{
  "best_metric": 1.6244957447052002,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.2222645825390774,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012199771254288982,
      "grad_norm": 1.166663646697998,
      "learning_rate": 2e-05,
      "loss": 4.5306,
      "step": 1
    },
    {
      "epoch": 0.012199771254288982,
      "eval_loss": 6.460769176483154,
      "eval_runtime": 1.4227,
      "eval_samples_per_second": 35.143,
      "eval_steps_per_second": 9.137,
      "step": 1
    },
    {
      "epoch": 0.024399542508577964,
      "grad_norm": 1.2659770250320435,
      "learning_rate": 4e-05,
      "loss": 4.8882,
      "step": 2
    },
    {
      "epoch": 0.036599313762866945,
      "grad_norm": 1.2624318599700928,
      "learning_rate": 6e-05,
      "loss": 5.0064,
      "step": 3
    },
    {
      "epoch": 0.04879908501715593,
      "grad_norm": 1.5363656282424927,
      "learning_rate": 8e-05,
      "loss": 5.3547,
      "step": 4
    },
    {
      "epoch": 0.06099885627144491,
      "grad_norm": 1.9164278507232666,
      "learning_rate": 0.0001,
      "loss": 5.0749,
      "step": 5
    },
    {
      "epoch": 0.07319862752573389,
      "grad_norm": 2.4485414028167725,
      "learning_rate": 9.997539658034168e-05,
      "loss": 5.2012,
      "step": 6
    },
    {
      "epoch": 0.08539839878002288,
      "grad_norm": 2.5348973274230957,
      "learning_rate": 9.990161322484486e-05,
      "loss": 4.5183,
      "step": 7
    },
    {
      "epoch": 0.09759817003431186,
      "grad_norm": 1.8544416427612305,
      "learning_rate": 9.977873061452552e-05,
      "loss": 4.0716,
      "step": 8
    },
    {
      "epoch": 0.10979794128860083,
      "grad_norm": 1.933067798614502,
      "learning_rate": 9.96068831197139e-05,
      "loss": 3.8384,
      "step": 9
    },
    {
      "epoch": 0.12199771254288982,
      "grad_norm": 2.36763072013855,
      "learning_rate": 9.938625865312251e-05,
      "loss": 3.4286,
      "step": 10
    },
    {
      "epoch": 0.1341974837971788,
      "grad_norm": 2.299260139465332,
      "learning_rate": 9.911709846436641e-05,
      "loss": 3.4454,
      "step": 11
    },
    {
      "epoch": 0.14639725505146778,
      "grad_norm": 3.964050531387329,
      "learning_rate": 9.879969687616027e-05,
      "loss": 3.7988,
      "step": 12
    },
    {
      "epoch": 0.15859702630575676,
      "grad_norm": 24.955421447753906,
      "learning_rate": 9.84344009624807e-05,
      "loss": 4.0564,
      "step": 13
    },
    {
      "epoch": 0.17079679756004576,
      "grad_norm": 4.6906256675720215,
      "learning_rate": 9.80216101690461e-05,
      "loss": 3.9187,
      "step": 14
    },
    {
      "epoch": 0.18299656881433474,
      "grad_norm": 4.218716144561768,
      "learning_rate": 9.756177587652856e-05,
      "loss": 3.6779,
      "step": 15
    },
    {
      "epoch": 0.1951963400686237,
      "grad_norm": 2.8284833431243896,
      "learning_rate": 9.705540090697575e-05,
      "loss": 3.3503,
      "step": 16
    },
    {
      "epoch": 0.2073961113229127,
      "grad_norm": 1.921479344367981,
      "learning_rate": 9.650303897398232e-05,
      "loss": 3.0593,
      "step": 17
    },
    {
      "epoch": 0.21959588257720167,
      "grad_norm": 1.7184988260269165,
      "learning_rate": 9.590529407721231e-05,
      "loss": 2.761,
      "step": 18
    },
    {
      "epoch": 0.23179565383149067,
      "grad_norm": 1.6135209798812866,
      "learning_rate": 9.526281984193436e-05,
      "loss": 2.6214,
      "step": 19
    },
    {
      "epoch": 0.24399542508577965,
      "grad_norm": 1.5472686290740967,
      "learning_rate": 9.4576318804292e-05,
      "loss": 2.594,
      "step": 20
    },
    {
      "epoch": 0.2561951963400686,
      "grad_norm": 1.5360417366027832,
      "learning_rate": 9.384654164309083e-05,
      "loss": 2.4474,
      "step": 21
    },
    {
      "epoch": 0.2683949675943576,
      "grad_norm": 1.5541893243789673,
      "learning_rate": 9.30742863589421e-05,
      "loss": 2.4182,
      "step": 22
    },
    {
      "epoch": 0.2805947388486466,
      "grad_norm": 1.6636126041412354,
      "learning_rate": 9.226039740166091e-05,
      "loss": 2.4277,
      "step": 23
    },
    {
      "epoch": 0.29279451010293556,
      "grad_norm": 1.7966293096542358,
      "learning_rate": 9.140576474687264e-05,
      "loss": 2.0648,
      "step": 24
    },
    {
      "epoch": 0.30499428135722456,
      "grad_norm": 4.8820672035217285,
      "learning_rate": 9.051132292283771e-05,
      "loss": 3.1713,
      "step": 25
    },
    {
      "epoch": 0.30499428135722456,
      "eval_loss": 2.542313575744629,
      "eval_runtime": 1.4246,
      "eval_samples_per_second": 35.097,
      "eval_steps_per_second": 9.125,
      "step": 25
    },
    {
      "epoch": 0.3171940526115135,
      "grad_norm": 1.8686131238937378,
      "learning_rate": 8.957804998855866e-05,
      "loss": 2.8531,
      "step": 26
    },
    {
      "epoch": 0.3293938238658025,
      "grad_norm": 1.7385876178741455,
      "learning_rate": 8.860696646428693e-05,
      "loss": 2.5454,
      "step": 27
    },
    {
      "epoch": 0.3415935951200915,
      "grad_norm": 1.7900599241256714,
      "learning_rate": 8.759913421559902e-05,
      "loss": 2.5226,
      "step": 28
    },
    {
      "epoch": 0.35379336637438047,
      "grad_norm": 1.4970581531524658,
      "learning_rate": 8.655565529226198e-05,
      "loss": 2.4534,
      "step": 29
    },
    {
      "epoch": 0.3659931376286695,
      "grad_norm": 1.2886368036270142,
      "learning_rate": 8.547767072315835e-05,
      "loss": 2.5245,
      "step": 30
    },
    {
      "epoch": 0.3781929088829584,
      "grad_norm": 1.2083213329315186,
      "learning_rate": 8.436635926858759e-05,
      "loss": 2.2635,
      "step": 31
    },
    {
      "epoch": 0.3903926801372474,
      "grad_norm": 1.313252568244934,
      "learning_rate": 8.322293613130917e-05,
      "loss": 2.3535,
      "step": 32
    },
    {
      "epoch": 0.40259245139153643,
      "grad_norm": 1.2841317653656006,
      "learning_rate": 8.204865162773613e-05,
      "loss": 2.0969,
      "step": 33
    },
    {
      "epoch": 0.4147922226458254,
      "grad_norm": 1.1799100637435913,
      "learning_rate": 8.084478982073247e-05,
      "loss": 1.8932,
      "step": 34
    },
    {
      "epoch": 0.4269919939001144,
      "grad_norm": 1.2775781154632568,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.7545,
      "step": 35
    },
    {
      "epoch": 0.43919176515440334,
      "grad_norm": 1.2880523204803467,
      "learning_rate": 7.835363082015468e-05,
      "loss": 1.8372,
      "step": 36
    },
    {
      "epoch": 0.45139153640869234,
      "grad_norm": 1.8644667863845825,
      "learning_rate": 7.706905767237288e-05,
      "loss": 1.519,
      "step": 37
    },
    {
      "epoch": 0.46359130766298134,
      "grad_norm": 1.275475263595581,
      "learning_rate": 7.576035233404096e-05,
      "loss": 2.5758,
      "step": 38
    },
    {
      "epoch": 0.4757910789172703,
      "grad_norm": 1.141963005065918,
      "learning_rate": 7.442894585523218e-05,
      "loss": 2.2862,
      "step": 39
    },
    {
      "epoch": 0.4879908501715593,
      "grad_norm": 2.4439399242401123,
      "learning_rate": 7.307629410938363e-05,
      "loss": 2.2467,
      "step": 40
    },
    {
      "epoch": 0.5001906214258482,
      "grad_norm": 1.0179998874664307,
      "learning_rate": 7.170387620131993e-05,
      "loss": 2.1335,
      "step": 41
    },
    {
      "epoch": 0.5123903926801372,
      "grad_norm": 1.028515338897705,
      "learning_rate": 7.031319284987394e-05,
      "loss": 2.1921,
      "step": 42
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 1.0229268074035645,
      "learning_rate": 6.890576474687263e-05,
      "loss": 1.9296,
      "step": 43
    },
    {
      "epoch": 0.5367899351887152,
      "grad_norm": 1.2306512594223022,
      "learning_rate": 6.7483130894283e-05,
      "loss": 2.0865,
      "step": 44
    },
    {
      "epoch": 0.5489897064430042,
      "grad_norm": 1.0769721269607544,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.8478,
      "step": 45
    },
    {
      "epoch": 0.5611894776972932,
      "grad_norm": 1.1530402898788452,
      "learning_rate": 6.459848338346861e-05,
      "loss": 1.9323,
      "step": 46
    },
    {
      "epoch": 0.5733892489515822,
      "grad_norm": 1.2950838804244995,
      "learning_rate": 6.313962404494496e-05,
      "loss": 1.712,
      "step": 47
    },
    {
      "epoch": 0.5855890202058711,
      "grad_norm": 1.328357219696045,
      "learning_rate": 6.167186414703289e-05,
      "loss": 1.6647,
      "step": 48
    },
    {
      "epoch": 0.5977887914601602,
      "grad_norm": 1.59043550491333,
      "learning_rate": 6.019680866363139e-05,
      "loss": 1.2337,
      "step": 49
    },
    {
      "epoch": 0.6099885627144491,
      "grad_norm": 4.231207847595215,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 1.9481,
      "step": 50
    },
    {
      "epoch": 0.6099885627144491,
      "eval_loss": 1.9504194259643555,
      "eval_runtime": 1.4224,
      "eval_samples_per_second": 35.151,
      "eval_steps_per_second": 9.139,
      "step": 50
    },
    {
      "epoch": 0.6221883339687381,
      "grad_norm": 0.9663915634155273,
      "learning_rate": 5.7231268960295e-05,
      "loss": 2.1974,
      "step": 51
    },
    {
      "epoch": 0.634388105223027,
      "grad_norm": 0.9641888737678528,
      "learning_rate": 5.574402751448614e-05,
      "loss": 2.1838,
      "step": 52
    },
    {
      "epoch": 0.6465878764773161,
      "grad_norm": 0.9429617524147034,
      "learning_rate": 5.425597248551387e-05,
      "loss": 2.0881,
      "step": 53
    },
    {
      "epoch": 0.658787647731605,
      "grad_norm": 1.0586568117141724,
      "learning_rate": 5.2768731039705e-05,
      "loss": 2.0872,
      "step": 54
    },
    {
      "epoch": 0.670987418985894,
      "grad_norm": 1.1340885162353516,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.8281,
      "step": 55
    },
    {
      "epoch": 0.683187190240183,
      "grad_norm": 1.0865514278411865,
      "learning_rate": 4.980319133636863e-05,
      "loss": 1.7659,
      "step": 56
    },
    {
      "epoch": 0.695386961494472,
      "grad_norm": 1.1755565404891968,
      "learning_rate": 4.83281358529671e-05,
      "loss": 1.8385,
      "step": 57
    },
    {
      "epoch": 0.7075867327487609,
      "grad_norm": 1.297876238822937,
      "learning_rate": 4.686037595505507e-05,
      "loss": 1.9225,
      "step": 58
    },
    {
      "epoch": 0.7197865040030499,
      "grad_norm": 1.1662304401397705,
      "learning_rate": 4.54015166165314e-05,
      "loss": 1.6643,
      "step": 59
    },
    {
      "epoch": 0.731986275257339,
      "grad_norm": 1.3199200630187988,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.5546,
      "step": 60
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 1.5923489332199097,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 1.3895,
      "step": 61
    },
    {
      "epoch": 0.7563858177659168,
      "grad_norm": 2.492323398590088,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.2338,
      "step": 62
    },
    {
      "epoch": 0.7685855890202059,
      "grad_norm": 1.8413420915603638,
      "learning_rate": 3.968680715012606e-05,
      "loss": 2.0796,
      "step": 63
    },
    {
      "epoch": 0.7807853602744949,
      "grad_norm": 0.9823299050331116,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.9643,
      "step": 64
    },
    {
      "epoch": 0.7929851315287838,
      "grad_norm": 1.094659686088562,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.9729,
      "step": 65
    },
    {
      "epoch": 0.8051849027830729,
      "grad_norm": 1.1028552055358887,
      "learning_rate": 3.557105414476782e-05,
      "loss": 1.9267,
      "step": 66
    },
    {
      "epoch": 0.8173846740373618,
      "grad_norm": 1.0977410078048706,
      "learning_rate": 3.423964766595906e-05,
      "loss": 1.7912,
      "step": 67
    },
    {
      "epoch": 0.8295844452916508,
      "grad_norm": 1.102168083190918,
      "learning_rate": 3.293094232762715e-05,
      "loss": 1.7725,
      "step": 68
    },
    {
      "epoch": 0.8417842165459397,
      "grad_norm": 1.1367805004119873,
      "learning_rate": 3.164636917984534e-05,
      "loss": 1.8996,
      "step": 69
    },
    {
      "epoch": 0.8539839878002288,
      "grad_norm": 1.1765918731689453,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 1.6463,
      "step": 70
    },
    {
      "epoch": 0.8661837590545177,
      "grad_norm": 1.2325594425201416,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 1.572,
      "step": 71
    },
    {
      "epoch": 0.8783835303088067,
      "grad_norm": 1.403302550315857,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 1.6589,
      "step": 72
    },
    {
      "epoch": 0.8905833015630957,
      "grad_norm": 1.3870701789855957,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.5272,
      "step": 73
    },
    {
      "epoch": 0.9027830728173847,
      "grad_norm": 1.7309116125106812,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.2688,
      "step": 74
    },
    {
      "epoch": 0.9149828440716736,
      "grad_norm": 3.672463893890381,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.656,
      "step": 75
    },
    {
      "epoch": 0.9149828440716736,
      "eval_loss": 1.6713114976882935,
      "eval_runtime": 1.4237,
      "eval_samples_per_second": 35.12,
      "eval_steps_per_second": 9.131,
      "step": 75
    },
    {
      "epoch": 0.9271826153259627,
      "grad_norm": 1.0527911186218262,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 2.1647,
      "step": 76
    },
    {
      "epoch": 0.9393823865802516,
      "grad_norm": 1.0965566635131836,
      "learning_rate": 2.2400865784401e-05,
      "loss": 1.8203,
      "step": 77
    },
    {
      "epoch": 0.9515821578345406,
      "grad_norm": 1.1224842071533203,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 1.8365,
      "step": 78
    },
    {
      "epoch": 0.9637819290888295,
      "grad_norm": 1.083632469177246,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 1.5104,
      "step": 79
    },
    {
      "epoch": 0.9759817003431186,
      "grad_norm": 1.1941848993301392,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 1.4217,
      "step": 80
    },
    {
      "epoch": 0.9881814715974075,
      "grad_norm": 1.4089711904525757,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.4428,
      "step": 81
    },
    {
      "epoch": 1.0026686999618757,
      "grad_norm": 1.9810051918029785,
      "learning_rate": 1.77396025983391e-05,
      "loss": 1.5342,
      "step": 82
    },
    {
      "epoch": 1.0148684712161646,
      "grad_norm": 0.940060555934906,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 1.7435,
      "step": 83
    },
    {
      "epoch": 1.0270682424704536,
      "grad_norm": 1.0035717487335205,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 1.9253,
      "step": 84
    },
    {
      "epoch": 1.0392680137247428,
      "grad_norm": 1.069605827331543,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 1.7862,
      "step": 85
    },
    {
      "epoch": 1.0514677849790317,
      "grad_norm": 1.121212124824524,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 1.505,
      "step": 86
    },
    {
      "epoch": 1.0636675562333207,
      "grad_norm": 1.131169080734253,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 1.6766,
      "step": 87
    },
    {
      "epoch": 1.0758673274876096,
      "grad_norm": 1.1634432077407837,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 1.4677,
      "step": 88
    },
    {
      "epoch": 1.0880670987418986,
      "grad_norm": 1.1550370454788208,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 1.4571,
      "step": 89
    },
    {
      "epoch": 1.1002668699961875,
      "grad_norm": 1.2418510913848877,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 1.3787,
      "step": 90
    },
    {
      "epoch": 1.1124666412504765,
      "grad_norm": 1.244449496269226,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 1.3382,
      "step": 91
    },
    {
      "epoch": 1.1246664125047656,
      "grad_norm": 1.207255482673645,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 1.1813,
      "step": 92
    },
    {
      "epoch": 1.1368661837590546,
      "grad_norm": 1.613624930381775,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 1.3322,
      "step": 93
    },
    {
      "epoch": 1.1490659550133435,
      "grad_norm": 1.5924932956695557,
      "learning_rate": 1.088290153563358e-05,
      "loss": 0.7849,
      "step": 94
    },
    {
      "epoch": 1.1612657262676325,
      "grad_norm": 1.3866314888000488,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 2.1158,
      "step": 95
    },
    {
      "epoch": 1.1734654975219214,
      "grad_norm": 1.0334395170211792,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 1.7684,
      "step": 96
    },
    {
      "epoch": 1.1856652687762104,
      "grad_norm": 1.1649991273880005,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 1.8588,
      "step": 97
    },
    {
      "epoch": 1.1978650400304995,
      "grad_norm": 1.1444116830825806,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 1.7781,
      "step": 98
    },
    {
      "epoch": 1.2100648112847885,
      "grad_norm": 1.1716587543487549,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 1.5944,
      "step": 99
    },
    {
      "epoch": 1.2222645825390774,
      "grad_norm": 1.1668322086334229,
      "learning_rate": 1e-05,
      "loss": 1.5552,
      "step": 100
    },
    {
      "epoch": 1.2222645825390774,
      "eval_loss": 1.6244957447052002,
      "eval_runtime": 1.4265,
      "eval_samples_per_second": 35.051,
      "eval_steps_per_second": 9.113,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.1248115621298176e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}