    {
      "epoch": 0.004628059606215963,
      "grad_norm": 46.5210075378418,
      "learning_rate": 4.470026884016805e-06,
      "loss": 4.391,
      "step": 29
    },
    {
      "epoch": 0.0047876478684992715,
      "grad_norm": 42.01366424560547,
      "learning_rate": 4.415111107797445e-06,
      "loss": 4.3002,
      "step": 30
    },
    {
      "epoch": 0.004947236130782581,
      "grad_norm": 43.48591613769531,
      "learning_rate": 4.357862063693486e-06,
      "loss": 3.8914,
      "step": 31
    },
    {
      "epoch": 0.00510682439306589,
      "grad_norm": 43.21699142456055,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 3.1507,
      "step": 32
    },
    {
      "epoch": 0.005266412655349199,
      "grad_norm": 41.28952407836914,
      "learning_rate": 4.236645926147493e-06,
      "loss": 2.0522,
      "step": 33
    },
    {
      "epoch": 0.0054260009176325084,
      "grad_norm": 36.86624526977539,
      "learning_rate": 4.172826515897146e-06,
      "loss": 2.1409,
      "step": 34
    },
    {
      "epoch": 0.005585589179915817,
      "grad_norm": 30.340343475341797,
      "learning_rate": 4.106969024216348e-06,
      "loss": 1.8715,
      "step": 35
    },
    {
      "epoch": 0.005745177442199126,
      "grad_norm": 24.695117950439453,
      "learning_rate": 4.039153688314146e-06,
      "loss": 1.0543,
      "step": 36
    },
    {
      "epoch": 0.005904765704482435,
      "grad_norm": 21.477252960205078,
      "learning_rate": 3.969463130731183e-06,
      "loss": 1.7806,
      "step": 37
    },
    {
      "epoch": 0.0060643539667657445,
      "grad_norm": 14.005023956298828,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.8706,
      "step": 38
    },
    {
      "epoch": 0.006223942229049054,
      "grad_norm": 12.730143547058105,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.688,
      "step": 39
    },
    {
      "epoch": 0.006383530491332363,
      "grad_norm": 9.65303897857666,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.9158,
      "step": 40
    },
    {
      "epoch": 0.006543118753615671,
      "grad_norm": 9.569194793701172,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 1.0299,
      "step": 41
    },
    {
      "epoch": 0.0067027070158989805,
      "grad_norm": 3.0408260822296143,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.3519,
      "step": 42
    },
    {
      "epoch": 0.00686229527818229,
      "grad_norm": 7.300391674041748,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.8792,
      "step": 43
    },
    {
      "epoch": 0.007021883540465599,
      "grad_norm": 8.536422729492188,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.354,
      "step": 44
    },
    {
      "epoch": 0.007181471802748908,
      "grad_norm": 7.12312126159668,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.6326,
      "step": 45
    },
    {
      "epoch": 0.0073410600650322165,
      "grad_norm": 19.750776290893555,
      "learning_rate": 3.272542485937369e-06,
      "loss": 1.8694,
      "step": 46
    },
    {
      "epoch": 0.007500648327315526,
      "grad_norm": 15.625970840454102,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.8438,
      "step": 47
    },
    {
      "epoch": 0.007660236589598835,
      "grad_norm": 8.163710594177246,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.1959,
      "step": 48
    },
    {
      "epoch": 0.007819824851882144,
      "grad_norm": 10.990124702453613,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.6136,
      "step": 49
    },
    {
      "epoch": 0.007979413114165453,
      "grad_norm": 12.102945327758789,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.5843,
      "step": 50
    },
    {
      "epoch": 0.007979413114165453,
      "eval_loss": 0.5140388607978821,
      "eval_runtime": 847.4177,
      "eval_samples_per_second": 12.454,
      "eval_steps_per_second": 3.114,
      "step": 50
    },
    {
      "epoch": 0.008139001376448763,
      "grad_norm": 7.3725104331970215,
      "learning_rate": 2.847932752400164e-06,
      "loss": 1.0074,
      "step": 51
    },
    {
      "epoch": 0.008298589638732071,
      "grad_norm": 7.9290900230407715,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.4143,
      "step": 52
    },
    {
      "epoch": 0.008458177901015381,
      "grad_norm": 16.212963104248047,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.6425,
      "step": 53
    },
    {
      "epoch": 0.00861776616329869,
      "grad_norm": 7.862034320831299,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.3512,
      "step": 54
    },
    {
      "epoch": 0.008777354425581998,
      "grad_norm": 3.113178253173828,
      "learning_rate": 2.5e-06,
      "loss": 0.1114,
      "step": 55
    },
    {
      "epoch": 0.008936942687865308,
      "grad_norm": 8.0140380859375,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.4566,
      "step": 56
    },
    {
      "epoch": 0.009096530950148616,
      "grad_norm": 11.397700309753418,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.6353,
      "step": 57
    },
    {
      "epoch": 0.009256119212431926,
      "grad_norm": 0.06368193030357361,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.001,
      "step": 58
    },
    {
      "epoch": 0.009415707474715235,
      "grad_norm": 4.552347183227539,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.2425,
      "step": 59
    },
    {
      "epoch": 0.009575295736998543,
      "grad_norm": 4.318637847900391,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.2014,
      "step": 60
    },
    {
      "epoch": 0.009734883999281853,
      "grad_norm": 2.7980666160583496,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.1012,
      "step": 61
    },
    {
      "epoch": 0.009894472261565162,
      "grad_norm": 2.5013349056243896,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0972,
      "step": 62
    },
    {
      "epoch": 0.010054060523848472,
      "grad_norm": 2.51824688911438,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.1209,
      "step": 63
    },
    {
      "epoch": 0.01021364878613178,
      "grad_norm": 4.979506492614746,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.2335,
      "step": 64
    },
    {
      "epoch": 0.010373237048415088,
      "grad_norm": 0.3189781904220581,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0033,
      "step": 65
    },
    {
      "epoch": 0.010532825310698398,
      "grad_norm": 13.277030944824219,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.3517,
      "step": 66
    },
    {
      "epoch": 0.010692413572981707,
      "grad_norm": 5.3693084716796875,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.1901,
      "step": 67
    },
    {
      "epoch": 0.010852001835265017,
      "grad_norm": 0.6272711157798767,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.006,
      "step": 68
    },
    {
      "epoch": 0.011011590097548325,
      "grad_norm": 9.435708045959473,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.2644,
      "step": 69
    },
    {
      "epoch": 0.011171178359831634,
      "grad_norm": 4.341763496398926,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.1834,
      "step": 70
    },
    {
      "epoch": 0.011330766622114944,
      "grad_norm": 9.02403450012207,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.4484,
      "step": 71
    },
    {
      "epoch": 0.011490354884398252,
      "grad_norm": 4.708563327789307,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.107,
      "step": 72
    },
    {
      "epoch": 0.011649943146681562,
      "grad_norm": 1.80886709690094,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0173,
      "step": 73
    },
    {
      "epoch": 0.01180953140896487,
      "grad_norm": 1.6764700412750244,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0171,
      "step": 74
    },
    {
      "epoch": 0.011969119671248179,
      "grad_norm": 2.3282880783081055,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0509,
      "step": 75
    },
    {
      "epoch": 0.012128707933531489,
      "grad_norm": 3.2590067386627197,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.1197,
      "step": 76
    },
    {
      "epoch": 0.012288296195814797,
      "grad_norm": 1.3154736757278442,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0891,
      "step": 77
    },
    {
      "epoch": 0.012447884458098107,
      "grad_norm": 2.3927087783813477,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0256,
      "step": 78
    },
    {
      "epoch": 0.012607472720381416,
      "grad_norm": 1.8653408288955688,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.1032,
      "step": 79
    },
    {
      "epoch": 0.012767060982664726,
      "grad_norm": 1.5105987787246704,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0666,
      "step": 80
    },
    {
      "epoch": 0.012926649244948034,
      "grad_norm": 7.518610000610352,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.2022,
      "step": 81
    },
    {
      "epoch": 0.013086237507231343,
      "grad_norm": 2.9338836669921875,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0967,
      "step": 82
    },
    {
      "epoch": 0.013245825769514653,
      "grad_norm": 1.571068525314331,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0741,
      "step": 83
    },
    {
      "epoch": 0.013405414031797961,
      "grad_norm": 8.719659805297852,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.2685,
      "step": 84
    },
    {
      "epoch": 0.013565002294081271,
      "grad_norm": 2.258552312850952,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.051,
      "step": 85
    },
    {
      "epoch": 0.01372459055636458,
      "grad_norm": 1.2262955904006958,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0505,
      "step": 86
    },
    {
      "epoch": 0.013884178818647888,
      "grad_norm": 3.613511323928833,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.2141,
      "step": 87
    },
    {
      "epoch": 0.014043767080931198,
      "grad_norm": 6.448750972747803,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.3561,
      "step": 88
    },
    {
      "epoch": 0.014203355343214506,
      "grad_norm": 6.130068302154541,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.2403,
      "step": 89
    },
    {
      "epoch": 0.014362943605497816,
      "grad_norm": 7.4299211502075195,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.3328,
      "step": 90
    },
    {
      "epoch": 0.014522531867781125,
      "grad_norm": 6.2848381996154785,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.2196,
      "step": 91
    },
    {
      "epoch": 0.014682120130064433,
      "grad_norm": 5.241060256958008,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.2432,
      "step": 92
    },
    {
      "epoch": 0.014841708392347743,
      "grad_norm": 8.220368385314941,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.2829,
      "step": 93
    },
    {
      "epoch": 0.015001296654631052,
      "grad_norm": 4.223203182220459,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.1818,
      "step": 94
    },
    {
      "epoch": 0.015160884916914362,
      "grad_norm": 3.850449562072754,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.1388,
      "step": 95
    },
    {
      "epoch": 0.01532047317919767,
      "grad_norm": 5.5809760093688965,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.2356,
      "step": 96
    },
    {
      "epoch": 0.015480061441480978,
      "grad_norm": 4.3721795082092285,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0995,
      "step": 97
    },
    {
      "epoch": 0.01563964970376429,
      "grad_norm": 5.354106426239014,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.1928,
      "step": 98
    },
    {
      "epoch": 0.015799237966047597,
      "grad_norm": 4.162508010864258,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.1439,
      "step": 99
    },
    {
      "epoch": 0.015958826228330905,
      "grad_norm": 5.800200939178467,
      "learning_rate": 0.0,
      "loss": 0.2004,
      "step": 100
    },
    {
      "epoch": 0.015958826228330905,
      "eval_loss": 0.18355341255664825,
      "eval_runtime": 847.1818,
      "eval_samples_per_second": 12.458,
      "eval_steps_per_second": 3.115,
      "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": 1.4874840035386982e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}