{
  "best_metric": 0.6730939745903015,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.039615727443795185,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039615727443795186,
      "grad_norm": 14.314478874206543,
      "learning_rate": 5e-06,
      "loss": 2.5987,
      "step": 1
    },
    {
      "epoch": 0.00039615727443795186,
      "eval_loss": 1.2088950872421265,
      "eval_runtime": 338.2836,
      "eval_samples_per_second": 12.569,
      "eval_steps_per_second": 6.285,
      "step": 1
    },
    {
      "epoch": 0.0007923145488759037,
      "grad_norm": 16.324403762817383,
      "learning_rate": 1e-05,
      "loss": 3.394,
      "step": 2
    },
    {
      "epoch": 0.0011884718233138556,
      "grad_norm": 18.80040168762207,
      "learning_rate": 1.5e-05,
      "loss": 3.0517,
      "step": 3
    },
    {
      "epoch": 0.0015846290977518075,
      "grad_norm": 17.43671989440918,
      "learning_rate": 2e-05,
      "loss": 3.2647,
      "step": 4
    },
    {
      "epoch": 0.0019807863721897595,
      "grad_norm": 14.420022010803223,
      "learning_rate": 2.5e-05,
      "loss": 2.9988,
      "step": 5
    },
    {
      "epoch": 0.0023769436466277113,
      "grad_norm": 13.038010597229004,
      "learning_rate": 3e-05,
      "loss": 2.9589,
      "step": 6
    },
    {
      "epoch": 0.002773100921065663,
      "grad_norm": 11.008463859558105,
      "learning_rate": 3.5e-05,
      "loss": 2.6601,
      "step": 7
    },
    {
      "epoch": 0.003169258195503615,
      "grad_norm": 11.67863941192627,
      "learning_rate": 4e-05,
      "loss": 2.6742,
      "step": 8
    },
    {
      "epoch": 0.0035654154699415667,
      "grad_norm": 12.343779563903809,
      "learning_rate": 4.5e-05,
      "loss": 2.9556,
      "step": 9
    },
    {
      "epoch": 0.003961572744379519,
      "grad_norm": 10.546838760375977,
      "learning_rate": 5e-05,
      "loss": 2.6015,
      "step": 10
    },
    {
      "epoch": 0.004357730018817471,
      "grad_norm": 11.106729507446289,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.5997,
      "step": 11
    },
    {
      "epoch": 0.004753887293255423,
      "grad_norm": 10.504631996154785,
      "learning_rate": 6e-05,
      "loss": 3.0646,
      "step": 12
    },
    {
      "epoch": 0.005150044567693374,
      "grad_norm": 9.306614875793457,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.5052,
      "step": 13
    },
    {
      "epoch": 0.005546201842131326,
      "grad_norm": 9.76103401184082,
      "learning_rate": 7e-05,
      "loss": 2.272,
      "step": 14
    },
    {
      "epoch": 0.005942359116569278,
      "grad_norm": 10.521080017089844,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.7484,
      "step": 15
    },
    {
      "epoch": 0.00633851639100723,
      "grad_norm": 10.383809089660645,
      "learning_rate": 8e-05,
      "loss": 2.4941,
      "step": 16
    },
    {
      "epoch": 0.006734673665445182,
      "grad_norm": 11.771020889282227,
      "learning_rate": 8.5e-05,
      "loss": 2.7839,
      "step": 17
    },
    {
      "epoch": 0.0071308309398831335,
      "grad_norm": 10.846237182617188,
      "learning_rate": 9e-05,
      "loss": 2.4915,
      "step": 18
    },
    {
      "epoch": 0.007526988214321085,
      "grad_norm": 9.68586254119873,
      "learning_rate": 9.5e-05,
      "loss": 2.4326,
      "step": 19
    },
    {
      "epoch": 0.007923145488759038,
      "grad_norm": 9.134086608886719,
      "learning_rate": 0.0001,
      "loss": 2.2999,
      "step": 20
    },
    {
      "epoch": 0.008319302763196989,
      "grad_norm": 10.715767860412598,
      "learning_rate": 9.999238475781957e-05,
      "loss": 2.4463,
      "step": 21
    },
    {
      "epoch": 0.008715460037634942,
      "grad_norm": 12.497233390808105,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.6965,
      "step": 22
    },
    {
      "epoch": 0.009111617312072893,
      "grad_norm": 11.588178634643555,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.6387,
      "step": 23
    },
    {
      "epoch": 0.009507774586510845,
      "grad_norm": 10.239289283752441,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.3716,
      "step": 24
    },
    {
      "epoch": 0.009903931860948796,
      "grad_norm": 10.348134994506836,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.3706,
      "step": 25
    },
    {
      "epoch": 0.010300089135386749,
      "grad_norm": 12.288321495056152,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.8137,
      "step": 26
    },
    {
      "epoch": 0.0106962464098247,
      "grad_norm": 10.109082221984863,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.5793,
      "step": 27
    },
    {
      "epoch": 0.011092403684262652,
      "grad_norm": 10.935514450073242,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.5139,
      "step": 28
    },
    {
      "epoch": 0.011488560958700603,
      "grad_norm": 11.004712104797363,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.4287,
      "step": 29
    },
    {
      "epoch": 0.011884718233138556,
      "grad_norm": 11.961386680603027,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.885,
      "step": 30
    },
    {
      "epoch": 0.012280875507576509,
      "grad_norm": 10.97961139678955,
      "learning_rate": 9.908135917238321e-05,
      "loss": 2.7134,
      "step": 31
    },
    {
      "epoch": 0.01267703278201446,
      "grad_norm": 13.087514877319336,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.0466,
      "step": 32
    },
    {
      "epoch": 0.013073190056452412,
      "grad_norm": 9.89000129699707,
      "learning_rate": 9.871850323926177e-05,
      "loss": 2.0578,
      "step": 33
    },
    {
      "epoch": 0.013469347330890363,
      "grad_norm": 13.183517456054688,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.8413,
      "step": 34
    },
    {
      "epoch": 0.013865504605328316,
      "grad_norm": 10.432723999023438,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.3153,
      "step": 35
    },
    {
      "epoch": 0.014261661879766267,
      "grad_norm": 10.83343505859375,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.3221,
      "step": 36
    },
    {
      "epoch": 0.01465781915420422,
      "grad_norm": 11.4821138381958,
      "learning_rate": 9.781523779815179e-05,
      "loss": 2.7535,
      "step": 37
    },
    {
      "epoch": 0.01505397642864217,
      "grad_norm": 13.579030990600586,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1641,
      "step": 38
    },
    {
      "epoch": 0.015450133703080123,
      "grad_norm": 12.277050018310547,
      "learning_rate": 9.727592877996585e-05,
      "loss": 2.5429,
      "step": 39
    },
    {
      "epoch": 0.015846290977518076,
      "grad_norm": 11.074421882629395,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3702,
      "step": 40
    },
    {
      "epoch": 0.016242448251956025,
      "grad_norm": 14.457468032836914,
      "learning_rate": 9.667902132486009e-05,
      "loss": 3.2263,
      "step": 41
    },
    {
      "epoch": 0.016638605526393978,
      "grad_norm": 12.959149360656738,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4348,
      "step": 42
    },
    {
      "epoch": 0.01703476280083193,
      "grad_norm": 17.107925415039062,
      "learning_rate": 9.602524267262203e-05,
      "loss": 3.3204,
      "step": 43
    },
    {
      "epoch": 0.017430920075269883,
      "grad_norm": 14.488329887390137,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.845,
      "step": 44
    },
    {
      "epoch": 0.017827077349707832,
      "grad_norm": 12.97142505645752,
      "learning_rate": 9.53153893518325e-05,
      "loss": 3.277,
      "step": 45
    },
    {
      "epoch": 0.018223234624145785,
      "grad_norm": 16.733470916748047,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.6097,
      "step": 46
    },
    {
      "epoch": 0.018619391898583738,
      "grad_norm": 13.195300102233887,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.9709,
      "step": 47
    },
    {
      "epoch": 0.01901554917302169,
      "grad_norm": 13.836097717285156,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.7804,
      "step": 48
    },
    {
      "epoch": 0.019411706447459643,
      "grad_norm": 12.61435317993164,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.2369,
      "step": 49
    },
    {
      "epoch": 0.019807863721897592,
      "grad_norm": 17.996479034423828,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.2496,
      "step": 50
    },
    {
      "epoch": 0.019807863721897592,
      "eval_loss": 0.7593479752540588,
      "eval_runtime": 340.1536,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 6.25,
      "step": 50
    },
    {
      "epoch": 0.020204020996335545,
      "grad_norm": 14.763004302978516,
      "learning_rate": 9.285836503510562e-05,
      "loss": 3.4166,
      "step": 51
    },
    {
      "epoch": 0.020600178270773498,
      "grad_norm": 8.999519348144531,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.2951,
      "step": 52
    },
    {
      "epoch": 0.02099633554521145,
      "grad_norm": 7.654372215270996,
      "learning_rate": 9.193352839727121e-05,
      "loss": 2.9339,
      "step": 53
    },
    {
      "epoch": 0.0213924928196494,
      "grad_norm": 6.517328262329102,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.4162,
      "step": 54
    },
    {
      "epoch": 0.021788650094087352,
      "grad_norm": 7.003291130065918,
      "learning_rate": 9.09576022144496e-05,
      "loss": 2.2779,
      "step": 55
    },
    {
      "epoch": 0.022184807368525305,
      "grad_norm": 8.182329177856445,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.9609,
      "step": 56
    },
    {
      "epoch": 0.022580964642963258,
      "grad_norm": 7.554233074188232,
      "learning_rate": 8.993177550236464e-05,
      "loss": 2.6803,
      "step": 57
    },
    {
      "epoch": 0.022977121917401207,
      "grad_norm": 7.749049186706543,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.5795,
      "step": 58
    },
    {
      "epoch": 0.02337327919183916,
      "grad_norm": 7.0886149406433105,
      "learning_rate": 8.885729807284856e-05,
      "loss": 2.3511,
      "step": 59
    },
    {
      "epoch": 0.023769436466277112,
      "grad_norm": 6.84679651260376,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1122,
      "step": 60
    },
    {
      "epoch": 0.024165593740715065,
      "grad_norm": 7.1356329917907715,
      "learning_rate": 8.773547901113862e-05,
      "loss": 2.3196,
      "step": 61
    },
    {
      "epoch": 0.024561751015153017,
      "grad_norm": 7.6530046463012695,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.4788,
      "step": 62
    },
    {
      "epoch": 0.024957908289590967,
      "grad_norm": 8.369495391845703,
      "learning_rate": 8.656768508095853e-05,
      "loss": 2.3375,
      "step": 63
    },
    {
      "epoch": 0.02535406556402892,
      "grad_norm": 8.36403751373291,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.0959,
      "step": 64
    },
    {
      "epoch": 0.025750222838466872,
      "grad_norm": 10.229287147521973,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.0627,
      "step": 65
    },
    {
      "epoch": 0.026146380112904825,
      "grad_norm": 8.87305736541748,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.5706,
      "step": 66
    },
    {
      "epoch": 0.026542537387342774,
      "grad_norm": 9.638481140136719,
      "learning_rate": 8.409991800312493e-05,
      "loss": 2.7759,
      "step": 67
    },
    {
      "epoch": 0.026938694661780727,
      "grad_norm": 9.509964942932129,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.5595,
      "step": 68
    },
    {
      "epoch": 0.02733485193621868,
      "grad_norm": 9.560708045959473,
      "learning_rate": 8.280295144952536e-05,
      "loss": 2.6391,
      "step": 69
    },
    {
      "epoch": 0.027731009210656632,
      "grad_norm": 8.581311225891113,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.784,
      "step": 70
    },
    {
      "epoch": 0.02812716648509458,
      "grad_norm": 7.63805627822876,
      "learning_rate": 8.146601955249188e-05,
      "loss": 2.2859,
      "step": 71
    },
    {
      "epoch": 0.028523323759532534,
      "grad_norm": 8.626289367675781,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.7975,
      "step": 72
    },
    {
      "epoch": 0.028919481033970486,
      "grad_norm": 11.270418167114258,
      "learning_rate": 8.009075115760243e-05,
      "loss": 2.5275,
      "step": 73
    },
    {
      "epoch": 0.02931563830840844,
      "grad_norm": 9.097280502319336,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.696,
      "step": 74
    },
    {
      "epoch": 0.02971179558284639,
      "grad_norm": 7.862690448760986,
      "learning_rate": 7.86788218175523e-05,
      "loss": 2.2284,
      "step": 75
    },
    {
      "epoch": 0.03010795285728434,
      "grad_norm": 7.738744735717773,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.3424,
      "step": 76
    },
    {
      "epoch": 0.030504110131722294,
      "grad_norm": 9.578076362609863,
      "learning_rate": 7.723195175075136e-05,
      "loss": 2.8572,
      "step": 77
    },
    {
      "epoch": 0.030900267406160246,
      "grad_norm": 9.798004150390625,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.9643,
      "step": 78
    },
    {
      "epoch": 0.0312964246805982,
      "grad_norm": 9.317380905151367,
      "learning_rate": 7.575190374550272e-05,
      "loss": 3.2559,
      "step": 79
    },
    {
      "epoch": 0.03169258195503615,
      "grad_norm": 9.332989692687988,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.6451,
      "step": 80
    },
    {
      "epoch": 0.032088739229474104,
      "grad_norm": 10.110783576965332,
      "learning_rate": 7.424048101231686e-05,
      "loss": 3.095,
      "step": 81
    },
    {
      "epoch": 0.03248489650391205,
      "grad_norm": 9.339815139770508,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.3127,
      "step": 82
    },
    {
      "epoch": 0.03288105377835,
      "grad_norm": 10.58879280090332,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.5449,
      "step": 83
    },
    {
      "epoch": 0.033277211052787956,
      "grad_norm": 10.540449142456055,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.362,
      "step": 84
    },
    {
      "epoch": 0.03367336832722591,
      "grad_norm": 12.278244972229004,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.5295,
      "step": 85
    },
    {
      "epoch": 0.03406952560166386,
      "grad_norm": 9.675426483154297,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.4279,
      "step": 86
    },
    {
      "epoch": 0.034465682876101814,
      "grad_norm": 8.322236061096191,
      "learning_rate": 6.953655642446368e-05,
      "loss": 2.1438,
      "step": 87
    },
    {
      "epoch": 0.034861840150539766,
      "grad_norm": 15.984248161315918,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.4826,
      "step": 88
    },
    {
      "epoch": 0.03525799742497772,
      "grad_norm": 11.099123001098633,
      "learning_rate": 6.7918397477265e-05,
      "loss": 2.8121,
      "step": 89
    },
    {
      "epoch": 0.035654154699415665,
      "grad_norm": 10.237126350402832,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.6013,
      "step": 90
    },
    {
      "epoch": 0.03605031197385362,
      "grad_norm": 12.89112663269043,
      "learning_rate": 6.627840772285784e-05,
      "loss": 2.3039,
      "step": 91
    },
    {
      "epoch": 0.03644646924829157,
      "grad_norm": 8.39738655090332,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.0425,
      "step": 92
    },
    {
      "epoch": 0.03684262652272952,
      "grad_norm": 10.789386749267578,
      "learning_rate": 6.461858523613684e-05,
      "loss": 2.7755,
      "step": 93
    },
    {
      "epoch": 0.037238783797167475,
      "grad_norm": 11.95657730102539,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.5013,
      "step": 94
    },
    {
      "epoch": 0.03763494107160543,
      "grad_norm": 9.726419448852539,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.6235,
      "step": 95
    },
    {
      "epoch": 0.03803109834604338,
      "grad_norm": 12.768197059631348,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.7799,
      "step": 96
    },
    {
      "epoch": 0.03842725562048133,
      "grad_norm": 11.749434471130371,
      "learning_rate": 6.124755271719325e-05,
      "loss": 2.9625,
      "step": 97
    },
    {
      "epoch": 0.038823412894919286,
      "grad_norm": 14.08253002166748,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.8971,
      "step": 98
    },
    {
      "epoch": 0.03921957016935723,
      "grad_norm": 11.256560325622559,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 2.3274,
      "step": 99
    },
    {
      "epoch": 0.039615727443795185,
      "grad_norm": 12.625090599060059,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.6474,
      "step": 100
    },
    {
      "epoch": 0.039615727443795185,
      "eval_loss": 0.6730939745903015,
      "eval_runtime": 340.0276,
      "eval_samples_per_second": 12.505,
      "eval_steps_per_second": 6.252,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.430998008987648e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}