{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 338,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002962962962962963,
      "grad_norm": 26.196367263793945,
      "learning_rate": 0.0,
      "loss": 1.391,
      "step": 1
    },
    {
      "epoch": 0.005925925925925926,
      "grad_norm": 29.17486572265625,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5631,
      "step": 2
    },
    {
      "epoch": 0.008888888888888889,
      "grad_norm": 24.81805419921875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3547,
      "step": 3
    },
    {
      "epoch": 0.011851851851851851,
      "grad_norm": 24.45110321044922,
      "learning_rate": 6e-06,
      "loss": 1.0026,
      "step": 4
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 16.00918960571289,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7801,
      "step": 5
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 11.325848579406738,
      "learning_rate": 1e-05,
      "loss": 0.7193,
      "step": 6
    },
    {
      "epoch": 0.02074074074074074,
      "grad_norm": 7.38839864730835,
      "learning_rate": 9.96996996996997e-06,
      "loss": 0.5335,
      "step": 7
    },
    {
      "epoch": 0.023703703703703703,
      "grad_norm": 5.825254917144775,
      "learning_rate": 9.93993993993994e-06,
      "loss": 0.3573,
      "step": 8
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 4.4633026123046875,
      "learning_rate": 9.90990990990991e-06,
      "loss": 0.3796,
      "step": 9
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 4.053958415985107,
      "learning_rate": 9.879879879879881e-06,
      "loss": 0.3977,
      "step": 10
    },
    {
      "epoch": 0.03259259259259259,
      "grad_norm": 2.752934217453003,
      "learning_rate": 9.849849849849851e-06,
      "loss": 0.2743,
      "step": 11
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 3.463881254196167,
      "learning_rate": 9.81981981981982e-06,
      "loss": 0.3572,
      "step": 12
    },
    {
      "epoch": 0.03851851851851852,
      "grad_norm": 2.3422250747680664,
      "learning_rate": 9.78978978978979e-06,
      "loss": 0.2064,
      "step": 13
    },
    {
      "epoch": 0.04148148148148148,
      "grad_norm": 3.0999391078948975,
      "learning_rate": 9.75975975975976e-06,
      "loss": 0.3499,
      "step": 14
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.3502352237701416,
      "learning_rate": 9.729729729729732e-06,
      "loss": 0.2156,
      "step": 15
    },
    {
      "epoch": 0.047407407407407405,
      "grad_norm": 2.616212844848633,
      "learning_rate": 9.699699699699701e-06,
      "loss": 0.2617,
      "step": 16
    },
    {
      "epoch": 0.05037037037037037,
      "grad_norm": 2.4553725719451904,
      "learning_rate": 9.669669669669671e-06,
      "loss": 0.2359,
      "step": 17
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 1.943063735961914,
      "learning_rate": 9.63963963963964e-06,
      "loss": 0.1545,
      "step": 18
    },
    {
      "epoch": 0.056296296296296296,
      "grad_norm": 2.594413995742798,
      "learning_rate": 9.60960960960961e-06,
      "loss": 0.252,
      "step": 19
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 2.310849905014038,
      "learning_rate": 9.57957957957958e-06,
      "loss": 0.2652,
      "step": 20
    },
    {
      "epoch": 0.06222222222222222,
      "grad_norm": 1.744059443473816,
      "learning_rate": 9.54954954954955e-06,
      "loss": 0.1433,
      "step": 21
    },
    {
      "epoch": 0.06518518518518518,
      "grad_norm": 2.6847920417785645,
      "learning_rate": 9.51951951951952e-06,
      "loss": 0.2493,
      "step": 22
    },
    {
      "epoch": 0.06814814814814815,
      "grad_norm": 2.659426689147949,
      "learning_rate": 9.489489489489491e-06,
      "loss": 0.2775,
      "step": 23
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 2.5133509635925293,
      "learning_rate": 9.45945945945946e-06,
      "loss": 0.2799,
      "step": 24
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.032827377319336,
      "learning_rate": 9.42942942942943e-06,
      "loss": 0.1641,
      "step": 25
    },
    {
      "epoch": 0.07703703703703704,
      "grad_norm": 2.1885931491851807,
      "learning_rate": 9.3993993993994e-06,
      "loss": 0.2202,
      "step": 26
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.6966447830200195,
      "learning_rate": 9.36936936936937e-06,
      "loss": 0.2697,
      "step": 27
    },
    {
      "epoch": 0.08296296296296296,
      "grad_norm": 2.327059268951416,
      "learning_rate": 9.339339339339341e-06,
      "loss": 0.2849,
      "step": 28
    },
    {
      "epoch": 0.08592592592592592,
      "grad_norm": 2.228886365890503,
      "learning_rate": 9.30930930930931e-06,
      "loss": 0.2232,
      "step": 29
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 2.055875062942505,
      "learning_rate": 9.27927927927928e-06,
      "loss": 0.1805,
      "step": 30
    },
    {
      "epoch": 0.09185185185185185,
      "grad_norm": 1.7031993865966797,
      "learning_rate": 9.24924924924925e-06,
      "loss": 0.1407,
      "step": 31
    },
    {
      "epoch": 0.09481481481481481,
      "grad_norm": 1.368647575378418,
      "learning_rate": 9.21921921921922e-06,
      "loss": 0.0936,
      "step": 32
    },
    {
      "epoch": 0.09777777777777778,
      "grad_norm": 1.511066198348999,
      "learning_rate": 9.189189189189191e-06,
      "loss": 0.133,
      "step": 33
    },
    {
      "epoch": 0.10074074074074074,
      "grad_norm": 1.9479334354400635,
      "learning_rate": 9.15915915915916e-06,
      "loss": 0.1778,
      "step": 34
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 2.1655945777893066,
      "learning_rate": 9.129129129129129e-06,
      "loss": 0.2445,
      "step": 35
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 2.039379119873047,
      "learning_rate": 9.0990990990991e-06,
      "loss": 0.1665,
      "step": 36
    },
    {
      "epoch": 0.10962962962962963,
      "grad_norm": 2.154710531234741,
      "learning_rate": 9.06906906906907e-06,
      "loss": 0.2167,
      "step": 37
    },
    {
      "epoch": 0.11259259259259259,
      "grad_norm": 2.1844663619995117,
      "learning_rate": 9.03903903903904e-06,
      "loss": 0.2034,
      "step": 38
    },
    {
      "epoch": 0.11555555555555555,
      "grad_norm": 1.6541115045547485,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.1286,
      "step": 39
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.522692084312439,
      "learning_rate": 8.97897897897898e-06,
      "loss": 0.1416,
      "step": 40
    },
    {
      "epoch": 0.12148148148148148,
      "grad_norm": 1.9426664113998413,
      "learning_rate": 8.94894894894895e-06,
      "loss": 0.1904,
      "step": 41
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 2.354405164718628,
      "learning_rate": 8.91891891891892e-06,
      "loss": 0.2436,
      "step": 42
    },
    {
      "epoch": 0.1274074074074074,
      "grad_norm": 1.4631575345993042,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1045,
      "step": 43
    },
    {
      "epoch": 0.13037037037037036,
      "grad_norm": 1.5969018936157227,
      "learning_rate": 8.85885885885886e-06,
      "loss": 0.1275,
      "step": 44
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 2.119080066680908,
      "learning_rate": 8.82882882882883e-06,
      "loss": 0.1944,
      "step": 45
    },
    {
      "epoch": 0.1362962962962963,
      "grad_norm": 2.2200496196746826,
      "learning_rate": 8.798798798798799e-06,
      "loss": 0.2196,
      "step": 46
    },
    {
      "epoch": 0.13925925925925925,
      "grad_norm": 2.9208028316497803,
      "learning_rate": 8.768768768768769e-06,
      "loss": 0.2964,
      "step": 47
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 1.5756683349609375,
      "learning_rate": 8.738738738738739e-06,
      "loss": 0.1151,
      "step": 48
    },
    {
      "epoch": 0.1451851851851852,
      "grad_norm": 1.8176603317260742,
      "learning_rate": 8.70870870870871e-06,
      "loss": 0.1538,
      "step": 49
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.403080701828003,
      "learning_rate": 8.67867867867868e-06,
      "loss": 0.1322,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "eval_loss": 0.16341860592365265,
      "eval_runtime": 36.1975,
      "eval_samples_per_second": 16.576,
      "eval_steps_per_second": 8.288,
      "step": 50
    },
    {
      "epoch": 0.1511111111111111,
      "grad_norm": 2.2376205921173096,
      "learning_rate": 8.64864864864865e-06,
      "loss": 0.2316,
      "step": 51
    },
    {
      "epoch": 0.15407407407407409,
      "grad_norm": 1.9774130582809448,
      "learning_rate": 8.618618618618619e-06,
      "loss": 0.1877,
      "step": 52
    },
    {
      "epoch": 0.15703703703703703,
      "grad_norm": 2.0866613388061523,
      "learning_rate": 8.588588588588589e-06,
      "loss": 0.2153,
      "step": 53
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.348820686340332,
      "learning_rate": 8.55855855855856e-06,
      "loss": 0.2053,
      "step": 54
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 1.2919985055923462,
      "learning_rate": 8.52852852852853e-06,
      "loss": 0.1013,
      "step": 55
    },
    {
      "epoch": 0.16592592592592592,
      "grad_norm": 1.9843566417694092,
      "learning_rate": 8.4984984984985e-06,
      "loss": 0.172,
      "step": 56
    },
    {
      "epoch": 0.1688888888888889,
      "grad_norm": 1.6446937322616577,
      "learning_rate": 8.46846846846847e-06,
      "loss": 0.1362,
      "step": 57
    },
    {
      "epoch": 0.17185185185185184,
      "grad_norm": 1.5656867027282715,
      "learning_rate": 8.438438438438439e-06,
      "loss": 0.1152,
      "step": 58
    },
    {
      "epoch": 0.1748148148148148,
      "grad_norm": 1.910049319267273,
      "learning_rate": 8.408408408408409e-06,
      "loss": 0.184,
      "step": 59
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.6699490547180176,
      "learning_rate": 8.378378378378378e-06,
      "loss": 0.1688,
      "step": 60
    },
    {
      "epoch": 0.18074074074074073,
      "grad_norm": 1.6635932922363281,
      "learning_rate": 8.348348348348348e-06,
      "loss": 0.1479,
      "step": 61
    },
    {
      "epoch": 0.1837037037037037,
      "grad_norm": 1.427409291267395,
      "learning_rate": 8.31831831831832e-06,
      "loss": 0.1207,
      "step": 62
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 2.2027547359466553,
      "learning_rate": 8.288288288288289e-06,
      "loss": 0.2201,
      "step": 63
    },
    {
      "epoch": 0.18962962962962962,
      "grad_norm": 1.492387294769287,
      "learning_rate": 8.258258258258259e-06,
      "loss": 0.1497,
      "step": 64
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 1.8828175067901611,
      "learning_rate": 8.228228228228229e-06,
      "loss": 0.1746,
      "step": 65
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 1.9826329946517944,
      "learning_rate": 8.198198198198198e-06,
      "loss": 0.1461,
      "step": 66
    },
    {
      "epoch": 0.1985185185185185,
      "grad_norm": 2.1321780681610107,
      "learning_rate": 8.16816816816817e-06,
      "loss": 0.2139,
      "step": 67
    },
    {
      "epoch": 0.20148148148148148,
      "grad_norm": 2.7579076290130615,
      "learning_rate": 8.13813813813814e-06,
      "loss": 0.272,
      "step": 68
    },
    {
      "epoch": 0.20444444444444446,
      "grad_norm": 2.14863920211792,
      "learning_rate": 8.108108108108109e-06,
      "loss": 0.2057,
      "step": 69
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 1.1974773406982422,
      "learning_rate": 8.078078078078079e-06,
      "loss": 0.109,
      "step": 70
    },
    {
      "epoch": 0.21037037037037037,
      "grad_norm": 2.038372278213501,
      "learning_rate": 8.048048048048048e-06,
      "loss": 0.1904,
      "step": 71
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 2.067734479904175,
      "learning_rate": 8.018018018018018e-06,
      "loss": 0.1815,
      "step": 72
    },
    {
      "epoch": 0.2162962962962963,
      "grad_norm": 1.6146552562713623,
      "learning_rate": 7.987987987987988e-06,
      "loss": 0.1311,
      "step": 73
    },
    {
      "epoch": 0.21925925925925926,
      "grad_norm": 1.4429906606674194,
      "learning_rate": 7.95795795795796e-06,
      "loss": 0.1079,
      "step": 74
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.6207659244537354,
      "learning_rate": 7.927927927927929e-06,
      "loss": 0.1286,
      "step": 75
    },
    {
      "epoch": 0.22518518518518518,
      "grad_norm": 1.74688720703125,
      "learning_rate": 7.897897897897899e-06,
      "loss": 0.1632,
      "step": 76
    },
    {
      "epoch": 0.22814814814814816,
      "grad_norm": 2.2548272609710693,
      "learning_rate": 7.867867867867868e-06,
      "loss": 0.2112,
      "step": 77
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 1.803618311882019,
      "learning_rate": 7.837837837837838e-06,
      "loss": 0.1652,
      "step": 78
    },
    {
      "epoch": 0.23407407407407407,
      "grad_norm": 1.5255917310714722,
      "learning_rate": 7.807807807807808e-06,
      "loss": 0.1226,
      "step": 79
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.7720850706100464,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.1611,
      "step": 80
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.6371973752975464,
      "learning_rate": 7.747747747747749e-06,
      "loss": 0.1605,
      "step": 81
    },
    {
      "epoch": 0.24296296296296296,
      "grad_norm": 1.882552981376648,
      "learning_rate": 7.717717717717719e-06,
      "loss": 0.1332,
      "step": 82
    },
    {
      "epoch": 0.24592592592592594,
      "grad_norm": 1.3123418092727661,
      "learning_rate": 7.687687687687688e-06,
      "loss": 0.1108,
      "step": 83
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 1.6034280061721802,
      "learning_rate": 7.657657657657658e-06,
      "loss": 0.137,
      "step": 84
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 1.7470242977142334,
      "learning_rate": 7.6276276276276285e-06,
      "loss": 0.1744,
      "step": 85
    },
    {
      "epoch": 0.2548148148148148,
      "grad_norm": 1.441054344177246,
      "learning_rate": 7.597597597597598e-06,
      "loss": 0.1511,
      "step": 86
    },
    {
      "epoch": 0.2577777777777778,
      "grad_norm": 2.028843402862549,
      "learning_rate": 7.567567567567569e-06,
      "loss": 0.2266,
      "step": 87
    },
    {
      "epoch": 0.2607407407407407,
      "grad_norm": 1.9553054571151733,
      "learning_rate": 7.5375375375375385e-06,
      "loss": 0.2055,
      "step": 88
    },
    {
      "epoch": 0.2637037037037037,
      "grad_norm": 1.4769302606582642,
      "learning_rate": 7.507507507507507e-06,
      "loss": 0.1306,
      "step": 89
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.769997000694275,
      "learning_rate": 7.477477477477479e-06,
      "loss": 0.1554,
      "step": 90
    },
    {
      "epoch": 0.2696296296296296,
      "grad_norm": 1.8313355445861816,
      "learning_rate": 7.447447447447448e-06,
      "loss": 0.2039,
      "step": 91
    },
    {
      "epoch": 0.2725925925925926,
      "grad_norm": 1.4959523677825928,
      "learning_rate": 7.417417417417418e-06,
      "loss": 0.1205,
      "step": 92
    },
    {
      "epoch": 0.27555555555555555,
      "grad_norm": 1.3079489469528198,
      "learning_rate": 7.387387387387388e-06,
      "loss": 0.0944,
      "step": 93
    },
    {
      "epoch": 0.2785185185185185,
      "grad_norm": 2.2171454429626465,
      "learning_rate": 7.3573573573573575e-06,
      "loss": 0.2488,
      "step": 94
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 1.5640006065368652,
      "learning_rate": 7.327327327327328e-06,
      "loss": 0.1513,
      "step": 95
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 1.7839136123657227,
      "learning_rate": 7.297297297297298e-06,
      "loss": 0.1784,
      "step": 96
    },
    {
      "epoch": 0.2874074074074074,
      "grad_norm": 1.7673215866088867,
      "learning_rate": 7.267267267267268e-06,
      "loss": 0.197,
      "step": 97
    },
    {
      "epoch": 0.2903703703703704,
      "grad_norm": 1.725556492805481,
      "learning_rate": 7.237237237237238e-06,
      "loss": 0.166,
      "step": 98
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 1.9898401498794556,
      "learning_rate": 7.207207207207208e-06,
      "loss": 0.2503,
      "step": 99
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.5718384981155396,
      "learning_rate": 7.177177177177178e-06,
      "loss": 0.1839,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 0.15100570023059845,
      "eval_runtime": 34.8201,
      "eval_samples_per_second": 17.231,
      "eval_steps_per_second": 8.616,
      "step": 100
    },
    {
      "epoch": 0.2992592592592593,
      "grad_norm": 1.6021071672439575,
      "learning_rate": 7.147147147147148e-06,
      "loss": 0.12,
      "step": 101
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 1.818358302116394,
      "learning_rate": 7.117117117117117e-06,
      "loss": 0.1723,
      "step": 102
    },
    {
      "epoch": 0.30518518518518517,
      "grad_norm": 2.344231605529785,
      "learning_rate": 7.087087087087087e-06,
      "loss": 0.2502,
      "step": 103
    },
    {
      "epoch": 0.30814814814814817,
      "grad_norm": 1.6187502145767212,
      "learning_rate": 7.057057057057057e-06,
      "loss": 0.1484,
      "step": 104
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 2.0236594676971436,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.2375,
      "step": 105
    },
    {
      "epoch": 0.31407407407407406,
      "grad_norm": 1.3421907424926758,
      "learning_rate": 6.996996996996997e-06,
      "loss": 0.1248,
      "step": 106
    },
    {
      "epoch": 0.31703703703703706,
      "grad_norm": 1.7137436866760254,
      "learning_rate": 6.966966966966967e-06,
      "loss": 0.1327,
      "step": 107
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.5430712699890137,
      "learning_rate": 6.936936936936938e-06,
      "loss": 0.1377,
      "step": 108
    },
    {
      "epoch": 0.32296296296296295,
      "grad_norm": 1.8252489566802979,
      "learning_rate": 6.906906906906907e-06,
      "loss": 0.1858,
      "step": 109
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 1.6401363611221313,
      "learning_rate": 6.876876876876878e-06,
      "loss": 0.1688,
      "step": 110
    },
    {
      "epoch": 0.3288888888888889,
      "grad_norm": 2.00161075592041,
      "learning_rate": 6.846846846846848e-06,
      "loss": 0.2185,
      "step": 111
    },
    {
      "epoch": 0.33185185185185184,
      "grad_norm": 1.5096336603164673,
      "learning_rate": 6.816816816816817e-06,
      "loss": 0.1512,
      "step": 112
    },
    {
      "epoch": 0.3348148148148148,
      "grad_norm": 1.5130608081817627,
      "learning_rate": 6.786786786786788e-06,
      "loss": 0.148,
      "step": 113
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 1.9438039064407349,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.1999,
      "step": 114
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 1.6692813634872437,
      "learning_rate": 6.726726726726728e-06,
      "loss": 0.1511,
      "step": 115
    },
    {
      "epoch": 0.3437037037037037,
      "grad_norm": 2.666036605834961,
      "learning_rate": 6.696696696696697e-06,
      "loss": 0.2642,
      "step": 116
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 2.052509069442749,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1502,
      "step": 117
    },
    {
      "epoch": 0.3496296296296296,
      "grad_norm": 2.0105957984924316,
      "learning_rate": 6.636636636636637e-06,
      "loss": 0.2013,
      "step": 118
    },
    {
      "epoch": 0.35259259259259257,
      "grad_norm": 1.9182209968566895,
      "learning_rate": 6.606606606606607e-06,
      "loss": 0.2099,
      "step": 119
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.5754648447036743,
      "learning_rate": 6.5765765765765775e-06,
      "loss": 0.1649,
      "step": 120
    },
    {
      "epoch": 0.3585185185185185,
      "grad_norm": 1.600990891456604,
      "learning_rate": 6.546546546546547e-06,
      "loss": 0.1654,
      "step": 121
    },
    {
      "epoch": 0.36148148148148146,
      "grad_norm": 1.3771768808364868,
      "learning_rate": 6.516516516516517e-06,
      "loss": 0.1339,
      "step": 122
    },
    {
      "epoch": 0.36444444444444446,
      "grad_norm": 1.6896615028381348,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.1452,
      "step": 123
    },
    {
      "epoch": 0.3674074074074074,
      "grad_norm": 2.2747747898101807,
      "learning_rate": 6.456456456456457e-06,
      "loss": 0.2534,
      "step": 124
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.7882659435272217,
      "learning_rate": 6.426426426426427e-06,
      "loss": 0.1538,
      "step": 125
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 2.0389018058776855,
      "learning_rate": 6.396396396396397e-06,
      "loss": 0.2142,
      "step": 126
    },
    {
      "epoch": 0.3762962962962963,
      "grad_norm": 1.4486392736434937,
      "learning_rate": 6.366366366366366e-06,
      "loss": 0.1294,
      "step": 127
    },
    {
      "epoch": 0.37925925925925924,
      "grad_norm": 1.307952642440796,
      "learning_rate": 6.336336336336338e-06,
      "loss": 0.1086,
      "step": 128
    },
    {
      "epoch": 0.38222222222222224,
      "grad_norm": 1.7688995599746704,
      "learning_rate": 6.3063063063063065e-06,
      "loss": 0.1312,
      "step": 129
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 1.5715543031692505,
      "learning_rate": 6.276276276276276e-06,
      "loss": 0.1127,
      "step": 130
    },
    {
      "epoch": 0.38814814814814813,
      "grad_norm": 1.8992527723312378,
      "learning_rate": 6.246246246246247e-06,
      "loss": 0.1903,
      "step": 131
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 1.7179133892059326,
      "learning_rate": 6.2162162162162164e-06,
      "loss": 0.1464,
      "step": 132
    },
    {
      "epoch": 0.3940740740740741,
      "grad_norm": 2.0789332389831543,
      "learning_rate": 6.186186186186187e-06,
      "loss": 0.2104,
      "step": 133
    },
    {
      "epoch": 0.397037037037037,
      "grad_norm": 2.1791136264801025,
      "learning_rate": 6.156156156156157e-06,
      "loss": 0.1974,
      "step": 134
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.6125152111053467,
      "learning_rate": 6.126126126126126e-06,
      "loss": 0.1578,
      "step": 135
    },
    {
      "epoch": 0.40296296296296297,
      "grad_norm": 1.641171932220459,
      "learning_rate": 6.096096096096097e-06,
      "loss": 0.118,
      "step": 136
    },
    {
      "epoch": 0.4059259259259259,
      "grad_norm": 1.2050586938858032,
      "learning_rate": 6.066066066066067e-06,
      "loss": 0.0857,
      "step": 137
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 1.8158055543899536,
      "learning_rate": 6.036036036036037e-06,
      "loss": 0.1466,
      "step": 138
    },
    {
      "epoch": 0.41185185185185186,
      "grad_norm": 1.768127679824829,
      "learning_rate": 6.006006006006007e-06,
      "loss": 0.1617,
      "step": 139
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 2.254601240158081,
      "learning_rate": 5.975975975975976e-06,
      "loss": 0.2465,
      "step": 140
    },
    {
      "epoch": 0.4177777777777778,
      "grad_norm": 1.8633688688278198,
      "learning_rate": 5.945945945945947e-06,
      "loss": 0.1962,
      "step": 141
    },
    {
      "epoch": 0.42074074074074075,
      "grad_norm": 1.3848683834075928,
      "learning_rate": 5.915915915915916e-06,
      "loss": 0.1209,
      "step": 142
    },
    {
      "epoch": 0.4237037037037037,
      "grad_norm": 1.888769268989563,
      "learning_rate": 5.885885885885886e-06,
      "loss": 0.208,
      "step": 143
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 1.8556807041168213,
      "learning_rate": 5.855855855855856e-06,
      "loss": 0.1714,
      "step": 144
    },
    {
      "epoch": 0.42962962962962964,
      "grad_norm": 1.8301142454147339,
      "learning_rate": 5.825825825825826e-06,
      "loss": 0.1268,
      "step": 145
    },
    {
      "epoch": 0.4325925925925926,
      "grad_norm": 1.180439829826355,
      "learning_rate": 5.7957957957957965e-06,
      "loss": 0.0824,
      "step": 146
    },
    {
      "epoch": 0.43555555555555553,
      "grad_norm": 1.590444803237915,
      "learning_rate": 5.765765765765766e-06,
      "loss": 0.1295,
      "step": 147
    },
    {
      "epoch": 0.43851851851851853,
      "grad_norm": 1.6015013456344604,
      "learning_rate": 5.735735735735736e-06,
      "loss": 0.1567,
      "step": 148
    },
    {
      "epoch": 0.4414814814814815,
      "grad_norm": 1.6852848529815674,
      "learning_rate": 5.7057057057057065e-06,
      "loss": 0.1644,
      "step": 149
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.8794025182724,
      "learning_rate": 5.675675675675676e-06,
      "loss": 0.2039,
      "step": 150
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.1441621482372284,
      "eval_runtime": 34.569,
      "eval_samples_per_second": 17.357,
      "eval_steps_per_second": 8.678,
      "step": 150
    },
    {
      "epoch": 0.4474074074074074,
      "grad_norm": 2.494988203048706,
      "learning_rate": 5.645645645645647e-06,
      "loss": 0.222,
      "step": 151
    },
    {
      "epoch": 0.45037037037037037,
      "grad_norm": 1.2473042011260986,
      "learning_rate": 5.615615615615616e-06,
      "loss": 0.1174,
      "step": 152
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 1.8427050113677979,
      "learning_rate": 5.585585585585585e-06,
      "loss": 0.1471,
      "step": 153
    },
    {
      "epoch": 0.4562962962962963,
      "grad_norm": 1.8922629356384277,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.1697,
      "step": 154
    },
    {
      "epoch": 0.45925925925925926,
      "grad_norm": 1.2011164426803589,
      "learning_rate": 5.5255255255255255e-06,
      "loss": 0.0908,
      "step": 155
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.8909984827041626,
      "learning_rate": 5.495495495495496e-06,
      "loss": 0.0422,
      "step": 156
    },
    {
      "epoch": 0.4651851851851852,
      "grad_norm": 2.0646488666534424,
      "learning_rate": 5.465465465465466e-06,
      "loss": 0.187,
      "step": 157
    },
    {
      "epoch": 0.46814814814814815,
      "grad_norm": 1.387000322341919,
      "learning_rate": 5.4354354354354355e-06,
      "loss": 0.1299,
      "step": 158
    },
    {
      "epoch": 0.4711111111111111,
      "grad_norm": 1.8743476867675781,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.189,
      "step": 159
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.466044306755066,
      "learning_rate": 5.375375375375376e-06,
      "loss": 0.1066,
      "step": 160
    },
    {
      "epoch": 0.47703703703703704,
      "grad_norm": 1.7190651893615723,
      "learning_rate": 5.345345345345346e-06,
      "loss": 0.163,
      "step": 161
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.4338423013687134,
      "learning_rate": 5.315315315315316e-06,
      "loss": 0.1066,
      "step": 162
    },
    {
      "epoch": 0.482962962962963,
      "grad_norm": 1.6196538209915161,
      "learning_rate": 5.285285285285286e-06,
      "loss": 0.1485,
      "step": 163
    },
    {
      "epoch": 0.48592592592592593,
      "grad_norm": 1.520822286605835,
      "learning_rate": 5.255255255255256e-06,
      "loss": 0.0936,
      "step": 164
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 1.7789751291275024,
      "learning_rate": 5.225225225225226e-06,
      "loss": 0.1682,
      "step": 165
    },
    {
      "epoch": 0.4918518518518519,
      "grad_norm": 1.5512176752090454,
      "learning_rate": 5.195195195195195e-06,
      "loss": 0.1162,
      "step": 166
    },
    {
      "epoch": 0.4948148148148148,
      "grad_norm": 1.663032054901123,
      "learning_rate": 5.165165165165165e-06,
      "loss": 0.1246,
      "step": 167
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 2.3175830841064453,
      "learning_rate": 5.135135135135135e-06,
      "loss": 0.2438,
      "step": 168
    },
    {
      "epoch": 0.5007407407407407,
      "grad_norm": 1.570450782775879,
      "learning_rate": 5.105105105105106e-06,
      "loss": 0.1303,
      "step": 169
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 1.859751582145691,
      "learning_rate": 5.075075075075075e-06,
      "loss": 0.1879,
      "step": 170
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 1.739382028579712,
      "learning_rate": 5.045045045045045e-06,
      "loss": 0.1757,
      "step": 171
    },
    {
      "epoch": 0.5096296296296297,
      "grad_norm": 2.1184515953063965,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.2023,
      "step": 172
    },
    {
      "epoch": 0.5125925925925926,
      "grad_norm": 1.756111741065979,
      "learning_rate": 4.984984984984985e-06,
      "loss": 0.1849,
      "step": 173
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 1.8319339752197266,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.1674,
      "step": 174
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.751037836074829,
      "learning_rate": 4.9249249249249255e-06,
      "loss": 0.1598,
      "step": 175
    },
    {
      "epoch": 0.5214814814814814,
      "grad_norm": 1.743888020515442,
      "learning_rate": 4.894894894894895e-06,
      "loss": 0.1687,
      "step": 176
    },
    {
      "epoch": 0.5244444444444445,
      "grad_norm": 1.4629242420196533,
      "learning_rate": 4.864864864864866e-06,
      "loss": 0.1068,
      "step": 177
    },
    {
      "epoch": 0.5274074074074074,
      "grad_norm": 1.7729042768478394,
      "learning_rate": 4.8348348348348355e-06,
      "loss": 0.1566,
      "step": 178
    },
    {
      "epoch": 0.5303703703703704,
      "grad_norm": 1.7250057458877563,
      "learning_rate": 4.804804804804805e-06,
      "loss": 0.1647,
      "step": 179
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.4216197729110718,
      "learning_rate": 4.774774774774775e-06,
      "loss": 0.1314,
      "step": 180
    },
    {
      "epoch": 0.5362962962962963,
      "grad_norm": 1.3827472925186157,
      "learning_rate": 4.7447447447447454e-06,
      "loss": 0.136,
      "step": 181
    },
    {
      "epoch": 0.5392592592592592,
      "grad_norm": 1.842445969581604,
      "learning_rate": 4.714714714714715e-06,
      "loss": 0.1444,
      "step": 182
    },
    {
      "epoch": 0.5422222222222223,
      "grad_norm": 1.409833550453186,
      "learning_rate": 4.684684684684685e-06,
      "loss": 0.1085,
      "step": 183
    },
    {
      "epoch": 0.5451851851851852,
      "grad_norm": 1.86112380027771,
      "learning_rate": 4.654654654654655e-06,
      "loss": 0.2012,
      "step": 184
    },
    {
      "epoch": 0.5481481481481482,
      "grad_norm": 1.4413951635360718,
      "learning_rate": 4.624624624624625e-06,
      "loss": 0.1054,
      "step": 185
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 1.911708116531372,
      "learning_rate": 4.594594594594596e-06,
      "loss": 0.1835,
      "step": 186
    },
    {
      "epoch": 0.554074074074074,
      "grad_norm": 2.0759902000427246,
      "learning_rate": 4.5645645645645645e-06,
      "loss": 0.2153,
      "step": 187
    },
    {
      "epoch": 0.557037037037037,
      "grad_norm": 1.4579334259033203,
      "learning_rate": 4.534534534534535e-06,
      "loss": 0.1444,
      "step": 188
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.7819633483886719,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.1749,
      "step": 189
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 1.8689404726028442,
      "learning_rate": 4.474474474474475e-06,
      "loss": 0.1643,
      "step": 190
    },
    {
      "epoch": 0.5659259259259259,
      "grad_norm": 1.5566734075546265,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.1574,
      "step": 191
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 1.4628602266311646,
      "learning_rate": 4.414414414414415e-06,
      "loss": 0.1084,
      "step": 192
    },
    {
      "epoch": 0.5718518518518518,
      "grad_norm": 1.647021770477295,
      "learning_rate": 4.384384384384384e-06,
      "loss": 0.1926,
      "step": 193
    },
    {
      "epoch": 0.5748148148148148,
      "grad_norm": 1.6518713235855103,
      "learning_rate": 4.354354354354355e-06,
      "loss": 0.183,
      "step": 194
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 1.5342694520950317,
      "learning_rate": 4.324324324324325e-06,
      "loss": 0.1236,
      "step": 195
    },
    {
      "epoch": 0.5807407407407408,
      "grad_norm": 1.4601221084594727,
      "learning_rate": 4.294294294294294e-06,
      "loss": 0.1362,
      "step": 196
    },
    {
      "epoch": 0.5837037037037037,
      "grad_norm": 1.6395004987716675,
      "learning_rate": 4.264264264264265e-06,
      "loss": 0.1642,
      "step": 197
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 1.6057806015014648,
      "learning_rate": 4.234234234234235e-06,
      "loss": 0.1592,
      "step": 198
    },
    {
      "epoch": 0.5896296296296296,
      "grad_norm": 3.541837215423584,
      "learning_rate": 4.204204204204204e-06,
      "loss": 0.1365,
      "step": 199
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.430999994277954,
      "learning_rate": 4.174174174174174e-06,
      "loss": 0.1148,
      "step": 200
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 0.1403791755437851,
      "eval_runtime": 34.8362,
      "eval_samples_per_second": 17.223,
      "eval_steps_per_second": 8.612,
      "step": 200
    },
    {
      "epoch": 0.5955555555555555,
      "grad_norm": 1.6547671556472778,
      "learning_rate": 4.1441441441441446e-06,
      "loss": 0.19,
      "step": 201
    },
    {
      "epoch": 0.5985185185185186,
      "grad_norm": 1.6391719579696655,
      "learning_rate": 4.114114114114114e-06,
      "loss": 0.1495,
      "step": 202
    },
    {
      "epoch": 0.6014814814814815,
      "grad_norm": 1.2628647089004517,
      "learning_rate": 4.084084084084085e-06,
      "loss": 0.1002,
      "step": 203
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 2.2295002937316895,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.2126,
      "step": 204
    },
    {
      "epoch": 0.6074074074074074,
      "grad_norm": 1.8382062911987305,
      "learning_rate": 4.024024024024024e-06,
      "loss": 0.1682,
      "step": 205
    },
    {
      "epoch": 0.6103703703703703,
      "grad_norm": 1.212780237197876,
      "learning_rate": 3.993993993993994e-06,
      "loss": 0.1139,
      "step": 206
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 1.3603010177612305,
      "learning_rate": 3.9639639639639645e-06,
      "loss": 0.0843,
      "step": 207
    },
    {
      "epoch": 0.6162962962962963,
      "grad_norm": 1.3856849670410156,
      "learning_rate": 3.933933933933934e-06,
      "loss": 0.1157,
      "step": 208
    },
    {
      "epoch": 0.6192592592592593,
      "grad_norm": 1.4613559246063232,
      "learning_rate": 3.903903903903904e-06,
      "loss": 0.1523,
      "step": 209
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 1.7328627109527588,
      "learning_rate": 3.8738738738738744e-06,
      "loss": 0.1681,
      "step": 210
    },
    {
      "epoch": 0.6251851851851852,
      "grad_norm": 1.6055383682250977,
      "learning_rate": 3.843843843843844e-06,
      "loss": 0.1646,
      "step": 211
    },
    {
      "epoch": 0.6281481481481481,
      "grad_norm": 1.8404487371444702,
      "learning_rate": 3.8138138138138143e-06,
      "loss": 0.1408,
      "step": 212
    },
    {
      "epoch": 0.6311111111111111,
      "grad_norm": 1.7946399450302124,
      "learning_rate": 3.7837837837837844e-06,
      "loss": 0.1632,
      "step": 213
    },
    {
      "epoch": 0.6340740740740741,
      "grad_norm": 1.4036692380905151,
      "learning_rate": 3.7537537537537537e-06,
      "loss": 0.1296,
      "step": 214
    },
    {
      "epoch": 0.6370370370370371,
      "grad_norm": 1.4276372194290161,
      "learning_rate": 3.723723723723724e-06,
      "loss": 0.1061,
      "step": 215
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.5025657415390015,
      "learning_rate": 3.693693693693694e-06,
      "loss": 0.1368,
      "step": 216
    },
    {
      "epoch": 0.642962962962963,
      "grad_norm": 1.5344430208206177,
      "learning_rate": 3.663663663663664e-06,
      "loss": 0.1348,
      "step": 217
    },
    {
      "epoch": 0.6459259259259259,
      "grad_norm": 1.432612657546997,
      "learning_rate": 3.633633633633634e-06,
      "loss": 0.1013,
      "step": 218
    },
    {
      "epoch": 0.6488888888888888,
      "grad_norm": 1.9909372329711914,
      "learning_rate": 3.603603603603604e-06,
      "loss": 0.1888,
      "step": 219
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 1.5217621326446533,
      "learning_rate": 3.573573573573574e-06,
      "loss": 0.1321,
      "step": 220
    },
    {
      "epoch": 0.6548148148148148,
      "grad_norm": 1.194360613822937,
      "learning_rate": 3.5435435435435437e-06,
      "loss": 0.1353,
      "step": 221
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 1.4699935913085938,
      "learning_rate": 3.513513513513514e-06,
      "loss": 0.123,
      "step": 222
    },
    {
      "epoch": 0.6607407407407407,
      "grad_norm": 1.4995054006576538,
      "learning_rate": 3.4834834834834835e-06,
      "loss": 0.122,
      "step": 223
    },
    {
      "epoch": 0.6637037037037037,
      "grad_norm": 1.4534063339233398,
      "learning_rate": 3.4534534534534537e-06,
      "loss": 0.094,
      "step": 224
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4797601699829102,
      "learning_rate": 3.423423423423424e-06,
      "loss": 0.1034,
      "step": 225
    },
    {
      "epoch": 0.6696296296296296,
      "grad_norm": 1.599757194519043,
      "learning_rate": 3.393393393393394e-06,
      "loss": 0.1189,
      "step": 226
    },
    {
      "epoch": 0.6725925925925926,
      "grad_norm": 1.8611334562301636,
      "learning_rate": 3.363363363363364e-06,
      "loss": 0.1892,
      "step": 227
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 1.172027826309204,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.088,
      "step": 228
    },
    {
      "epoch": 0.6785185185185185,
      "grad_norm": 1.2169817686080933,
      "learning_rate": 3.3033033033033035e-06,
      "loss": 0.0828,
      "step": 229
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.2061595916748047,
      "learning_rate": 3.2732732732732736e-06,
      "loss": 0.1068,
      "step": 230
    },
    {
      "epoch": 0.6844444444444444,
      "grad_norm": 2.398705005645752,
      "learning_rate": 3.2432432432432437e-06,
      "loss": 0.1967,
      "step": 231
    },
    {
      "epoch": 0.6874074074074074,
      "grad_norm": 1.7223678827285767,
      "learning_rate": 3.2132132132132134e-06,
      "loss": 0.1467,
      "step": 232
    },
    {
      "epoch": 0.6903703703703704,
      "grad_norm": 1.446260690689087,
      "learning_rate": 3.183183183183183e-06,
      "loss": 0.1189,
      "step": 233
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 1.3965102434158325,
      "learning_rate": 3.1531531531531532e-06,
      "loss": 0.102,
      "step": 234
    },
    {
      "epoch": 0.6962962962962963,
      "grad_norm": 1.9204449653625488,
      "learning_rate": 3.1231231231231234e-06,
      "loss": 0.1347,
      "step": 235
    },
    {
      "epoch": 0.6992592592592592,
      "grad_norm": 2.090420722961426,
      "learning_rate": 3.0930930930930935e-06,
      "loss": 0.1709,
      "step": 236
    },
    {
      "epoch": 0.7022222222222222,
      "grad_norm": 1.7081043720245361,
      "learning_rate": 3.063063063063063e-06,
      "loss": 0.1579,
      "step": 237
    },
    {
      "epoch": 0.7051851851851851,
      "grad_norm": 1.7010947465896606,
      "learning_rate": 3.0330330330330333e-06,
      "loss": 0.138,
      "step": 238
    },
    {
      "epoch": 0.7081481481481482,
      "grad_norm": 1.357643723487854,
      "learning_rate": 3.0030030030030034e-06,
      "loss": 0.1034,
      "step": 239
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.8156524896621704,
      "learning_rate": 2.9729729729729736e-06,
      "loss": 0.1678,
      "step": 240
    },
    {
      "epoch": 0.7140740740740741,
      "grad_norm": 1.56818687915802,
      "learning_rate": 2.942942942942943e-06,
      "loss": 0.1482,
      "step": 241
    },
    {
      "epoch": 0.717037037037037,
      "grad_norm": 1.6360663175582886,
      "learning_rate": 2.912912912912913e-06,
      "loss": 0.1337,
      "step": 242
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.9676984548568726,
      "learning_rate": 2.882882882882883e-06,
      "loss": 0.195,
      "step": 243
    },
    {
      "epoch": 0.7229629629629629,
      "grad_norm": 1.349134922027588,
      "learning_rate": 2.8528528528528532e-06,
      "loss": 0.1114,
      "step": 244
    },
    {
      "epoch": 0.725925925925926,
      "grad_norm": 1.2810369729995728,
      "learning_rate": 2.8228228228228234e-06,
      "loss": 0.0839,
      "step": 245
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 1.8792139291763306,
      "learning_rate": 2.7927927927927926e-06,
      "loss": 0.1807,
      "step": 246
    },
    {
      "epoch": 0.7318518518518519,
      "grad_norm": 1.450472116470337,
      "learning_rate": 2.7627627627627628e-06,
      "loss": 0.0974,
      "step": 247
    },
    {
      "epoch": 0.7348148148148148,
      "grad_norm": 1.491336464881897,
      "learning_rate": 2.732732732732733e-06,
      "loss": 0.1128,
      "step": 248
    },
    {
      "epoch": 0.7377777777777778,
      "grad_norm": 1.8053474426269531,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.1684,
      "step": 249
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.7267152070999146,
      "learning_rate": 2.672672672672673e-06,
      "loss": 0.1585,
      "step": 250
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.13797889649868011,
      "eval_runtime": 34.4912,
      "eval_samples_per_second": 17.396,
      "eval_steps_per_second": 8.698,
      "step": 250
    },
    {
      "epoch": 0.7437037037037038,
      "grad_norm": 1.6875180006027222,
      "learning_rate": 2.642642642642643e-06,
      "loss": 0.1378,
      "step": 251
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 1.4719009399414062,
      "learning_rate": 2.612612612612613e-06,
      "loss": 0.1205,
      "step": 252
    },
    {
      "epoch": 0.7496296296296296,
      "grad_norm": 1.9640744924545288,
      "learning_rate": 2.5825825825825827e-06,
      "loss": 0.1681,
      "step": 253
    },
    {
      "epoch": 0.7525925925925926,
      "grad_norm": 1.6427189111709595,
      "learning_rate": 2.552552552552553e-06,
      "loss": 0.1291,
      "step": 254
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 1.5226848125457764,
      "learning_rate": 2.5225225225225225e-06,
      "loss": 0.1486,
      "step": 255
    },
    {
      "epoch": 0.7585185185185185,
      "grad_norm": 1.754725694656372,
      "learning_rate": 2.4924924924924926e-06,
      "loss": 0.1542,
      "step": 256
    },
    {
      "epoch": 0.7614814814814815,
      "grad_norm": 1.7979521751403809,
      "learning_rate": 2.4624624624624628e-06,
      "loss": 0.1836,
      "step": 257
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 1.590338110923767,
      "learning_rate": 2.432432432432433e-06,
      "loss": 0.1578,
      "step": 258
    },
    {
      "epoch": 0.7674074074074074,
      "grad_norm": 1.7710669040679932,
      "learning_rate": 2.4024024024024026e-06,
      "loss": 0.1669,
      "step": 259
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 1.720993161201477,
      "learning_rate": 2.3723723723723727e-06,
      "loss": 0.1428,
      "step": 260
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 1.92098867893219,
      "learning_rate": 2.3423423423423424e-06,
      "loss": 0.183,
      "step": 261
    },
    {
      "epoch": 0.7762962962962963,
      "grad_norm": 2.084221124649048,
      "learning_rate": 2.3123123123123125e-06,
      "loss": 0.1868,
      "step": 262
    },
    {
      "epoch": 0.7792592592592592,
      "grad_norm": 2.2521073818206787,
      "learning_rate": 2.2822822822822822e-06,
      "loss": 0.2131,
      "step": 263
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 1.4058071374893188,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.0974,
      "step": 264
    },
    {
      "epoch": 0.7851851851851852,
      "grad_norm": 1.4631900787353516,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.1023,
      "step": 265
    },
    {
      "epoch": 0.7881481481481482,
      "grad_norm": 1.267242670059204,
      "learning_rate": 2.192192192192192e-06,
      "loss": 0.1067,
      "step": 266
    },
    {
      "epoch": 0.7911111111111111,
      "grad_norm": 1.887813687324524,
      "learning_rate": 2.1621621621621623e-06,
      "loss": 0.1748,
      "step": 267
    },
    {
      "epoch": 0.794074074074074,
      "grad_norm": 1.5966384410858154,
      "learning_rate": 2.1321321321321325e-06,
      "loss": 0.1257,
      "step": 268
    },
    {
      "epoch": 0.797037037037037,
      "grad_norm": 2.05362606048584,
      "learning_rate": 2.102102102102102e-06,
      "loss": 0.1673,
      "step": 269
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.3489139080047607,
      "learning_rate": 2.0720720720720723e-06,
      "loss": 0.2364,
      "step": 270
    },
    {
      "epoch": 0.802962962962963,
      "grad_norm": 1.5986089706420898,
      "learning_rate": 2.0420420420420424e-06,
      "loss": 0.1254,
      "step": 271
    },
    {
      "epoch": 0.8059259259259259,
      "grad_norm": 2.0650482177734375,
      "learning_rate": 2.012012012012012e-06,
      "loss": 0.1613,
      "step": 272
    },
    {
      "epoch": 0.8088888888888889,
      "grad_norm": 2.072725772857666,
      "learning_rate": 1.9819819819819822e-06,
      "loss": 0.2111,
      "step": 273
    },
    {
      "epoch": 0.8118518518518518,
      "grad_norm": 1.1221811771392822,
      "learning_rate": 1.951951951951952e-06,
      "loss": 0.074,
      "step": 274
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.741605520248413,
      "learning_rate": 1.921921921921922e-06,
      "loss": 0.1811,
      "step": 275
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 2.093367338180542,
      "learning_rate": 1.8918918918918922e-06,
      "loss": 0.2025,
      "step": 276
    },
    {
      "epoch": 0.8207407407407408,
      "grad_norm": 1.7748947143554688,
      "learning_rate": 1.861861861861862e-06,
      "loss": 0.1514,
      "step": 277
    },
    {
      "epoch": 0.8237037037037037,
      "grad_norm": 1.2260737419128418,
      "learning_rate": 1.831831831831832e-06,
      "loss": 0.0855,
      "step": 278
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 1.5776963233947754,
      "learning_rate": 1.801801801801802e-06,
      "loss": 0.1251,
      "step": 279
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 1.679695963859558,
      "learning_rate": 1.7717717717717719e-06,
      "loss": 0.1731,
      "step": 280
    },
    {
      "epoch": 0.8325925925925926,
      "grad_norm": 1.1554036140441895,
      "learning_rate": 1.7417417417417418e-06,
      "loss": 0.0854,
      "step": 281
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 2.033879041671753,
      "learning_rate": 1.711711711711712e-06,
      "loss": 0.1791,
      "step": 282
    },
    {
      "epoch": 0.8385185185185186,
      "grad_norm": 1.275734782218933,
      "learning_rate": 1.681681681681682e-06,
      "loss": 0.109,
      "step": 283
    },
    {
      "epoch": 0.8414814814814815,
      "grad_norm": 1.7007089853286743,
      "learning_rate": 1.6516516516516517e-06,
      "loss": 0.1412,
      "step": 284
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 1.807941198348999,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.1138,
      "step": 285
    },
    {
      "epoch": 0.8474074074074074,
      "grad_norm": 1.204346776008606,
      "learning_rate": 1.5915915915915916e-06,
      "loss": 0.0964,
      "step": 286
    },
    {
      "epoch": 0.8503703703703703,
      "grad_norm": 1.3683191537857056,
      "learning_rate": 1.5615615615615617e-06,
      "loss": 0.1007,
      "step": 287
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.3524974584579468,
      "learning_rate": 1.5315315315315316e-06,
      "loss": 0.1037,
      "step": 288
    },
    {
      "epoch": 0.8562962962962963,
      "grad_norm": 1.6213585138320923,
      "learning_rate": 1.5015015015015017e-06,
      "loss": 0.139,
      "step": 289
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 1.0120651721954346,
      "learning_rate": 1.4714714714714714e-06,
      "loss": 0.0637,
      "step": 290
    },
    {
      "epoch": 0.8622222222222222,
      "grad_norm": 1.4436391592025757,
      "learning_rate": 1.4414414414414416e-06,
      "loss": 0.1086,
      "step": 291
    },
    {
      "epoch": 0.8651851851851852,
      "grad_norm": 1.368062138557434,
      "learning_rate": 1.4114114114114117e-06,
      "loss": 0.0931,
      "step": 292
    },
    {
      "epoch": 0.8681481481481481,
      "grad_norm": 1.4197474718093872,
      "learning_rate": 1.3813813813813814e-06,
      "loss": 0.0939,
      "step": 293
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 2.005744457244873,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.2045,
      "step": 294
    },
    {
      "epoch": 0.8740740740740741,
      "grad_norm": 1.149666666984558,
      "learning_rate": 1.3213213213213214e-06,
      "loss": 0.092,
      "step": 295
    },
    {
      "epoch": 0.8770370370370371,
      "grad_norm": 1.7258998155593872,
      "learning_rate": 1.2912912912912913e-06,
      "loss": 0.1355,
      "step": 296
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.1928515434265137,
      "learning_rate": 1.2612612612612613e-06,
      "loss": 0.0956,
      "step": 297
    },
    {
      "epoch": 0.882962962962963,
      "grad_norm": 1.7309209108352661,
      "learning_rate": 1.2312312312312314e-06,
      "loss": 0.155,
      "step": 298
    },
    {
      "epoch": 0.8859259259259259,
      "grad_norm": 1.3706496953964233,
      "learning_rate": 1.2012012012012013e-06,
      "loss": 0.112,
      "step": 299
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.4032557010650635,
      "learning_rate": 1.1711711711711712e-06,
      "loss": 0.104,
      "step": 300
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.1356930136680603,
      "eval_runtime": 34.4832,
      "eval_samples_per_second": 17.4,
      "eval_steps_per_second": 8.7,
      "step": 300
    },
    {
      "epoch": 0.8918518518518519,
      "grad_norm": 1.860055923461914,
      "learning_rate": 1.1411411411411411e-06,
      "loss": 0.1568,
      "step": 301
    },
    {
      "epoch": 0.8948148148148148,
      "grad_norm": 1.8489398956298828,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.1448,
      "step": 302
    },
    {
      "epoch": 0.8977777777777778,
      "grad_norm": 1.2739697694778442,
      "learning_rate": 1.0810810810810812e-06,
      "loss": 0.0907,
      "step": 303
    },
    {
      "epoch": 0.9007407407407407,
      "grad_norm": 1.712273120880127,
      "learning_rate": 1.051051051051051e-06,
      "loss": 0.177,
      "step": 304
    },
    {
      "epoch": 0.9037037037037037,
      "grad_norm": 1.532152533531189,
      "learning_rate": 1.0210210210210212e-06,
      "loss": 0.1109,
      "step": 305
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 2.0539047718048096,
      "learning_rate": 9.909909909909911e-07,
      "loss": 0.1223,
      "step": 306
    },
    {
      "epoch": 0.9096296296296297,
      "grad_norm": 1.081939458847046,
      "learning_rate": 9.60960960960961e-07,
      "loss": 0.0893,
      "step": 307
    },
    {
      "epoch": 0.9125925925925926,
      "grad_norm": 1.7349634170532227,
      "learning_rate": 9.30930930930931e-07,
      "loss": 0.1765,
      "step": 308
    },
    {
      "epoch": 0.9155555555555556,
      "grad_norm": 1.9391576051712036,
      "learning_rate": 9.00900900900901e-07,
      "loss": 0.1869,
      "step": 309
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 1.5753812789916992,
      "learning_rate": 8.708708708708709e-07,
      "loss": 0.1303,
      "step": 310
    },
    {
      "epoch": 0.9214814814814815,
      "grad_norm": 1.043404221534729,
      "learning_rate": 8.40840840840841e-07,
      "loss": 0.0789,
      "step": 311
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 1.3314138650894165,
      "learning_rate": 8.108108108108109e-07,
      "loss": 0.0983,
      "step": 312
    },
    {
      "epoch": 0.9274074074074075,
      "grad_norm": 1.8325467109680176,
      "learning_rate": 7.807807807807808e-07,
      "loss": 0.1691,
      "step": 313
    },
    {
      "epoch": 0.9303703703703704,
      "grad_norm": 1.239039421081543,
      "learning_rate": 7.507507507507509e-07,
      "loss": 0.083,
      "step": 314
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 1.6132171154022217,
      "learning_rate": 7.207207207207208e-07,
      "loss": 0.1312,
      "step": 315
    },
    {
      "epoch": 0.9362962962962963,
      "grad_norm": 1.6791914701461792,
      "learning_rate": 6.906906906906907e-07,
      "loss": 0.1742,
      "step": 316
    },
    {
      "epoch": 0.9392592592592592,
      "grad_norm": 1.4714045524597168,
      "learning_rate": 6.606606606606607e-07,
      "loss": 0.1183,
      "step": 317
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 1.660597324371338,
      "learning_rate": 6.306306306306306e-07,
      "loss": 0.1266,
      "step": 318
    },
    {
      "epoch": 0.9451851851851852,
      "grad_norm": 1.3589818477630615,
      "learning_rate": 6.006006006006006e-07,
      "loss": 0.1276,
      "step": 319
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 1.5479717254638672,
      "learning_rate": 5.705705705705706e-07,
      "loss": 0.1167,
      "step": 320
    },
    {
      "epoch": 0.9511111111111111,
      "grad_norm": 1.6448798179626465,
      "learning_rate": 5.405405405405406e-07,
      "loss": 0.1245,
      "step": 321
    },
    {
      "epoch": 0.9540740740740741,
      "grad_norm": 1.5266709327697754,
      "learning_rate": 5.105105105105106e-07,
      "loss": 0.1392,
      "step": 322
    },
    {
      "epoch": 0.957037037037037,
      "grad_norm": 1.353745460510254,
      "learning_rate": 4.804804804804805e-07,
      "loss": 0.1239,
      "step": 323
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.4509172439575195,
      "learning_rate": 4.504504504504505e-07,
      "loss": 0.0913,
      "step": 324
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.1288158893585205,
      "learning_rate": 4.204204204204205e-07,
      "loss": 0.0873,
      "step": 325
    },
    {
      "epoch": 0.965925925925926,
      "grad_norm": 1.7373437881469727,
      "learning_rate": 3.903903903903904e-07,
      "loss": 0.1608,
      "step": 326
    },
    {
      "epoch": 0.9688888888888889,
      "grad_norm": 1.1237938404083252,
      "learning_rate": 3.603603603603604e-07,
      "loss": 0.0823,
      "step": 327
    },
    {
      "epoch": 0.9718518518518519,
      "grad_norm": 1.800816297531128,
      "learning_rate": 3.3033033033033036e-07,
      "loss": 0.1563,
      "step": 328
    },
    {
      "epoch": 0.9748148148148148,
      "grad_norm": 1.7061725854873657,
      "learning_rate": 3.003003003003003e-07,
      "loss": 0.1384,
      "step": 329
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.4900712966918945,
      "learning_rate": 2.702702702702703e-07,
      "loss": 0.0859,
      "step": 330
    },
    {
      "epoch": 0.9807407407407407,
      "grad_norm": 1.9032883644104004,
      "learning_rate": 2.4024024024024026e-07,
      "loss": 0.189,
      "step": 331
    },
    {
      "epoch": 0.9837037037037037,
      "grad_norm": 1.3040142059326172,
      "learning_rate": 2.1021021021021025e-07,
      "loss": 0.1349,
      "step": 332
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 1.6230350732803345,
      "learning_rate": 1.801801801801802e-07,
      "loss": 0.1176,
      "step": 333
    },
    {
      "epoch": 0.9896296296296296,
      "grad_norm": 1.1613117456436157,
      "learning_rate": 1.5015015015015016e-07,
      "loss": 0.09,
      "step": 334
    },
    {
      "epoch": 0.9925925925925926,
      "grad_norm": 1.852225661277771,
      "learning_rate": 1.2012012012012013e-07,
      "loss": 0.1581,
      "step": 335
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 1.7616565227508545,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.1669,
      "step": 336
    },
    {
      "epoch": 0.9985185185185185,
      "grad_norm": 1.6350497007369995,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.1346,
      "step": 337
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.5312914848327637,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1532,
      "step": 338
    }
  ],
  "logging_steps": 1,
  "max_steps": 338,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.298485270853632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}