{
  "best_metric": 0.733076810836792,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03545392098207361,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003545392098207361,
      "grad_norm": 4.848531246185303,
      "learning_rate": 2e-05,
      "loss": 5.0876,
      "step": 1
    },
    {
      "epoch": 0.0003545392098207361,
      "eval_loss": 6.216423511505127,
      "eval_runtime": 1.4346,
      "eval_samples_per_second": 34.853,
      "eval_steps_per_second": 9.062,
      "step": 1
    },
    {
      "epoch": 0.0007090784196414722,
      "grad_norm": 5.189554691314697,
      "learning_rate": 4e-05,
      "loss": 4.9835,
      "step": 2
    },
    {
      "epoch": 0.0010636176294622083,
      "grad_norm": 5.395487308502197,
      "learning_rate": 6e-05,
      "loss": 5.0002,
      "step": 3
    },
    {
      "epoch": 0.0014181568392829444,
      "grad_norm": 5.79182767868042,
      "learning_rate": 8e-05,
      "loss": 4.815,
      "step": 4
    },
    {
      "epoch": 0.0017726960491036806,
      "grad_norm": 5.924882411956787,
      "learning_rate": 0.0001,
      "loss": 3.5888,
      "step": 5
    },
    {
      "epoch": 0.0021272352589244165,
      "grad_norm": 5.22299861907959,
      "learning_rate": 9.997539658034168e-05,
      "loss": 2.5276,
      "step": 6
    },
    {
      "epoch": 0.002481774468745153,
      "grad_norm": 3.220250129699707,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.5851,
      "step": 7
    },
    {
      "epoch": 0.002836313678565889,
      "grad_norm": 1.6759289503097534,
      "learning_rate": 9.977873061452552e-05,
      "loss": 1.2539,
      "step": 8
    },
    {
      "epoch": 0.003190852888386625,
      "grad_norm": 1.6135218143463135,
      "learning_rate": 9.96068831197139e-05,
      "loss": 1.0919,
      "step": 9
    },
    {
      "epoch": 0.003545392098207361,
      "grad_norm": 1.962496042251587,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.8399,
      "step": 10
    },
    {
      "epoch": 0.003899931308028097,
      "grad_norm": 2.1563808917999268,
      "learning_rate": 9.911709846436641e-05,
      "loss": 0.7126,
      "step": 11
    },
    {
      "epoch": 0.004254470517848833,
      "grad_norm": 1.3578228950500488,
      "learning_rate": 9.879969687616027e-05,
      "loss": 0.7229,
      "step": 12
    },
    {
      "epoch": 0.004609009727669569,
      "grad_norm": 1.3786768913269043,
      "learning_rate": 9.84344009624807e-05,
      "loss": 0.8936,
      "step": 13
    },
    {
      "epoch": 0.004963548937490306,
      "grad_norm": 1.6054021120071411,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.1911,
      "step": 14
    },
    {
      "epoch": 0.005318088147311041,
      "grad_norm": 0.9699863791465759,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.0015,
      "step": 15
    },
    {
      "epoch": 0.005672627357131778,
      "grad_norm": 1.0598102807998657,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.1119,
      "step": 16
    },
    {
      "epoch": 0.006027166566952514,
      "grad_norm": 1.0990904569625854,
      "learning_rate": 9.650303897398232e-05,
      "loss": 0.8657,
      "step": 17
    },
    {
      "epoch": 0.00638170577677325,
      "grad_norm": 0.9300882816314697,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.8144,
      "step": 18
    },
    {
      "epoch": 0.006736244986593986,
      "grad_norm": 0.7585983276367188,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.7869,
      "step": 19
    },
    {
      "epoch": 0.007090784196414722,
      "grad_norm": 0.83787602186203,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.7916,
      "step": 20
    },
    {
      "epoch": 0.007445323406235459,
      "grad_norm": 0.7473427653312683,
      "learning_rate": 9.384654164309083e-05,
      "loss": 0.6681,
      "step": 21
    },
    {
      "epoch": 0.007799862616056194,
      "grad_norm": 0.5894711017608643,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.675,
      "step": 22
    },
    {
      "epoch": 0.008154401825876931,
      "grad_norm": 0.715570867061615,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.6853,
      "step": 23
    },
    {
      "epoch": 0.008508941035697666,
      "grad_norm": 0.6784505844116211,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.4911,
      "step": 24
    },
    {
      "epoch": 0.008863480245518402,
      "grad_norm": 0.7639828324317932,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.4635,
      "step": 25
    },
    {
      "epoch": 0.008863480245518402,
      "eval_loss": 0.7849562168121338,
      "eval_runtime": 1.4348,
      "eval_samples_per_second": 34.849,
      "eval_steps_per_second": 9.061,
      "step": 25
    },
    {
      "epoch": 0.009218019455339139,
      "grad_norm": 0.6689695119857788,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.0456,
      "step": 26
    },
    {
      "epoch": 0.009572558665159875,
      "grad_norm": 0.8705013990402222,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.0945,
      "step": 27
    },
    {
      "epoch": 0.009927097874980612,
      "grad_norm": 0.7108039259910583,
      "learning_rate": 8.759913421559902e-05,
      "loss": 1.0126,
      "step": 28
    },
    {
      "epoch": 0.010281637084801348,
      "grad_norm": 0.8193414211273193,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.9494,
      "step": 29
    },
    {
      "epoch": 0.010636176294622083,
      "grad_norm": 0.8473891019821167,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.7592,
      "step": 30
    },
    {
      "epoch": 0.010990715504442819,
      "grad_norm": 0.7946711182594299,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.7088,
      "step": 31
    },
    {
      "epoch": 0.011345254714263555,
      "grad_norm": 0.6517184972763062,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.6003,
      "step": 32
    },
    {
      "epoch": 0.011699793924084292,
      "grad_norm": 0.6414614915847778,
      "learning_rate": 8.204865162773613e-05,
      "loss": 0.7046,
      "step": 33
    },
    {
      "epoch": 0.012054333133905028,
      "grad_norm": 0.6361235976219177,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.5813,
      "step": 34
    },
    {
      "epoch": 0.012408872343725764,
      "grad_norm": 0.7114998698234558,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.4539,
      "step": 35
    },
    {
      "epoch": 0.0127634115535465,
      "grad_norm": 0.5631694793701172,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.4299,
      "step": 36
    },
    {
      "epoch": 0.013117950763367235,
      "grad_norm": 0.6165447235107422,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.3928,
      "step": 37
    },
    {
      "epoch": 0.013472489973187972,
      "grad_norm": 0.7139920592308044,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.7725,
      "step": 38
    },
    {
      "epoch": 0.013827029183008708,
      "grad_norm": 0.7106257081031799,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.9712,
      "step": 39
    },
    {
      "epoch": 0.014181568392829445,
      "grad_norm": 0.7304429411888123,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.8644,
      "step": 40
    },
    {
      "epoch": 0.014536107602650181,
      "grad_norm": 0.6472069025039673,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.7419,
      "step": 41
    },
    {
      "epoch": 0.014890646812470917,
      "grad_norm": 0.8418741822242737,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.7852,
      "step": 42
    },
    {
      "epoch": 0.015245186022291652,
      "grad_norm": 0.7708389759063721,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.6849,
      "step": 43
    },
    {
      "epoch": 0.015599725232112388,
      "grad_norm": 0.7205597758293152,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.6503,
      "step": 44
    },
    {
      "epoch": 0.015954264441933125,
      "grad_norm": 0.731856107711792,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.645,
      "step": 45
    },
    {
      "epoch": 0.016308803651753863,
      "grad_norm": 0.7058491110801697,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.5082,
      "step": 46
    },
    {
      "epoch": 0.016663342861574598,
      "grad_norm": 0.7743491530418396,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.5277,
      "step": 47
    },
    {
      "epoch": 0.017017882071395332,
      "grad_norm": 0.9558595418930054,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.5754,
      "step": 48
    },
    {
      "epoch": 0.01737242128121607,
      "grad_norm": 0.8757135272026062,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.5726,
      "step": 49
    },
    {
      "epoch": 0.017726960491036805,
      "grad_norm": 0.6394727230072021,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.3937,
      "step": 50
    },
    {
      "epoch": 0.017726960491036805,
      "eval_loss": 0.7727236747741699,
      "eval_runtime": 1.4316,
      "eval_samples_per_second": 34.927,
      "eval_steps_per_second": 9.081,
      "step": 50
    },
    {
      "epoch": 0.018081499700857543,
      "grad_norm": 0.724443793296814,
      "learning_rate": 5.7231268960295e-05,
      "loss": 0.9597,
      "step": 51
    },
    {
      "epoch": 0.018436038910678278,
      "grad_norm": 0.7282636761665344,
      "learning_rate": 5.574402751448614e-05,
      "loss": 0.9182,
      "step": 52
    },
    {
      "epoch": 0.018790578120499012,
      "grad_norm": 0.6671382188796997,
      "learning_rate": 5.425597248551387e-05,
      "loss": 0.7908,
      "step": 53
    },
    {
      "epoch": 0.01914511733031975,
      "grad_norm": 0.7780370116233826,
      "learning_rate": 5.2768731039705e-05,
      "loss": 0.8091,
      "step": 54
    },
    {
      "epoch": 0.019499656540140485,
      "grad_norm": 0.810192346572876,
      "learning_rate": 5.128392945374505e-05,
      "loss": 0.7749,
      "step": 55
    },
    {
      "epoch": 0.019854195749961223,
      "grad_norm": 0.7341954112052917,
      "learning_rate": 4.980319133636863e-05,
      "loss": 0.6715,
      "step": 56
    },
    {
      "epoch": 0.020208734959781958,
      "grad_norm": 0.7532359957695007,
      "learning_rate": 4.83281358529671e-05,
      "loss": 0.6982,
      "step": 57
    },
    {
      "epoch": 0.020563274169602696,
      "grad_norm": 0.7728514075279236,
      "learning_rate": 4.686037595505507e-05,
      "loss": 0.668,
      "step": 58
    },
    {
      "epoch": 0.02091781337942343,
      "grad_norm": 0.6659958958625793,
      "learning_rate": 4.54015166165314e-05,
      "loss": 0.5427,
      "step": 59
    },
    {
      "epoch": 0.021272352589244165,
      "grad_norm": 0.6720303893089294,
      "learning_rate": 4.395315307866405e-05,
      "loss": 0.466,
      "step": 60
    },
    {
      "epoch": 0.021626891799064903,
      "grad_norm": 0.6820637583732605,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 0.429,
      "step": 61
    },
    {
      "epoch": 0.021981431008885638,
      "grad_norm": 0.8596479892730713,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.4649,
      "step": 62
    },
    {
      "epoch": 0.022335970218706376,
      "grad_norm": 0.6639199256896973,
      "learning_rate": 3.968680715012606e-05,
      "loss": 0.5984,
      "step": 63
    },
    {
      "epoch": 0.02269050942852711,
      "grad_norm": 0.7899975180625916,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.0047,
      "step": 64
    },
    {
      "epoch": 0.02304504863834785,
      "grad_norm": 0.878670871257782,
      "learning_rate": 3.692370589061639e-05,
      "loss": 0.9028,
      "step": 65
    },
    {
      "epoch": 0.023399587848168583,
      "grad_norm": 1.0611952543258667,
      "learning_rate": 3.557105414476782e-05,
      "loss": 0.925,
      "step": 66
    },
    {
      "epoch": 0.023754127057989318,
      "grad_norm": 0.7318688631057739,
      "learning_rate": 3.423964766595906e-05,
      "loss": 0.7136,
      "step": 67
    },
    {
      "epoch": 0.024108666267810056,
      "grad_norm": 0.7990502715110779,
      "learning_rate": 3.293094232762715e-05,
      "loss": 0.6471,
      "step": 68
    },
    {
      "epoch": 0.02446320547763079,
      "grad_norm": 0.7018380761146545,
      "learning_rate": 3.164636917984534e-05,
      "loss": 0.7014,
      "step": 69
    },
    {
      "epoch": 0.02481774468745153,
      "grad_norm": 0.6606969833374023,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.6384,
      "step": 70
    },
    {
      "epoch": 0.025172283897272264,
      "grad_norm": 0.7007325291633606,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 0.4989,
      "step": 71
    },
    {
      "epoch": 0.025526823107093,
      "grad_norm": 0.7680234313011169,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 0.5995,
      "step": 72
    },
    {
      "epoch": 0.025881362316913736,
      "grad_norm": 0.712881326675415,
      "learning_rate": 2.677706386869083e-05,
      "loss": 0.4674,
      "step": 73
    },
    {
      "epoch": 0.02623590152673447,
      "grad_norm": 0.7732957005500793,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 0.5283,
      "step": 74
    },
    {
      "epoch": 0.02659044073655521,
      "grad_norm": 0.6836099028587341,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.3073,
      "step": 75
    },
    {
      "epoch": 0.02659044073655521,
      "eval_loss": 0.7449390292167664,
      "eval_runtime": 1.4311,
      "eval_samples_per_second": 34.938,
      "eval_steps_per_second": 9.084,
      "step": 75
    },
    {
      "epoch": 0.026944979946375944,
      "grad_norm": 0.6937525272369385,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 0.9399,
      "step": 76
    },
    {
      "epoch": 0.027299519156196682,
      "grad_norm": 0.7247990965843201,
      "learning_rate": 2.2400865784401e-05,
      "loss": 0.8895,
      "step": 77
    },
    {
      "epoch": 0.027654058366017416,
      "grad_norm": 0.6984252333641052,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 0.7613,
      "step": 78
    },
    {
      "epoch": 0.02800859757583815,
      "grad_norm": 0.6211410164833069,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 0.6435,
      "step": 79
    },
    {
      "epoch": 0.02836313678565889,
      "grad_norm": 0.7938443422317505,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.5725,
      "step": 80
    },
    {
      "epoch": 0.028717675995479624,
      "grad_norm": 0.6987906098365784,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.69,
      "step": 81
    },
    {
      "epoch": 0.029072215205300362,
      "grad_norm": 0.8338001370429993,
      "learning_rate": 1.77396025983391e-05,
      "loss": 0.7627,
      "step": 82
    },
    {
      "epoch": 0.029426754415121097,
      "grad_norm": 0.6527311205863953,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 0.5054,
      "step": 83
    },
    {
      "epoch": 0.029781293624941835,
      "grad_norm": 0.7132216691970825,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 0.5969,
      "step": 84
    },
    {
      "epoch": 0.03013583283476257,
      "grad_norm": 0.7264847159385681,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.5129,
      "step": 85
    },
    {
      "epoch": 0.030490372044583304,
      "grad_norm": 0.7762057781219482,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 0.4313,
      "step": 86
    },
    {
      "epoch": 0.030844911254404042,
      "grad_norm": 0.6852719187736511,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 0.4345,
      "step": 87
    },
    {
      "epoch": 0.031199450464224777,
      "grad_norm": 0.7660951018333435,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 0.724,
      "step": 88
    },
    {
      "epoch": 0.03155398967404551,
      "grad_norm": 0.7194827198982239,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 0.8667,
      "step": 89
    },
    {
      "epoch": 0.03190852888386625,
      "grad_norm": 0.7124308943748474,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 0.7907,
      "step": 90
    },
    {
      "epoch": 0.03226306809368699,
      "grad_norm": 0.8714865446090698,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 0.8492,
      "step": 91
    },
    {
      "epoch": 0.032617607303507726,
      "grad_norm": 0.757225513458252,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 0.742,
      "step": 92
    },
    {
      "epoch": 0.03297214651332846,
      "grad_norm": 0.754546046257019,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 0.6044,
      "step": 93
    },
    {
      "epoch": 0.033326685723149195,
      "grad_norm": 0.770008385181427,
      "learning_rate": 1.088290153563358e-05,
      "loss": 0.6478,
      "step": 94
    },
    {
      "epoch": 0.03368122493296993,
      "grad_norm": 0.8305578231811523,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 0.647,
      "step": 95
    },
    {
      "epoch": 0.034035764142790664,
      "grad_norm": 0.9594391584396362,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 0.6551,
      "step": 96
    },
    {
      "epoch": 0.0343903033526114,
      "grad_norm": 0.823460042476654,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 0.5407,
      "step": 97
    },
    {
      "epoch": 0.03474484256243214,
      "grad_norm": 0.8756825923919678,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 0.4781,
      "step": 98
    },
    {
      "epoch": 0.03509938177225287,
      "grad_norm": 0.7407690286636353,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 0.4027,
      "step": 99
    },
    {
      "epoch": 0.03545392098207361,
      "grad_norm": 0.6229119300842285,
      "learning_rate": 1e-05,
      "loss": 0.276,
      "step": 100
    },
    {
      "epoch": 0.03545392098207361,
      "eval_loss": 0.733076810836792,
      "eval_runtime": 1.4314,
      "eval_samples_per_second": 34.932,
      "eval_steps_per_second": 9.082,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.1249873143390536e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}