{
  "best_metric": 0.8196816444396973,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.8281573498964804,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008281573498964804,
      "grad_norm": 0.8388795256614685,
      "learning_rate": 7e-06,
      "loss": 0.804,
      "step": 1
    },
    {
      "epoch": 0.008281573498964804,
      "eval_loss": 1.1692047119140625,
      "eval_runtime": 32.2894,
      "eval_samples_per_second": 6.318,
      "eval_steps_per_second": 1.579,
      "step": 1
    },
    {
      "epoch": 0.016563146997929608,
      "grad_norm": 1.023823618888855,
      "learning_rate": 1.4e-05,
      "loss": 0.8544,
      "step": 2
    },
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 1.0270742177963257,
      "learning_rate": 2.1e-05,
      "loss": 0.8755,
      "step": 3
    },
    {
      "epoch": 0.033126293995859216,
      "grad_norm": 0.9506105780601501,
      "learning_rate": 2.8e-05,
      "loss": 0.8441,
      "step": 4
    },
    {
      "epoch": 0.041407867494824016,
      "grad_norm": 0.7932412028312683,
      "learning_rate": 3.5e-05,
      "loss": 0.7846,
      "step": 5
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 0.7128869295120239,
      "learning_rate": 4.2e-05,
      "loss": 0.9147,
      "step": 6
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 0.4176234304904938,
      "learning_rate": 4.899999999999999e-05,
      "loss": 0.7784,
      "step": 7
    },
    {
      "epoch": 0.06625258799171843,
      "grad_norm": 0.6762263178825378,
      "learning_rate": 5.6e-05,
      "loss": 0.8248,
      "step": 8
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 0.8291305899620056,
      "learning_rate": 6.3e-05,
      "loss": 0.8014,
      "step": 9
    },
    {
      "epoch": 0.08281573498964803,
      "grad_norm": 0.8136356472969055,
      "learning_rate": 7e-05,
      "loss": 0.9253,
      "step": 10
    },
    {
      "epoch": 0.09109730848861283,
      "grad_norm": 0.4319281578063965,
      "learning_rate": 6.999521567473641e-05,
      "loss": 0.8555,
      "step": 11
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 0.36292925477027893,
      "learning_rate": 6.998086400693241e-05,
      "loss": 0.7425,
      "step": 12
    },
    {
      "epoch": 0.10766045548654245,
      "grad_norm": 0.3616969585418701,
      "learning_rate": 6.995694892019065e-05,
      "loss": 0.9021,
      "step": 13
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 0.3888731002807617,
      "learning_rate": 6.99234769526571e-05,
      "loss": 0.7912,
      "step": 14
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 0.3677065968513489,
      "learning_rate": 6.988045725523343e-05,
      "loss": 0.6922,
      "step": 15
    },
    {
      "epoch": 0.13250517598343686,
      "grad_norm": 0.38920730352401733,
      "learning_rate": 6.982790158907539e-05,
      "loss": 0.8843,
      "step": 16
    },
    {
      "epoch": 0.14078674948240166,
      "grad_norm": 0.4462592601776123,
      "learning_rate": 6.976582432237733e-05,
      "loss": 0.9304,
      "step": 17
    },
    {
      "epoch": 0.14906832298136646,
      "grad_norm": 0.40514039993286133,
      "learning_rate": 6.969424242644413e-05,
      "loss": 0.8461,
      "step": 18
    },
    {
      "epoch": 0.15734989648033126,
      "grad_norm": 0.44129592180252075,
      "learning_rate": 6.961317547105138e-05,
      "loss": 0.8518,
      "step": 19
    },
    {
      "epoch": 0.16563146997929606,
      "grad_norm": 0.4335060715675354,
      "learning_rate": 6.952264561909527e-05,
      "loss": 0.8793,
      "step": 20
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.543445885181427,
      "learning_rate": 6.942267762053337e-05,
      "loss": 0.9113,
      "step": 21
    },
    {
      "epoch": 0.18219461697722567,
      "grad_norm": 0.5542380809783936,
      "learning_rate": 6.931329880561832e-05,
      "loss": 0.9433,
      "step": 22
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.516521692276001,
      "learning_rate": 6.919453907742597e-05,
      "loss": 0.9016,
      "step": 23
    },
    {
      "epoch": 0.19875776397515527,
      "grad_norm": 0.5378891825675964,
      "learning_rate": 6.90664309036802e-05,
      "loss": 0.7877,
      "step": 24
    },
    {
      "epoch": 0.2070393374741201,
      "grad_norm": 0.577548086643219,
      "learning_rate": 6.892900930787656e-05,
      "loss": 0.8454,
      "step": 25
    },
    {
      "epoch": 0.2153209109730849,
      "grad_norm": 0.5783238410949707,
      "learning_rate": 6.87823118597072e-05,
      "loss": 0.8776,
      "step": 26
    },
    {
      "epoch": 0.2236024844720497,
      "grad_norm": 0.5544853210449219,
      "learning_rate": 6.862637866478969e-05,
      "loss": 0.8123,
      "step": 27
    },
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 0.7183583974838257,
      "learning_rate": 6.846125235370252e-05,
      "loss": 0.941,
      "step": 28
    },
    {
      "epoch": 0.2401656314699793,
      "grad_norm": 0.7497084140777588,
      "learning_rate": 6.828697807033038e-05,
      "loss": 0.9533,
      "step": 29
    },
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 1.0239611864089966,
      "learning_rate": 6.81036034595222e-05,
      "loss": 1.0226,
      "step": 30
    },
    {
      "epoch": 0.2567287784679089,
      "grad_norm": 0.215080127120018,
      "learning_rate": 6.791117865406564e-05,
      "loss": 0.5555,
      "step": 31
    },
    {
      "epoch": 0.2650103519668737,
      "grad_norm": 0.32441794872283936,
      "learning_rate": 6.770975626098112e-05,
      "loss": 0.7501,
      "step": 32
    },
    {
      "epoch": 0.2732919254658385,
      "grad_norm": 0.309184730052948,
      "learning_rate": 6.749939134713974e-05,
      "loss": 0.7853,
      "step": 33
    },
    {
      "epoch": 0.2815734989648033,
      "grad_norm": 0.3206530511379242,
      "learning_rate": 6.728014142420846e-05,
      "loss": 0.659,
      "step": 34
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 0.2530266046524048,
      "learning_rate": 6.7052066432927e-05,
      "loss": 0.651,
      "step": 35
    },
    {
      "epoch": 0.2981366459627329,
      "grad_norm": 0.27744585275650024,
      "learning_rate": 6.681522872672069e-05,
      "loss": 0.6502,
      "step": 36
    },
    {
      "epoch": 0.3064182194616977,
      "grad_norm": 0.2372923493385315,
      "learning_rate": 6.656969305465356e-05,
      "loss": 0.7619,
      "step": 37
    },
    {
      "epoch": 0.3146997929606625,
      "grad_norm": 0.2609351575374603,
      "learning_rate": 6.631552654372672e-05,
      "loss": 0.6668,
      "step": 38
    },
    {
      "epoch": 0.32298136645962733,
      "grad_norm": 0.2953057885169983,
      "learning_rate": 6.60527986805264e-05,
      "loss": 0.7653,
      "step": 39
    },
    {
      "epoch": 0.33126293995859213,
      "grad_norm": 0.32191261649131775,
      "learning_rate": 6.578158129222711e-05,
      "loss": 0.8575,
      "step": 40
    },
    {
      "epoch": 0.33954451345755693,
      "grad_norm": 0.2882176339626312,
      "learning_rate": 6.550194852695469e-05,
      "loss": 0.7252,
      "step": 41
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.27066636085510254,
      "learning_rate": 6.521397683351509e-05,
      "loss": 0.7575,
      "step": 42
    },
    {
      "epoch": 0.35610766045548653,
      "grad_norm": 0.3208519518375397,
      "learning_rate": 6.491774494049386e-05,
      "loss": 0.8635,
      "step": 43
    },
    {
      "epoch": 0.36438923395445133,
      "grad_norm": 0.35946550965309143,
      "learning_rate": 6.461333383473272e-05,
      "loss": 0.8081,
      "step": 44
    },
    {
      "epoch": 0.37267080745341613,
      "grad_norm": 0.3770899176597595,
      "learning_rate": 6.430082673918849e-05,
      "loss": 0.8199,
      "step": 45
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.36672505736351013,
      "learning_rate": 6.398030909018069e-05,
      "loss": 0.8569,
      "step": 46
    },
    {
      "epoch": 0.38923395445134573,
      "grad_norm": 0.3554442226886749,
      "learning_rate": 6.365186851403423e-05,
      "loss": 0.8098,
      "step": 47
    },
    {
      "epoch": 0.39751552795031053,
      "grad_norm": 0.3235284388065338,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.791,
      "step": 48
    },
    {
      "epoch": 0.4057971014492754,
      "grad_norm": 0.3624836206436157,
      "learning_rate": 6.297157989132236e-05,
      "loss": 0.7369,
      "step": 49
    },
    {
      "epoch": 0.4140786749482402,
      "grad_norm": 0.3535378873348236,
      "learning_rate": 6.261991782887377e-05,
      "loss": 0.6616,
      "step": 50
    },
    {
      "epoch": 0.4140786749482402,
      "eval_loss": 0.8644523024559021,
      "eval_runtime": 32.248,
      "eval_samples_per_second": 6.326,
      "eval_steps_per_second": 1.581,
      "step": 50
    },
    {
      "epoch": 0.422360248447205,
      "grad_norm": 0.3799665868282318,
      "learning_rate": 6.226070475667393e-05,
      "loss": 0.7939,
      "step": 51
    },
    {
      "epoch": 0.4306418219461698,
      "grad_norm": 0.4117141664028168,
      "learning_rate": 6.189403887999006e-05,
      "loss": 0.7855,
      "step": 52
    },
    {
      "epoch": 0.4389233954451346,
      "grad_norm": 0.4020320177078247,
      "learning_rate": 6.152002044161171e-05,
      "loss": 0.8022,
      "step": 53
    },
    {
      "epoch": 0.4472049689440994,
      "grad_norm": 0.46013712882995605,
      "learning_rate": 6.113875169444539e-05,
      "loss": 0.8572,
      "step": 54
    },
    {
      "epoch": 0.4554865424430642,
      "grad_norm": 0.45274391770362854,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 0.7123,
      "step": 55
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 0.5365428328514099,
      "learning_rate": 6.035488216768811e-05,
      "loss": 0.8758,
      "step": 56
    },
    {
      "epoch": 0.4720496894409938,
      "grad_norm": 0.641646146774292,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 0.9564,
      "step": 57
    },
    {
      "epoch": 0.4803312629399586,
      "grad_norm": 0.508011519908905,
      "learning_rate": 5.954328744953709e-05,
      "loss": 0.8731,
      "step": 58
    },
    {
      "epoch": 0.4886128364389234,
      "grad_norm": 0.8867300152778625,
      "learning_rate": 5.91273693191498e-05,
      "loss": 0.9009,
      "step": 59
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 0.9791533946990967,
      "learning_rate": 5.870485500690094e-05,
      "loss": 1.1371,
      "step": 60
    },
    {
      "epoch": 0.505175983436853,
      "grad_norm": 0.24218077957630157,
      "learning_rate": 5.827586002398468e-05,
      "loss": 0.6875,
      "step": 61
    },
    {
      "epoch": 0.5134575569358178,
      "grad_norm": 0.22737136483192444,
      "learning_rate": 5.784050165334589e-05,
      "loss": 0.7116,
      "step": 62
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.2559671103954315,
      "learning_rate": 5.739889891761608e-05,
      "loss": 0.7719,
      "step": 63
    },
    {
      "epoch": 0.5300207039337475,
      "grad_norm": 0.24487318098545074,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 0.7212,
      "step": 64
    },
    {
      "epoch": 0.5383022774327122,
      "grad_norm": 0.23421718180179596,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 0.7471,
      "step": 65
    },
    {
      "epoch": 0.546583850931677,
      "grad_norm": 0.21821844577789307,
      "learning_rate": 5.603784015490587e-05,
      "loss": 0.6552,
      "step": 66
    },
    {
      "epoch": 0.5548654244306418,
      "grad_norm": 0.26210862398147583,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.774,
      "step": 67
    },
    {
      "epoch": 0.5631469979296067,
      "grad_norm": 0.2591906785964966,
      "learning_rate": 5.510150319390302e-05,
      "loss": 0.687,
      "step": 68
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.26978063583374023,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 0.7278,
      "step": 69
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 0.24709314107894897,
      "learning_rate": 5.414318553428494e-05,
      "loss": 0.5976,
      "step": 70
    },
    {
      "epoch": 0.587991718426501,
      "grad_norm": 0.30029296875,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 0.7129,
      "step": 71
    },
    {
      "epoch": 0.5962732919254659,
      "grad_norm": 0.32972994446754456,
      "learning_rate": 5.316393508234253e-05,
      "loss": 0.8332,
      "step": 72
    },
    {
      "epoch": 0.6045548654244306,
      "grad_norm": 0.3365096151828766,
      "learning_rate": 5.266679382071953e-05,
      "loss": 0.8121,
      "step": 73
    },
    {
      "epoch": 0.6128364389233955,
      "grad_norm": 0.31908273696899414,
      "learning_rate": 5.216482263406778e-05,
      "loss": 0.8543,
      "step": 74
    },
    {
      "epoch": 0.6211180124223602,
      "grad_norm": 0.3485449552536011,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 0.8116,
      "step": 75
    },
    {
      "epoch": 0.629399585921325,
      "grad_norm": 0.33620256185531616,
      "learning_rate": 5.114694070425407e-05,
      "loss": 0.7493,
      "step": 76
    },
    {
      "epoch": 0.6376811594202898,
      "grad_norm": 0.35500848293304443,
      "learning_rate": 5.063130823984823e-05,
      "loss": 0.7026,
      "step": 77
    },
    {
      "epoch": 0.6459627329192547,
      "grad_norm": 0.4022809565067291,
      "learning_rate": 5.011140233184724e-05,
      "loss": 0.7928,
      "step": 78
    },
    {
      "epoch": 0.6542443064182195,
      "grad_norm": 0.41914957761764526,
      "learning_rate": 4.958736511733516e-05,
      "loss": 0.8219,
      "step": 79
    },
    {
      "epoch": 0.6625258799171843,
      "grad_norm": 0.4002333879470825,
      "learning_rate": 4.905933986285393e-05,
      "loss": 0.8019,
      "step": 80
    },
    {
      "epoch": 0.6708074534161491,
      "grad_norm": 0.46458199620246887,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 0.7353,
      "step": 81
    },
    {
      "epoch": 0.6790890269151139,
      "grad_norm": 0.5049306154251099,
      "learning_rate": 4.799190371213772e-05,
      "loss": 0.935,
      "step": 82
    },
    {
      "epoch": 0.6873706004140787,
      "grad_norm": 0.48192158341407776,
      "learning_rate": 4.745278464228808e-05,
      "loss": 0.8568,
      "step": 83
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.5385396480560303,
      "learning_rate": 4.69102611054575e-05,
      "loss": 0.8613,
      "step": 84
    },
    {
      "epoch": 0.7039337474120083,
      "grad_norm": 0.4860864579677582,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 0.8288,
      "step": 85
    },
    {
      "epoch": 0.7122153209109731,
      "grad_norm": 0.4691753387451172,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.7301,
      "step": 86
    },
    {
      "epoch": 0.7204968944099379,
      "grad_norm": 0.6713128685951233,
      "learning_rate": 4.526375130845627e-05,
      "loss": 1.0118,
      "step": 87
    },
    {
      "epoch": 0.7287784679089027,
      "grad_norm": 0.8337951302528381,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 0.8735,
      "step": 88
    },
    {
      "epoch": 0.7370600414078675,
      "grad_norm": 0.7612811326980591,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 0.9304,
      "step": 89
    },
    {
      "epoch": 0.7453416149068323,
      "grad_norm": 0.8643386960029602,
      "learning_rate": 4.359199204992797e-05,
      "loss": 1.0096,
      "step": 90
    },
    {
      "epoch": 0.7536231884057971,
      "grad_norm": 0.20685485005378723,
      "learning_rate": 4.30298372016363e-05,
      "loss": 0.6227,
      "step": 91
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.25332385301589966,
      "learning_rate": 4.246548707603114e-05,
      "loss": 0.7315,
      "step": 92
    },
    {
      "epoch": 0.7701863354037267,
      "grad_norm": 0.24437353014945984,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 0.6921,
      "step": 93
    },
    {
      "epoch": 0.7784679089026915,
      "grad_norm": 0.2593900263309479,
      "learning_rate": 4.133081870162385e-05,
      "loss": 0.7514,
      "step": 94
    },
    {
      "epoch": 0.7867494824016563,
      "grad_norm": 0.2574782371520996,
      "learning_rate": 4.076081065982569e-05,
      "loss": 0.6447,
      "step": 95
    },
    {
      "epoch": 0.7950310559006211,
      "grad_norm": 0.3053584396839142,
      "learning_rate": 4.018922766991447e-05,
      "loss": 0.6437,
      "step": 96
    },
    {
      "epoch": 0.8033126293995859,
      "grad_norm": 0.2642808258533478,
      "learning_rate": 3.961622599697241e-05,
      "loss": 0.7539,
      "step": 97
    },
    {
      "epoch": 0.8115942028985508,
      "grad_norm": 0.2618858814239502,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 0.6641,
      "step": 98
    },
    {
      "epoch": 0.8198757763975155,
      "grad_norm": 0.2602124512195587,
      "learning_rate": 3.84665935587662e-05,
      "loss": 0.6166,
      "step": 99
    },
    {
      "epoch": 0.8281573498964804,
      "grad_norm": 0.2887020707130432,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 0.6502,
      "step": 100
    },
    {
      "epoch": 0.8281573498964804,
      "eval_loss": 0.8196816444396973,
      "eval_runtime": 32.2536,
      "eval_samples_per_second": 6.325,
      "eval_steps_per_second": 1.581,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": 3.373606698567598e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}