{
  "best_metric": 0.21579746901988983,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.16359918200409,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008179959100204499,
      "grad_norm": 0.4496954381465912,
      "learning_rate": 1.013e-05,
      "loss": 0.8848,
      "step": 1
    },
    {
      "epoch": 0.0008179959100204499,
      "eval_loss": 0.5526403784751892,
      "eval_runtime": 164.1948,
      "eval_samples_per_second": 3.137,
      "eval_steps_per_second": 0.786,
      "step": 1
    },
    {
      "epoch": 0.0016359918200408998,
      "grad_norm": 0.38289597630500793,
      "learning_rate": 2.026e-05,
      "loss": 0.6338,
      "step": 2
    },
    {
      "epoch": 0.00245398773006135,
      "grad_norm": 0.678950309753418,
      "learning_rate": 3.039e-05,
      "loss": 1.371,
      "step": 3
    },
    {
      "epoch": 0.0032719836400817996,
      "grad_norm": 0.5606029629707336,
      "learning_rate": 4.052e-05,
      "loss": 1.0274,
      "step": 4
    },
    {
      "epoch": 0.00408997955010225,
      "grad_norm": 0.5244286060333252,
      "learning_rate": 5.065e-05,
      "loss": 0.7953,
      "step": 5
    },
    {
      "epoch": 0.0049079754601227,
      "grad_norm": 0.49360060691833496,
      "learning_rate": 6.078e-05,
      "loss": 0.8689,
      "step": 6
    },
    {
      "epoch": 0.0057259713701431495,
      "grad_norm": 1.8924438953399658,
      "learning_rate": 7.091e-05,
      "loss": 1.2078,
      "step": 7
    },
    {
      "epoch": 0.006543967280163599,
      "grad_norm": 0.60125732421875,
      "learning_rate": 8.104e-05,
      "loss": 0.951,
      "step": 8
    },
    {
      "epoch": 0.007361963190184049,
      "grad_norm": 0.5913432836532593,
      "learning_rate": 9.117e-05,
      "loss": 0.9561,
      "step": 9
    },
    {
      "epoch": 0.0081799591002045,
      "grad_norm": 0.6411980390548706,
      "learning_rate": 0.0001013,
      "loss": 0.9956,
      "step": 10
    },
    {
      "epoch": 0.00899795501022495,
      "grad_norm": 0.6919670701026917,
      "learning_rate": 0.00010076684210526316,
      "loss": 0.8319,
      "step": 11
    },
    {
      "epoch": 0.0098159509202454,
      "grad_norm": 0.6590487360954285,
      "learning_rate": 0.0001002336842105263,
      "loss": 0.7345,
      "step": 12
    },
    {
      "epoch": 0.01063394683026585,
      "grad_norm": 0.82487952709198,
      "learning_rate": 9.970052631578946e-05,
      "loss": 0.8608,
      "step": 13
    },
    {
      "epoch": 0.011451942740286299,
      "grad_norm": 0.7508109211921692,
      "learning_rate": 9.916736842105263e-05,
      "loss": 0.9751,
      "step": 14
    },
    {
      "epoch": 0.012269938650306749,
      "grad_norm": 0.7014967203140259,
      "learning_rate": 9.863421052631579e-05,
      "loss": 0.9172,
      "step": 15
    },
    {
      "epoch": 0.013087934560327199,
      "grad_norm": 0.6674103140830994,
      "learning_rate": 9.810105263157895e-05,
      "loss": 0.5077,
      "step": 16
    },
    {
      "epoch": 0.013905930470347648,
      "grad_norm": 0.8871914744377136,
      "learning_rate": 9.756789473684211e-05,
      "loss": 1.1221,
      "step": 17
    },
    {
      "epoch": 0.014723926380368098,
      "grad_norm": 0.8045795559883118,
      "learning_rate": 9.703473684210525e-05,
      "loss": 0.9631,
      "step": 18
    },
    {
      "epoch": 0.015541922290388548,
      "grad_norm": 0.8533051013946533,
      "learning_rate": 9.650157894736842e-05,
      "loss": 0.9807,
      "step": 19
    },
    {
      "epoch": 0.016359918200409,
      "grad_norm": 0.5677836537361145,
      "learning_rate": 9.596842105263158e-05,
      "loss": 0.4352,
      "step": 20
    },
    {
      "epoch": 0.01717791411042945,
      "grad_norm": 1.4102709293365479,
      "learning_rate": 9.543526315789474e-05,
      "loss": 1.2272,
      "step": 21
    },
    {
      "epoch": 0.0179959100204499,
      "grad_norm": 1.0736172199249268,
      "learning_rate": 9.49021052631579e-05,
      "loss": 1.1928,
      "step": 22
    },
    {
      "epoch": 0.01881390593047035,
      "grad_norm": 1.2938551902770996,
      "learning_rate": 9.436894736842105e-05,
      "loss": 0.9907,
      "step": 23
    },
    {
      "epoch": 0.0196319018404908,
      "grad_norm": 0.9903382658958435,
      "learning_rate": 9.38357894736842e-05,
      "loss": 0.8166,
      "step": 24
    },
    {
      "epoch": 0.02044989775051125,
      "grad_norm": 0.8400692939758301,
      "learning_rate": 9.330263157894737e-05,
      "loss": 0.9552,
      "step": 25
    },
    {
      "epoch": 0.0212678936605317,
      "grad_norm": 0.6418869495391846,
      "learning_rate": 9.276947368421051e-05,
      "loss": 0.4748,
      "step": 26
    },
    {
      "epoch": 0.022085889570552148,
      "grad_norm": 0.7171022295951843,
      "learning_rate": 9.223631578947369e-05,
      "loss": 0.6061,
      "step": 27
    },
    {
      "epoch": 0.022903885480572598,
      "grad_norm": 0.9005898237228394,
      "learning_rate": 9.170315789473684e-05,
      "loss": 0.7294,
      "step": 28
    },
    {
      "epoch": 0.023721881390593048,
      "grad_norm": 0.853922426700592,
      "learning_rate": 9.117e-05,
      "loss": 0.8019,
      "step": 29
    },
    {
      "epoch": 0.024539877300613498,
      "grad_norm": 0.6506239175796509,
      "learning_rate": 9.063684210526316e-05,
      "loss": 0.5485,
      "step": 30
    },
    {
      "epoch": 0.025357873210633947,
      "grad_norm": 0.8468363285064697,
      "learning_rate": 9.010368421052632e-05,
      "loss": 0.8216,
      "step": 31
    },
    {
      "epoch": 0.026175869120654397,
      "grad_norm": 1.2255985736846924,
      "learning_rate": 8.957052631578946e-05,
      "loss": 0.499,
      "step": 32
    },
    {
      "epoch": 0.026993865030674847,
      "grad_norm": 0.7245408296585083,
      "learning_rate": 8.903736842105263e-05,
      "loss": 0.4545,
      "step": 33
    },
    {
      "epoch": 0.027811860940695297,
      "grad_norm": 0.5149531960487366,
      "learning_rate": 8.850421052631579e-05,
      "loss": 0.3527,
      "step": 34
    },
    {
      "epoch": 0.028629856850715747,
      "grad_norm": 0.7418886423110962,
      "learning_rate": 8.797105263157895e-05,
      "loss": 0.6099,
      "step": 35
    },
    {
      "epoch": 0.029447852760736196,
      "grad_norm": 0.3611685037612915,
      "learning_rate": 8.743789473684211e-05,
      "loss": 0.152,
      "step": 36
    },
    {
      "epoch": 0.030265848670756646,
      "grad_norm": 0.2011786550283432,
      "learning_rate": 8.690473684210526e-05,
      "loss": 0.0166,
      "step": 37
    },
    {
      "epoch": 0.031083844580777096,
      "grad_norm": 0.09635209292173386,
      "learning_rate": 8.637157894736842e-05,
      "loss": 0.0076,
      "step": 38
    },
    {
      "epoch": 0.03190184049079755,
      "grad_norm": 0.08170394599437714,
      "learning_rate": 8.583842105263158e-05,
      "loss": 0.0055,
      "step": 39
    },
    {
      "epoch": 0.032719836400818,
      "grad_norm": 0.10278013348579407,
      "learning_rate": 8.530526315789472e-05,
      "loss": 0.0038,
      "step": 40
    },
    {
      "epoch": 0.03353783231083845,
      "grad_norm": 0.22206488251686096,
      "learning_rate": 8.47721052631579e-05,
      "loss": 0.0034,
      "step": 41
    },
    {
      "epoch": 0.0343558282208589,
      "grad_norm": 0.06311889737844467,
      "learning_rate": 8.423894736842105e-05,
      "loss": 0.0029,
      "step": 42
    },
    {
      "epoch": 0.03517382413087935,
      "grad_norm": 0.12246158719062805,
      "learning_rate": 8.37057894736842e-05,
      "loss": 0.0043,
      "step": 43
    },
    {
      "epoch": 0.0359918200408998,
      "grad_norm": 0.08296216279268265,
      "learning_rate": 8.317263157894737e-05,
      "loss": 0.0021,
      "step": 44
    },
    {
      "epoch": 0.03680981595092025,
      "grad_norm": 0.053368937224149704,
      "learning_rate": 8.263947368421053e-05,
      "loss": 0.001,
      "step": 45
    },
    {
      "epoch": 0.0376278118609407,
      "grad_norm": 0.0612197071313858,
      "learning_rate": 8.210631578947368e-05,
      "loss": 0.001,
      "step": 46
    },
    {
      "epoch": 0.03844580777096115,
      "grad_norm": 0.03648490086197853,
      "learning_rate": 8.157315789473684e-05,
      "loss": 0.001,
      "step": 47
    },
    {
      "epoch": 0.0392638036809816,
      "grad_norm": 0.020957158878445625,
      "learning_rate": 8.104e-05,
      "loss": 0.0004,
      "step": 48
    },
    {
      "epoch": 0.04008179959100205,
      "grad_norm": 0.31076347827911377,
      "learning_rate": 8.050684210526316e-05,
      "loss": 0.0053,
      "step": 49
    },
    {
      "epoch": 0.0408997955010225,
      "grad_norm": 0.009556309320032597,
      "learning_rate": 7.997368421052632e-05,
      "loss": 0.0002,
      "step": 50
    },
    {
      "epoch": 0.0408997955010225,
      "eval_loss": 0.31697726249694824,
      "eval_runtime": 164.5433,
      "eval_samples_per_second": 3.13,
      "eval_steps_per_second": 0.784,
      "step": 50
    },
    {
      "epoch": 0.04171779141104295,
      "grad_norm": 1.0068371295928955,
      "learning_rate": 7.944052631578947e-05,
      "loss": 0.9885,
      "step": 51
    },
    {
      "epoch": 0.0425357873210634,
      "grad_norm": 0.724956214427948,
      "learning_rate": 7.890736842105263e-05,
      "loss": 0.8083,
      "step": 52
    },
    {
      "epoch": 0.043353783231083846,
      "grad_norm": 0.5116149187088013,
      "learning_rate": 7.837421052631579e-05,
      "loss": 0.7497,
      "step": 53
    },
    {
      "epoch": 0.044171779141104296,
      "grad_norm": 0.5890445709228516,
      "learning_rate": 7.784105263157893e-05,
      "loss": 1.0557,
      "step": 54
    },
    {
      "epoch": 0.044989775051124746,
      "grad_norm": 0.6366136074066162,
      "learning_rate": 7.730789473684211e-05,
      "loss": 1.0897,
      "step": 55
    },
    {
      "epoch": 0.045807770961145196,
      "grad_norm": 0.503930926322937,
      "learning_rate": 7.677473684210526e-05,
      "loss": 0.909,
      "step": 56
    },
    {
      "epoch": 0.046625766871165646,
      "grad_norm": 0.3874259293079376,
      "learning_rate": 7.624157894736842e-05,
      "loss": 0.6214,
      "step": 57
    },
    {
      "epoch": 0.047443762781186095,
      "grad_norm": 0.46610915660858154,
      "learning_rate": 7.570842105263158e-05,
      "loss": 0.5465,
      "step": 58
    },
    {
      "epoch": 0.048261758691206545,
      "grad_norm": 0.38099950551986694,
      "learning_rate": 7.517526315789474e-05,
      "loss": 0.3863,
      "step": 59
    },
    {
      "epoch": 0.049079754601226995,
      "grad_norm": 0.7457447648048401,
      "learning_rate": 7.464210526315789e-05,
      "loss": 0.4988,
      "step": 60
    },
    {
      "epoch": 0.049897750511247445,
      "grad_norm": 0.48318201303482056,
      "learning_rate": 7.410894736842106e-05,
      "loss": 0.6316,
      "step": 61
    },
    {
      "epoch": 0.050715746421267895,
      "grad_norm": 0.41538336873054504,
      "learning_rate": 7.35757894736842e-05,
      "loss": 0.3852,
      "step": 62
    },
    {
      "epoch": 0.051533742331288344,
      "grad_norm": 0.40224334597587585,
      "learning_rate": 7.304263157894737e-05,
      "loss": 0.4715,
      "step": 63
    },
    {
      "epoch": 0.052351738241308794,
      "grad_norm": 0.9810552597045898,
      "learning_rate": 7.250947368421053e-05,
      "loss": 0.6195,
      "step": 64
    },
    {
      "epoch": 0.053169734151329244,
      "grad_norm": 0.930385172367096,
      "learning_rate": 7.197631578947368e-05,
      "loss": 0.6228,
      "step": 65
    },
    {
      "epoch": 0.053987730061349694,
      "grad_norm": 0.5943039655685425,
      "learning_rate": 7.144315789473684e-05,
      "loss": 0.7253,
      "step": 66
    },
    {
      "epoch": 0.054805725971370144,
      "grad_norm": 0.9984376430511475,
      "learning_rate": 7.091e-05,
      "loss": 0.9143,
      "step": 67
    },
    {
      "epoch": 0.05562372188139059,
      "grad_norm": 0.7382859587669373,
      "learning_rate": 7.037684210526316e-05,
      "loss": 0.9344,
      "step": 68
    },
    {
      "epoch": 0.05644171779141104,
      "grad_norm": 0.5910463333129883,
      "learning_rate": 6.984368421052632e-05,
      "loss": 0.5557,
      "step": 69
    },
    {
      "epoch": 0.05725971370143149,
      "grad_norm": 0.5349307060241699,
      "learning_rate": 6.931052631578947e-05,
      "loss": 0.6016,
      "step": 70
    },
    {
      "epoch": 0.05807770961145194,
      "grad_norm": 0.5327895283699036,
      "learning_rate": 6.877736842105263e-05,
      "loss": 0.5221,
      "step": 71
    },
    {
      "epoch": 0.05889570552147239,
      "grad_norm": 0.6906758546829224,
      "learning_rate": 6.824421052631579e-05,
      "loss": 0.8609,
      "step": 72
    },
    {
      "epoch": 0.05971370143149284,
      "grad_norm": 2.961278200149536,
      "learning_rate": 6.771105263157895e-05,
      "loss": 0.707,
      "step": 73
    },
    {
      "epoch": 0.06053169734151329,
      "grad_norm": 0.5922215580940247,
      "learning_rate": 6.71778947368421e-05,
      "loss": 0.6751,
      "step": 74
    },
    {
      "epoch": 0.06134969325153374,
      "grad_norm": 0.7490167617797852,
      "learning_rate": 6.664473684210527e-05,
      "loss": 0.7576,
      "step": 75
    },
    {
      "epoch": 0.06216768916155419,
      "grad_norm": 0.7223999500274658,
      "learning_rate": 6.611157894736842e-05,
      "loss": 0.6025,
      "step": 76
    },
    {
      "epoch": 0.06298568507157465,
      "grad_norm": 0.6571590304374695,
      "learning_rate": 6.557842105263158e-05,
      "loss": 0.7033,
      "step": 77
    },
    {
      "epoch": 0.0638036809815951,
      "grad_norm": 0.5444533824920654,
      "learning_rate": 6.504526315789474e-05,
      "loss": 0.5138,
      "step": 78
    },
    {
      "epoch": 0.06462167689161555,
      "grad_norm": 0.5655301213264465,
      "learning_rate": 6.451210526315789e-05,
      "loss": 0.4987,
      "step": 79
    },
    {
      "epoch": 0.065439672801636,
      "grad_norm": 0.632288932800293,
      "learning_rate": 6.397894736842105e-05,
      "loss": 0.4189,
      "step": 80
    },
    {
      "epoch": 0.06625766871165645,
      "grad_norm": 0.7677326202392578,
      "learning_rate": 6.344578947368421e-05,
      "loss": 0.3,
      "step": 81
    },
    {
      "epoch": 0.0670756646216769,
      "grad_norm": 0.4775019884109497,
      "learning_rate": 6.291263157894737e-05,
      "loss": 0.3159,
      "step": 82
    },
    {
      "epoch": 0.06789366053169735,
      "grad_norm": 0.41117969155311584,
      "learning_rate": 6.237947368421053e-05,
      "loss": 0.317,
      "step": 83
    },
    {
      "epoch": 0.0687116564417178,
      "grad_norm": 0.1944044977426529,
      "learning_rate": 6.184631578947368e-05,
      "loss": 0.074,
      "step": 84
    },
    {
      "epoch": 0.06952965235173825,
      "grad_norm": 0.267262727022171,
      "learning_rate": 6.131315789473684e-05,
      "loss": 0.1004,
      "step": 85
    },
    {
      "epoch": 0.0703476482617587,
      "grad_norm": 0.4343488812446594,
      "learning_rate": 6.078e-05,
      "loss": 0.1652,
      "step": 86
    },
    {
      "epoch": 0.07116564417177915,
      "grad_norm": 0.016880128532648087,
      "learning_rate": 6.024684210526315e-05,
      "loss": 0.0009,
      "step": 87
    },
    {
      "epoch": 0.0719836400817996,
      "grad_norm": 0.22920526564121246,
      "learning_rate": 5.9713684210526305e-05,
      "loss": 0.0066,
      "step": 88
    },
    {
      "epoch": 0.07280163599182005,
      "grad_norm": 0.1432953178882599,
      "learning_rate": 5.918052631578947e-05,
      "loss": 0.002,
      "step": 89
    },
    {
      "epoch": 0.0736196319018405,
      "grad_norm": 0.015287825837731361,
      "learning_rate": 5.8647368421052634e-05,
      "loss": 0.0007,
      "step": 90
    },
    {
      "epoch": 0.07443762781186095,
      "grad_norm": 0.15962694585323334,
      "learning_rate": 5.811421052631579e-05,
      "loss": 0.0084,
      "step": 91
    },
    {
      "epoch": 0.0752556237218814,
      "grad_norm": 0.0835452675819397,
      "learning_rate": 5.758105263157894e-05,
      "loss": 0.0026,
      "step": 92
    },
    {
      "epoch": 0.07607361963190185,
      "grad_norm": 0.3013435900211334,
      "learning_rate": 5.70478947368421e-05,
      "loss": 0.0046,
      "step": 93
    },
    {
      "epoch": 0.0768916155419223,
      "grad_norm": 0.007186358794569969,
      "learning_rate": 5.6514736842105256e-05,
      "loss": 0.0004,
      "step": 94
    },
    {
      "epoch": 0.07770961145194274,
      "grad_norm": 0.0493503175675869,
      "learning_rate": 5.5981578947368424e-05,
      "loss": 0.0019,
      "step": 95
    },
    {
      "epoch": 0.0785276073619632,
      "grad_norm": 0.09706468880176544,
      "learning_rate": 5.544842105263158e-05,
      "loss": 0.0017,
      "step": 96
    },
    {
      "epoch": 0.07934560327198364,
      "grad_norm": 0.0098764318972826,
      "learning_rate": 5.491526315789474e-05,
      "loss": 0.0004,
      "step": 97
    },
    {
      "epoch": 0.0801635991820041,
      "grad_norm": 0.16427290439605713,
      "learning_rate": 5.438210526315789e-05,
      "loss": 0.0069,
      "step": 98
    },
    {
      "epoch": 0.08098159509202454,
      "grad_norm": 0.02355344407260418,
      "learning_rate": 5.384894736842105e-05,
      "loss": 0.0006,
      "step": 99
    },
    {
      "epoch": 0.081799591002045,
      "grad_norm": 0.022215725854039192,
      "learning_rate": 5.331578947368421e-05,
      "loss": 0.0007,
      "step": 100
    },
    {
      "epoch": 0.081799591002045,
      "eval_loss": 0.2767239809036255,
      "eval_runtime": 164.6277,
      "eval_samples_per_second": 3.128,
      "eval_steps_per_second": 0.784,
      "step": 100
    },
    {
      "epoch": 0.08261758691206544,
      "grad_norm": 2.208616256713867,
      "learning_rate": 5.278263157894736e-05,
      "loss": 0.8554,
      "step": 101
    },
    {
      "epoch": 0.0834355828220859,
      "grad_norm": 0.6053175330162048,
      "learning_rate": 5.224947368421053e-05,
      "loss": 0.8102,
      "step": 102
    },
    {
      "epoch": 0.08425357873210634,
      "grad_norm": 0.443279892206192,
      "learning_rate": 5.171631578947368e-05,
      "loss": 0.6613,
      "step": 103
    },
    {
      "epoch": 0.0850715746421268,
      "grad_norm": 0.5657853484153748,
      "learning_rate": 5.1183157894736844e-05,
      "loss": 0.904,
      "step": 104
    },
    {
      "epoch": 0.08588957055214724,
      "grad_norm": 0.5122092366218567,
      "learning_rate": 5.065e-05,
      "loss": 0.7585,
      "step": 105
    },
    {
      "epoch": 0.08670756646216769,
      "grad_norm": 0.4323250353336334,
      "learning_rate": 5.011684210526315e-05,
      "loss": 0.6443,
      "step": 106
    },
    {
      "epoch": 0.08752556237218814,
      "grad_norm": 0.4903777539730072,
      "learning_rate": 4.958368421052631e-05,
      "loss": 0.8381,
      "step": 107
    },
    {
      "epoch": 0.08834355828220859,
      "grad_norm": 0.49713271856307983,
      "learning_rate": 4.9050526315789473e-05,
      "loss": 0.6974,
      "step": 108
    },
    {
      "epoch": 0.08916155419222904,
      "grad_norm": 0.5440729260444641,
      "learning_rate": 4.851736842105263e-05,
      "loss": 0.7326,
      "step": 109
    },
    {
      "epoch": 0.08997955010224949,
      "grad_norm": 0.5971400737762451,
      "learning_rate": 4.798421052631579e-05,
      "loss": 0.8564,
      "step": 110
    },
    {
      "epoch": 0.09079754601226994,
      "grad_norm": 0.4081849157810211,
      "learning_rate": 4.745105263157895e-05,
      "loss": 0.5119,
      "step": 111
    },
    {
      "epoch": 0.09161554192229039,
      "grad_norm": 0.42180880904197693,
      "learning_rate": 4.69178947368421e-05,
      "loss": 0.479,
      "step": 112
    },
    {
      "epoch": 0.09243353783231084,
      "grad_norm": 0.48688748478889465,
      "learning_rate": 4.638473684210526e-05,
      "loss": 0.5893,
      "step": 113
    },
    {
      "epoch": 0.09325153374233129,
      "grad_norm": 0.3098672926425934,
      "learning_rate": 4.585157894736842e-05,
      "loss": 0.3024,
      "step": 114
    },
    {
      "epoch": 0.09406952965235174,
      "grad_norm": 0.3973608911037445,
      "learning_rate": 4.531842105263158e-05,
      "loss": 0.4749,
      "step": 115
    },
    {
      "epoch": 0.09488752556237219,
      "grad_norm": 0.45003950595855713,
      "learning_rate": 4.478526315789473e-05,
      "loss": 0.5641,
      "step": 116
    },
    {
      "epoch": 0.09570552147239264,
      "grad_norm": 0.4103372395038605,
      "learning_rate": 4.425210526315789e-05,
      "loss": 0.3926,
      "step": 117
    },
    {
      "epoch": 0.09652351738241309,
      "grad_norm": 0.5700619220733643,
      "learning_rate": 4.3718947368421054e-05,
      "loss": 0.7772,
      "step": 118
    },
    {
      "epoch": 0.09734151329243354,
      "grad_norm": 0.5302966833114624,
      "learning_rate": 4.318578947368421e-05,
      "loss": 0.5547,
      "step": 119
    },
    {
      "epoch": 0.09815950920245399,
      "grad_norm": 0.5432780981063843,
      "learning_rate": 4.265263157894736e-05,
      "loss": 0.7294,
      "step": 120
    },
    {
      "epoch": 0.09897750511247444,
      "grad_norm": 0.5698531866073608,
      "learning_rate": 4.211947368421052e-05,
      "loss": 0.6319,
      "step": 121
    },
    {
      "epoch": 0.09979550102249489,
      "grad_norm": 0.4369616210460663,
      "learning_rate": 4.1586315789473684e-05,
      "loss": 0.4439,
      "step": 122
    },
    {
      "epoch": 0.10061349693251534,
      "grad_norm": 0.5331543684005737,
      "learning_rate": 4.105315789473684e-05,
      "loss": 0.5258,
      "step": 123
    },
    {
      "epoch": 0.10143149284253579,
      "grad_norm": 0.5208017230033875,
      "learning_rate": 4.052e-05,
      "loss": 0.5332,
      "step": 124
    },
    {
      "epoch": 0.10224948875255624,
      "grad_norm": 0.6325660943984985,
      "learning_rate": 3.998684210526316e-05,
      "loss": 0.7877,
      "step": 125
    },
    {
      "epoch": 0.10306748466257669,
      "grad_norm": 0.8065600991249084,
      "learning_rate": 3.945368421052631e-05,
      "loss": 0.8469,
      "step": 126
    },
    {
      "epoch": 0.10388548057259714,
      "grad_norm": 0.5705050230026245,
      "learning_rate": 3.892052631578947e-05,
      "loss": 0.5351,
      "step": 127
    },
    {
      "epoch": 0.10470347648261759,
      "grad_norm": 0.60113525390625,
      "learning_rate": 3.838736842105263e-05,
      "loss": 0.5405,
      "step": 128
    },
    {
      "epoch": 0.10552147239263804,
      "grad_norm": 0.5440464019775391,
      "learning_rate": 3.785421052631579e-05,
      "loss": 0.5673,
      "step": 129
    },
    {
      "epoch": 0.10633946830265849,
      "grad_norm": 0.6333761215209961,
      "learning_rate": 3.732105263157894e-05,
      "loss": 0.7063,
      "step": 130
    },
    {
      "epoch": 0.10715746421267894,
      "grad_norm": 0.3166744112968445,
      "learning_rate": 3.67878947368421e-05,
      "loss": 0.2672,
      "step": 131
    },
    {
      "epoch": 0.10797546012269939,
      "grad_norm": 0.47239211201667786,
      "learning_rate": 3.6254736842105264e-05,
      "loss": 0.2944,
      "step": 132
    },
    {
      "epoch": 0.10879345603271984,
      "grad_norm": 0.6278908252716064,
      "learning_rate": 3.572157894736842e-05,
      "loss": 0.7175,
      "step": 133
    },
    {
      "epoch": 0.10961145194274029,
      "grad_norm": 6.725371837615967,
      "learning_rate": 3.518842105263158e-05,
      "loss": 0.5899,
      "step": 134
    },
    {
      "epoch": 0.11042944785276074,
      "grad_norm": 0.3569982945919037,
      "learning_rate": 3.465526315789473e-05,
      "loss": 0.2153,
      "step": 135
    },
    {
      "epoch": 0.11124744376278119,
      "grad_norm": 0.8054752945899963,
      "learning_rate": 3.4122105263157894e-05,
      "loss": 0.6044,
      "step": 136
    },
    {
      "epoch": 0.11206543967280164,
      "grad_norm": 0.37957316637039185,
      "learning_rate": 3.358894736842105e-05,
      "loss": 0.2575,
      "step": 137
    },
    {
      "epoch": 0.11288343558282209,
      "grad_norm": 0.33962732553482056,
      "learning_rate": 3.305578947368421e-05,
      "loss": 0.1472,
      "step": 138
    },
    {
      "epoch": 0.11370143149284254,
      "grad_norm": 0.1770872324705124,
      "learning_rate": 3.252263157894737e-05,
      "loss": 0.008,
      "step": 139
    },
    {
      "epoch": 0.11451942740286299,
      "grad_norm": 0.09861530363559723,
      "learning_rate": 3.198947368421052e-05,
      "loss": 0.0033,
      "step": 140
    },
    {
      "epoch": 0.11533742331288344,
      "grad_norm": 0.1032843068242073,
      "learning_rate": 3.1456315789473684e-05,
      "loss": 0.0027,
      "step": 141
    },
    {
      "epoch": 0.11615541922290389,
      "grad_norm": 0.11989390105009079,
      "learning_rate": 3.092315789473684e-05,
      "loss": 0.0018,
      "step": 142
    },
    {
      "epoch": 0.11697341513292434,
      "grad_norm": 0.01104150153696537,
      "learning_rate": 3.039e-05,
      "loss": 0.0004,
      "step": 143
    },
    {
      "epoch": 0.11779141104294479,
      "grad_norm": 0.01930282451212406,
      "learning_rate": 2.9856842105263153e-05,
      "loss": 0.0005,
      "step": 144
    },
    {
      "epoch": 0.11860940695296524,
      "grad_norm": 0.15893378853797913,
      "learning_rate": 2.9323684210526317e-05,
      "loss": 0.0031,
      "step": 145
    },
    {
      "epoch": 0.11942740286298568,
      "grad_norm": 0.03184283524751663,
      "learning_rate": 2.879052631578947e-05,
      "loss": 0.0009,
      "step": 146
    },
    {
      "epoch": 0.12024539877300613,
      "grad_norm": 0.06102335825562477,
      "learning_rate": 2.8257368421052628e-05,
      "loss": 0.0013,
      "step": 147
    },
    {
      "epoch": 0.12106339468302658,
      "grad_norm": 0.0802997276186943,
      "learning_rate": 2.772421052631579e-05,
      "loss": 0.0015,
      "step": 148
    },
    {
      "epoch": 0.12188139059304703,
      "grad_norm": 0.02622400037944317,
      "learning_rate": 2.7191052631578946e-05,
      "loss": 0.0005,
      "step": 149
    },
    {
      "epoch": 0.12269938650306748,
      "grad_norm": 0.019685884937644005,
      "learning_rate": 2.6657894736842104e-05,
      "loss": 0.0006,
      "step": 150
    },
    {
      "epoch": 0.12269938650306748,
      "eval_loss": 0.22924812138080597,
      "eval_runtime": 164.6274,
      "eval_samples_per_second": 3.128,
      "eval_steps_per_second": 0.784,
      "step": 150
    },
    {
      "epoch": 0.12351738241308793,
      "grad_norm": 0.42591241002082825,
      "learning_rate": 2.6124736842105265e-05,
      "loss": 0.847,
      "step": 151
    },
    {
      "epoch": 0.12433537832310838,
      "grad_norm": 0.37749016284942627,
      "learning_rate": 2.5591578947368422e-05,
      "loss": 0.643,
      "step": 152
    },
    {
      "epoch": 0.12515337423312883,
      "grad_norm": 7.373504638671875,
      "learning_rate": 2.5058421052631576e-05,
      "loss": 1.1166,
      "step": 153
    },
    {
      "epoch": 0.1259713701431493,
      "grad_norm": 0.4218708276748657,
      "learning_rate": 2.4525263157894737e-05,
      "loss": 0.5926,
      "step": 154
    },
    {
      "epoch": 0.12678936605316973,
      "grad_norm": 0.415558397769928,
      "learning_rate": 2.3992105263157894e-05,
      "loss": 0.539,
      "step": 155
    },
    {
      "epoch": 0.1276073619631902,
      "grad_norm": 0.367865651845932,
      "learning_rate": 2.345894736842105e-05,
      "loss": 0.4419,
      "step": 156
    },
    {
      "epoch": 0.12842535787321063,
      "grad_norm": 0.47910165786743164,
      "learning_rate": 2.292578947368421e-05,
      "loss": 0.72,
      "step": 157
    },
    {
      "epoch": 0.1292433537832311,
      "grad_norm": 0.547726035118103,
      "learning_rate": 2.2392631578947366e-05,
      "loss": 0.7997,
      "step": 158
    },
    {
      "epoch": 0.13006134969325153,
      "grad_norm": 0.49771469831466675,
      "learning_rate": 2.1859473684210527e-05,
      "loss": 0.7018,
      "step": 159
    },
    {
      "epoch": 0.130879345603272,
      "grad_norm": 0.6116258502006531,
      "learning_rate": 2.132631578947368e-05,
      "loss": 0.907,
      "step": 160
    },
    {
      "epoch": 0.13169734151329243,
      "grad_norm": 0.5866420865058899,
      "learning_rate": 2.0793157894736842e-05,
      "loss": 0.6216,
      "step": 161
    },
    {
      "epoch": 0.1325153374233129,
      "grad_norm": 0.6702650785446167,
      "learning_rate": 2.026e-05,
      "loss": 0.6452,
      "step": 162
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.5496453046798706,
      "learning_rate": 1.9726842105263157e-05,
      "loss": 0.6332,
      "step": 163
    },
    {
      "epoch": 0.1341513292433538,
      "grad_norm": 0.37603631615638733,
      "learning_rate": 1.9193684210526314e-05,
      "loss": 0.3876,
      "step": 164
    },
    {
      "epoch": 0.13496932515337423,
      "grad_norm": 0.4126095473766327,
      "learning_rate": 1.866052631578947e-05,
      "loss": 0.4168,
      "step": 165
    },
    {
      "epoch": 0.1357873210633947,
      "grad_norm": 0.6646726131439209,
      "learning_rate": 1.8127368421052632e-05,
      "loss": 0.8142,
      "step": 166
    },
    {
      "epoch": 0.13660531697341513,
      "grad_norm": 0.3889711797237396,
      "learning_rate": 1.759421052631579e-05,
      "loss": 0.4465,
      "step": 167
    },
    {
      "epoch": 0.1374233128834356,
      "grad_norm": 0.44813233613967896,
      "learning_rate": 1.7061052631578947e-05,
      "loss": 0.4387,
      "step": 168
    },
    {
      "epoch": 0.13824130879345603,
      "grad_norm": 0.4522460699081421,
      "learning_rate": 1.6527894736842104e-05,
      "loss": 0.4947,
      "step": 169
    },
    {
      "epoch": 0.1390593047034765,
      "grad_norm": 0.5248112082481384,
      "learning_rate": 1.599473684210526e-05,
      "loss": 0.5836,
      "step": 170
    },
    {
      "epoch": 0.13987730061349693,
      "grad_norm": 0.6201620697975159,
      "learning_rate": 1.546157894736842e-05,
      "loss": 0.8913,
      "step": 171
    },
    {
      "epoch": 0.1406952965235174,
      "grad_norm": 0.565233051776886,
      "learning_rate": 1.4928421052631576e-05,
      "loss": 0.5188,
      "step": 172
    },
    {
      "epoch": 0.14151329243353783,
      "grad_norm": 0.4735608994960785,
      "learning_rate": 1.4395263157894735e-05,
      "loss": 0.3935,
      "step": 173
    },
    {
      "epoch": 0.1423312883435583,
      "grad_norm": 0.6751230955123901,
      "learning_rate": 1.3862105263157895e-05,
      "loss": 0.7061,
      "step": 174
    },
    {
      "epoch": 0.14314928425357873,
      "grad_norm": 0.5896326303482056,
      "learning_rate": 1.3328947368421052e-05,
      "loss": 0.6753,
      "step": 175
    },
    {
      "epoch": 0.1439672801635992,
      "grad_norm": 0.46921586990356445,
      "learning_rate": 1.2795789473684211e-05,
      "loss": 0.4023,
      "step": 176
    },
    {
      "epoch": 0.14478527607361963,
      "grad_norm": 0.8884191513061523,
      "learning_rate": 1.2262631578947368e-05,
      "loss": 0.5684,
      "step": 177
    },
    {
      "epoch": 0.1456032719836401,
      "grad_norm": 0.34956350922584534,
      "learning_rate": 1.1729473684210526e-05,
      "loss": 0.1983,
      "step": 178
    },
    {
      "epoch": 0.14642126789366053,
      "grad_norm": 0.6150217056274414,
      "learning_rate": 1.1196315789473683e-05,
      "loss": 0.6407,
      "step": 179
    },
    {
      "epoch": 0.147239263803681,
      "grad_norm": 0.41867491602897644,
      "learning_rate": 1.066315789473684e-05,
      "loss": 0.3322,
      "step": 180
    },
    {
      "epoch": 0.14805725971370143,
      "grad_norm": 0.6983818411827087,
      "learning_rate": 1.013e-05,
      "loss": 0.7427,
      "step": 181
    },
    {
      "epoch": 0.1488752556237219,
      "grad_norm": 0.7040908336639404,
      "learning_rate": 9.596842105263157e-06,
      "loss": 0.6962,
      "step": 182
    },
    {
      "epoch": 0.14969325153374233,
      "grad_norm": 0.6211279630661011,
      "learning_rate": 9.063684210526316e-06,
      "loss": 0.5084,
      "step": 183
    },
    {
      "epoch": 0.1505112474437628,
      "grad_norm": 0.4377440810203552,
      "learning_rate": 8.530526315789473e-06,
      "loss": 0.226,
      "step": 184
    },
    {
      "epoch": 0.15132924335378323,
      "grad_norm": 0.1414121389389038,
      "learning_rate": 7.99736842105263e-06,
      "loss": 0.052,
      "step": 185
    },
    {
      "epoch": 0.1521472392638037,
      "grad_norm": 0.06823990494012833,
      "learning_rate": 7.464210526315788e-06,
      "loss": 0.0031,
      "step": 186
    },
    {
      "epoch": 0.15296523517382413,
      "grad_norm": 0.013092203065752983,
      "learning_rate": 6.931052631578947e-06,
      "loss": 0.0006,
      "step": 187
    },
    {
      "epoch": 0.1537832310838446,
      "grad_norm": 0.19664902985095978,
      "learning_rate": 6.3978947368421055e-06,
      "loss": 0.0032,
      "step": 188
    },
    {
      "epoch": 0.15460122699386503,
      "grad_norm": 0.016594722867012024,
      "learning_rate": 5.864736842105263e-06,
      "loss": 0.0006,
      "step": 189
    },
    {
      "epoch": 0.1554192229038855,
      "grad_norm": 0.009124848060309887,
      "learning_rate": 5.33157894736842e-06,
      "loss": 0.0005,
      "step": 190
    },
    {
      "epoch": 0.15623721881390593,
      "grad_norm": 0.10051782429218292,
      "learning_rate": 4.7984210526315785e-06,
      "loss": 0.0042,
      "step": 191
    },
    {
      "epoch": 0.1570552147239264,
      "grad_norm": 0.0568082332611084,
      "learning_rate": 4.265263157894737e-06,
      "loss": 0.0029,
      "step": 192
    },
    {
      "epoch": 0.15787321063394683,
      "grad_norm": 0.09655116498470306,
      "learning_rate": 3.732105263157894e-06,
      "loss": 0.0036,
      "step": 193
    },
    {
      "epoch": 0.1586912065439673,
      "grad_norm": 0.17335928976535797,
      "learning_rate": 3.1989473684210527e-06,
      "loss": 0.007,
      "step": 194
    },
    {
      "epoch": 0.15950920245398773,
      "grad_norm": 0.008331399410963058,
      "learning_rate": 2.66578947368421e-06,
      "loss": 0.0005,
      "step": 195
    },
    {
      "epoch": 0.1603271983640082,
      "grad_norm": 0.1623714417219162,
      "learning_rate": 2.1326315789473684e-06,
      "loss": 0.0043,
      "step": 196
    },
    {
      "epoch": 0.16114519427402862,
      "grad_norm": 0.05319036543369293,
      "learning_rate": 1.5994736842105264e-06,
      "loss": 0.0018,
      "step": 197
    },
    {
      "epoch": 0.1619631901840491,
      "grad_norm": 0.006065657362341881,
      "learning_rate": 1.0663157894736842e-06,
      "loss": 0.0004,
      "step": 198
    },
    {
      "epoch": 0.16278118609406952,
      "grad_norm": 0.010582847520709038,
      "learning_rate": 5.331578947368421e-07,
      "loss": 0.0005,
      "step": 199
    },
    {
      "epoch": 0.16359918200409,
      "grad_norm": 0.026805628091096878,
      "learning_rate": 0.0,
      "loss": 0.001,
      "step": 200
    },
    {
      "epoch": 0.16359918200409,
      "eval_loss": 0.21579746901988983,
      "eval_runtime": 165.9203,
      "eval_samples_per_second": 3.104,
      "eval_steps_per_second": 0.777,
      "step": 200
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.484049111154688e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}