{
  "best_metric": 1.6871801614761353,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.9569377990430622,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 0.2898043692111969,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 1.2766,
      "step": 1
    },
    {
      "epoch": 0.009569377990430622,
      "eval_loss": 1.7112627029418945,
      "eval_runtime": 6.1955,
      "eval_samples_per_second": 28.569,
      "eval_steps_per_second": 3.712,
      "step": 1
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.34713202714920044,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 1.5539,
      "step": 2
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 0.3730577528476715,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.579,
      "step": 3
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.3811738193035126,
      "learning_rate": 6.666666666666667e-07,
      "loss": 1.4265,
      "step": 4
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 0.4220571517944336,
      "learning_rate": 8.333333333333333e-07,
      "loss": 1.4615,
      "step": 5
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 0.3910525441169739,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.4868,
      "step": 6
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 0.4316890835762024,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 1.4942,
      "step": 7
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 0.42238056659698486,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.3912,
      "step": 8
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 0.442205548286438,
      "learning_rate": 1.5e-06,
      "loss": 1.5868,
      "step": 9
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 0.449980229139328,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.4851,
      "step": 10
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.4727616608142853,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 1.4913,
      "step": 11
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 0.4863353371620178,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5382,
      "step": 12
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 0.5202990770339966,
      "learning_rate": 2.166666666666667e-06,
      "loss": 1.6332,
      "step": 13
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 0.5461772680282593,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 1.7509,
      "step": 14
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 0.5950157642364502,
      "learning_rate": 2.5e-06,
      "loss": 1.7086,
      "step": 15
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 0.6629598140716553,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.988,
      "step": 16
    },
    {
      "epoch": 0.16267942583732056,
      "grad_norm": 0.6870561242103577,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 1.7678,
      "step": 17
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 0.7218582034111023,
      "learning_rate": 3e-06,
      "loss": 1.9163,
      "step": 18
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.8249039649963379,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 2.0316,
      "step": 19
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 0.8442855477333069,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.9119,
      "step": 20
    },
    {
      "epoch": 0.20095693779904306,
      "grad_norm": 0.8914102911949158,
      "learning_rate": 3.5e-06,
      "loss": 1.9953,
      "step": 21
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.050236701965332,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 2.083,
      "step": 22
    },
    {
      "epoch": 0.22009569377990432,
      "grad_norm": 1.180810809135437,
      "learning_rate": 3.833333333333334e-06,
      "loss": 2.1334,
      "step": 23
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 1.5636886358261108,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.3595,
      "step": 24
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 2.270892381668091,
      "learning_rate": 4.166666666666667e-06,
      "loss": 2.3181,
      "step": 25
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 4.532635688781738,
      "learning_rate": 4.333333333333334e-06,
      "loss": 2.9364,
      "step": 26
    },
    {
      "epoch": 0.2583732057416268,
      "grad_norm": 0.31247401237487793,
      "learning_rate": 4.5e-06,
      "loss": 1.5535,
      "step": 27
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 0.3282526731491089,
      "learning_rate": 4.666666666666667e-06,
      "loss": 1.5298,
      "step": 28
    },
    {
      "epoch": 0.27751196172248804,
      "grad_norm": 0.3487168252468109,
      "learning_rate": 4.833333333333333e-06,
      "loss": 1.4726,
      "step": 29
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 0.3524574637413025,
      "learning_rate": 5e-06,
      "loss": 1.4867,
      "step": 30
    },
    {
      "epoch": 0.2966507177033493,
      "grad_norm": 0.38237130641937256,
      "learning_rate": 4.997482666353287e-06,
      "loss": 1.5526,
      "step": 31
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 0.3740280866622925,
      "learning_rate": 4.989935734988098e-06,
      "loss": 1.5824,
      "step": 32
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.384922057390213,
      "learning_rate": 4.977374404419838e-06,
      "loss": 1.484,
      "step": 33
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 0.39929136633872986,
      "learning_rate": 4.959823971496575e-06,
      "loss": 1.4441,
      "step": 34
    },
    {
      "epoch": 0.3349282296650718,
      "grad_norm": 0.4269602596759796,
      "learning_rate": 4.937319780454559e-06,
      "loss": 1.4605,
      "step": 35
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 0.42611387372016907,
      "learning_rate": 4.909907151739634e-06,
      "loss": 1.4582,
      "step": 36
    },
    {
      "epoch": 0.35406698564593303,
      "grad_norm": 0.44079849123954773,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 1.4773,
      "step": 37
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.45776522159576416,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 1.5388,
      "step": 38
    },
    {
      "epoch": 0.37320574162679426,
      "grad_norm": 0.490684449672699,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 1.5102,
      "step": 39
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 0.48765408992767334,
      "learning_rate": 4.752422169756048e-06,
      "loss": 1.4939,
      "step": 40
    },
    {
      "epoch": 0.3923444976076555,
      "grad_norm": 0.567180335521698,
      "learning_rate": 4.701488829641845e-06,
      "loss": 1.6571,
      "step": 41
    },
    {
      "epoch": 0.4019138755980861,
      "grad_norm": 0.5661348700523376,
      "learning_rate": 4.646121984004666e-06,
      "loss": 1.7493,
      "step": 42
    },
    {
      "epoch": 0.41148325358851673,
      "grad_norm": 0.6247003078460693,
      "learning_rate": 4.586433134303257e-06,
      "loss": 1.6714,
      "step": 43
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.6758706569671631,
      "learning_rate": 4.522542485937369e-06,
      "loss": 1.808,
      "step": 44
    },
    {
      "epoch": 0.430622009569378,
      "grad_norm": 0.7075497508049011,
      "learning_rate": 4.454578706170075e-06,
      "loss": 1.9295,
      "step": 45
    },
    {
      "epoch": 0.44019138755980863,
      "grad_norm": 0.7805354595184326,
      "learning_rate": 4.382678665009028e-06,
      "loss": 1.9702,
      "step": 46
    },
    {
      "epoch": 0.44976076555023925,
      "grad_norm": 0.7875988483428955,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 1.9085,
      "step": 47
    },
    {
      "epoch": 0.45933014354066987,
      "grad_norm": 0.9109578132629395,
      "learning_rate": 4.227656622467162e-06,
      "loss": 1.9608,
      "step": 48
    },
    {
      "epoch": 0.4688995215311005,
      "grad_norm": 1.0963773727416992,
      "learning_rate": 4.144846814849282e-06,
      "loss": 2.1041,
      "step": 49
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 1.3884176015853882,
      "learning_rate": 4.058724504646834e-06,
      "loss": 2.2791,
      "step": 50
    },
    {
      "epoch": 0.4784688995215311,
      "eval_loss": 1.6973111629486084,
      "eval_runtime": 5.7693,
      "eval_samples_per_second": 30.68,
      "eval_steps_per_second": 3.987,
      "step": 50
    },
    {
      "epoch": 0.4880382775119617,
      "grad_norm": 1.9222286939620972,
      "learning_rate": 3.969463130731183e-06,
      "loss": 2.2571,
      "step": 51
    },
    {
      "epoch": 0.49760765550239233,
      "grad_norm": 4.275127410888672,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 2.4938,
      "step": 52
    },
    {
      "epoch": 0.507177033492823,
      "grad_norm": 0.2680644392967224,
      "learning_rate": 3.782248193514766e-06,
      "loss": 1.3738,
      "step": 53
    },
    {
      "epoch": 0.5167464114832536,
      "grad_norm": 0.3094908893108368,
      "learning_rate": 3.684671656182497e-06,
      "loss": 1.6464,
      "step": 54
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.31784677505493164,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 1.4569,
      "step": 55
    },
    {
      "epoch": 0.5358851674641149,
      "grad_norm": 0.34948986768722534,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 1.3778,
      "step": 56
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.34939584136009216,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 1.4479,
      "step": 57
    },
    {
      "epoch": 0.5550239234449761,
      "grad_norm": 0.36129850149154663,
      "learning_rate": 3.272542485937369e-06,
      "loss": 1.4858,
      "step": 58
    },
    {
      "epoch": 0.5645933014354066,
      "grad_norm": 0.38175034523010254,
      "learning_rate": 3.165092113916688e-06,
      "loss": 1.5229,
      "step": 59
    },
    {
      "epoch": 0.5741626794258373,
      "grad_norm": 0.39641234278678894,
      "learning_rate": 3.056302334890786e-06,
      "loss": 1.5009,
      "step": 60
    },
    {
      "epoch": 0.583732057416268,
      "grad_norm": 0.40825703740119934,
      "learning_rate": 2.946392236996592e-06,
      "loss": 1.4181,
      "step": 61
    },
    {
      "epoch": 0.5933014354066986,
      "grad_norm": 0.43495655059814453,
      "learning_rate": 2.835583164544139e-06,
      "loss": 1.4476,
      "step": 62
    },
    {
      "epoch": 0.6028708133971292,
      "grad_norm": 0.4451518952846527,
      "learning_rate": 2.724098272258584e-06,
      "loss": 1.616,
      "step": 63
    },
    {
      "epoch": 0.6124401913875598,
      "grad_norm": 0.47959691286087036,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 1.5528,
      "step": 64
    },
    {
      "epoch": 0.6220095693779905,
      "grad_norm": 0.48145580291748047,
      "learning_rate": 2.5e-06,
      "loss": 1.5756,
      "step": 65
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.506266176700592,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 1.608,
      "step": 66
    },
    {
      "epoch": 0.6411483253588517,
      "grad_norm": 0.5399481058120728,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 1.686,
      "step": 67
    },
    {
      "epoch": 0.6507177033492823,
      "grad_norm": 0.5846008062362671,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 1.8601,
      "step": 68
    },
    {
      "epoch": 0.6602870813397129,
      "grad_norm": 0.5942398309707642,
      "learning_rate": 2.053607763003409e-06,
      "loss": 1.6992,
      "step": 69
    },
    {
      "epoch": 0.6698564593301436,
      "grad_norm": 0.6084458231925964,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 1.7457,
      "step": 70
    },
    {
      "epoch": 0.6794258373205742,
      "grad_norm": 0.719818651676178,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 1.7357,
      "step": 71
    },
    {
      "epoch": 0.6889952153110048,
      "grad_norm": 0.7451322674751282,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 1.9377,
      "step": 72
    },
    {
      "epoch": 0.6985645933014354,
      "grad_norm": 0.8885253667831421,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 1.9484,
      "step": 73
    },
    {
      "epoch": 0.7081339712918661,
      "grad_norm": 1.0710029602050781,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 1.9866,
      "step": 74
    },
    {
      "epoch": 0.7177033492822966,
      "grad_norm": 1.0909761190414429,
      "learning_rate": 1.415290652206105e-06,
      "loss": 2.0548,
      "step": 75
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.6213032007217407,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 2.2782,
      "step": 76
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 2.127164125442505,
      "learning_rate": 1.217751806485235e-06,
      "loss": 2.0789,
      "step": 77
    },
    {
      "epoch": 0.7464114832535885,
      "grad_norm": 3.6304738521575928,
      "learning_rate": 1.122757546369744e-06,
      "loss": 2.0903,
      "step": 78
    },
    {
      "epoch": 0.7559808612440191,
      "grad_norm": 0.2699255645275116,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 1.4164,
      "step": 79
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 0.29987215995788574,
      "learning_rate": 9.412754953531664e-07,
      "loss": 1.2793,
      "step": 80
    },
    {
      "epoch": 0.7751196172248804,
      "grad_norm": 0.3141963481903076,
      "learning_rate": 8.551531851507186e-07,
      "loss": 1.4328,
      "step": 81
    },
    {
      "epoch": 0.784688995215311,
      "grad_norm": 0.336625874042511,
      "learning_rate": 7.723433775328385e-07,
      "loss": 1.4148,
      "step": 82
    },
    {
      "epoch": 0.7942583732057417,
      "grad_norm": 0.368731290102005,
      "learning_rate": 6.930128404315214e-07,
      "loss": 1.517,
      "step": 83
    },
    {
      "epoch": 0.8038277511961722,
      "grad_norm": 0.37500929832458496,
      "learning_rate": 6.17321334990973e-07,
      "loss": 1.5432,
      "step": 84
    },
    {
      "epoch": 0.8133971291866029,
      "grad_norm": 0.38130730390548706,
      "learning_rate": 5.454212938299256e-07,
      "loss": 1.5176,
      "step": 85
    },
    {
      "epoch": 0.8229665071770335,
      "grad_norm": 0.41141316294670105,
      "learning_rate": 4.774575140626317e-07,
      "loss": 1.4348,
      "step": 86
    },
    {
      "epoch": 0.8325358851674641,
      "grad_norm": 0.41603273153305054,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 1.5163,
      "step": 87
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.44736191630363464,
      "learning_rate": 3.538780159953348e-07,
      "loss": 1.4274,
      "step": 88
    },
    {
      "epoch": 0.8516746411483254,
      "grad_norm": 0.43399325013160706,
      "learning_rate": 2.98511170358155e-07,
      "loss": 1.5425,
      "step": 89
    },
    {
      "epoch": 0.861244019138756,
      "grad_norm": 0.47178566455841064,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 1.6099,
      "step": 90
    },
    {
      "epoch": 0.8708133971291866,
      "grad_norm": 0.5100260972976685,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 1.6085,
      "step": 91
    },
    {
      "epoch": 0.8803827751196173,
      "grad_norm": 0.5522103905677795,
      "learning_rate": 1.59412823400657e-07,
      "loss": 1.7014,
      "step": 92
    },
    {
      "epoch": 0.8899521531100478,
      "grad_norm": 0.5604200959205627,
      "learning_rate": 1.223587092621162e-07,
      "loss": 1.5571,
      "step": 93
    },
    {
      "epoch": 0.8995215311004785,
      "grad_norm": 0.608319103717804,
      "learning_rate": 9.00928482603669e-08,
      "loss": 1.7045,
      "step": 94
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.645991861820221,
      "learning_rate": 6.268021954544095e-08,
      "loss": 1.6996,
      "step": 95
    },
    {
      "epoch": 0.9186602870813397,
      "grad_norm": 0.7313124537467957,
      "learning_rate": 4.017602850342584e-08,
      "loss": 1.8184,
      "step": 96
    },
    {
      "epoch": 0.9282296650717703,
      "grad_norm": 0.7927725315093994,
      "learning_rate": 2.262559558016325e-08,
      "loss": 1.9343,
      "step": 97
    },
    {
      "epoch": 0.937799043062201,
      "grad_norm": 0.9807630181312561,
      "learning_rate": 1.006426501190233e-08,
      "loss": 1.8933,
      "step": 98
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.920979917049408,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 1.8406,
      "step": 99
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 1.0186470746994019,
      "learning_rate": 0.0,
      "loss": 1.9207,
      "step": 100
    },
    {
      "epoch": 0.9569377990430622,
      "eval_loss": 1.6871801614761353,
      "eval_runtime": 6.0137,
      "eval_samples_per_second": 29.433,
      "eval_steps_per_second": 3.825,
      "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": 2.78948348952576e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}