{
  "best_metric": 0.8919714689254761,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.6756756756756757,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033783783783783786,
      "grad_norm": 3.790795087814331,
      "learning_rate": 5e-06,
      "loss": 1.4948,
      "step": 1
    },
    {
      "epoch": 0.0033783783783783786,
      "eval_loss": 2.366645336151123,
      "eval_runtime": 45.5726,
      "eval_samples_per_second": 10.95,
      "eval_steps_per_second": 5.486,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 4.27876091003418,
      "learning_rate": 1e-05,
      "loss": 1.6839,
      "step": 2
    },
    {
      "epoch": 0.010135135135135136,
      "grad_norm": 4.081669807434082,
      "learning_rate": 1.5e-05,
      "loss": 1.5767,
      "step": 3
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 3.980726480484009,
      "learning_rate": 2e-05,
      "loss": 1.5418,
      "step": 4
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 3.4310128688812256,
      "learning_rate": 2.5e-05,
      "loss": 1.5372,
      "step": 5
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 2.8119819164276123,
      "learning_rate": 3e-05,
      "loss": 1.3767,
      "step": 6
    },
    {
      "epoch": 0.02364864864864865,
      "grad_norm": 2.1277658939361572,
      "learning_rate": 3.5e-05,
      "loss": 1.2593,
      "step": 7
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.5391322374343872,
      "learning_rate": 4e-05,
      "loss": 1.2748,
      "step": 8
    },
    {
      "epoch": 0.030405405405405407,
      "grad_norm": 1.341151237487793,
      "learning_rate": 4.5e-05,
      "loss": 1.1627,
      "step": 9
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 1.4433046579360962,
      "learning_rate": 5e-05,
      "loss": 1.1408,
      "step": 10
    },
    {
      "epoch": 0.037162162162162164,
      "grad_norm": 1.3264684677124023,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.0924,
      "step": 11
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.5089952945709229,
      "learning_rate": 6e-05,
      "loss": 1.1045,
      "step": 12
    },
    {
      "epoch": 0.04391891891891892,
      "grad_norm": 1.2900017499923706,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.0468,
      "step": 13
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 1.226200819015503,
      "learning_rate": 7e-05,
      "loss": 1.0241,
      "step": 14
    },
    {
      "epoch": 0.05067567567567568,
      "grad_norm": 1.1079437732696533,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0797,
      "step": 15
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.118066430091858,
      "learning_rate": 8e-05,
      "loss": 1.064,
      "step": 16
    },
    {
      "epoch": 0.057432432432432436,
      "grad_norm": 1.14432954788208,
      "learning_rate": 8.5e-05,
      "loss": 1.0531,
      "step": 17
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 1.10897696018219,
      "learning_rate": 9e-05,
      "loss": 1.1692,
      "step": 18
    },
    {
      "epoch": 0.06418918918918919,
      "grad_norm": 1.2004364728927612,
      "learning_rate": 9.5e-05,
      "loss": 1.233,
      "step": 19
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 1.031334638595581,
      "learning_rate": 0.0001,
      "loss": 0.9639,
      "step": 20
    },
    {
      "epoch": 0.07094594594594594,
      "grad_norm": 1.0391218662261963,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.0314,
      "step": 21
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 1.0851644277572632,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.9859,
      "step": 22
    },
    {
      "epoch": 0.0777027027027027,
      "grad_norm": 1.3139114379882812,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.1277,
      "step": 23
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.143263339996338,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1157,
      "step": 24
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 1.2163656949996948,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.0792,
      "step": 25
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 1.844299077987671,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1085,
      "step": 26
    },
    {
      "epoch": 0.09121621621621621,
      "grad_norm": 1.5571035146713257,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.0205,
      "step": 27
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.331886887550354,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1869,
      "step": 28
    },
    {
      "epoch": 0.09797297297297297,
      "grad_norm": 1.3357473611831665,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.059,
      "step": 29
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.6065927743911743,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2931,
      "step": 30
    },
    {
      "epoch": 0.10472972972972973,
      "grad_norm": 1.4034627676010132,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.2066,
      "step": 31
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.4192296266555786,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.216,
      "step": 32
    },
    {
      "epoch": 0.11148648648648649,
      "grad_norm": 1.8513731956481934,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.1236,
      "step": 33
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 1.535695195198059,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.2842,
      "step": 34
    },
    {
      "epoch": 0.11824324324324324,
      "grad_norm": 1.70310640335083,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0982,
      "step": 35
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.8845494985580444,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1928,
      "step": 36
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.9401278495788574,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.1353,
      "step": 37
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 1.7827504873275757,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0933,
      "step": 38
    },
    {
      "epoch": 0.13175675675675674,
      "grad_norm": 2.116203546524048,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.2047,
      "step": 39
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.9922860860824585,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.2051,
      "step": 40
    },
    {
      "epoch": 0.13851351351351351,
      "grad_norm": 1.739909052848816,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.0593,
      "step": 41
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.9242291450500488,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0776,
      "step": 42
    },
    {
      "epoch": 0.14527027027027026,
      "grad_norm": 2.0772931575775146,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.0936,
      "step": 43
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 2.72910475730896,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2138,
      "step": 44
    },
    {
      "epoch": 0.15202702702702703,
      "grad_norm": 2.3262908458709717,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.8939,
      "step": 45
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 2.338627815246582,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.919,
      "step": 46
    },
    {
      "epoch": 0.15878378378378377,
      "grad_norm": 2.6159088611602783,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.9041,
      "step": 47
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 3.0837512016296387,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9639,
      "step": 48
    },
    {
      "epoch": 0.16554054054054054,
      "grad_norm": 3.6426544189453125,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.1832,
      "step": 49
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 3.982973575592041,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9804,
      "step": 50
    },
    {
      "epoch": 0.16891891891891891,
      "eval_loss": 1.1289108991622925,
      "eval_runtime": 46.3711,
      "eval_samples_per_second": 10.761,
      "eval_steps_per_second": 5.391,
      "step": 50
    },
    {
      "epoch": 0.17229729729729729,
      "grad_norm": 1.6470714807510376,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.9835,
      "step": 51
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 1.65348482131958,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.044,
      "step": 52
    },
    {
      "epoch": 0.17905405405405406,
      "grad_norm": 0.9217798709869385,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.9206,
      "step": 53
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 0.6984456181526184,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.724,
      "step": 54
    },
    {
      "epoch": 0.1858108108108108,
      "grad_norm": 0.8570162057876587,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.9921,
      "step": 55
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 0.8727167248725891,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9956,
      "step": 56
    },
    {
      "epoch": 0.19256756756756757,
      "grad_norm": 0.9744833707809448,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.9819,
      "step": 57
    },
    {
      "epoch": 0.19594594594594594,
      "grad_norm": 0.98649662733078,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.887,
      "step": 58
    },
    {
      "epoch": 0.19932432432432431,
      "grad_norm": 0.8099063634872437,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.8632,
      "step": 59
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 0.8015736937522888,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.9062,
      "step": 60
    },
    {
      "epoch": 0.20608108108108109,
      "grad_norm": 0.868614137172699,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.9653,
      "step": 61
    },
    {
      "epoch": 0.20945945945945946,
      "grad_norm": 0.7105808258056641,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8513,
      "step": 62
    },
    {
      "epoch": 0.21283783783783783,
      "grad_norm": 0.7809450030326843,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.9441,
      "step": 63
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.910719096660614,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.929,
      "step": 64
    },
    {
      "epoch": 0.2195945945945946,
      "grad_norm": 0.8238301873207092,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8879,
      "step": 65
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 0.8302669525146484,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.8487,
      "step": 66
    },
    {
      "epoch": 0.22635135135135134,
      "grad_norm": 0.9159395694732666,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.939,
      "step": 67
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 0.8282083868980408,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.9193,
      "step": 68
    },
    {
      "epoch": 0.23310810810810811,
      "grad_norm": 0.877231240272522,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.9358,
      "step": 69
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 1.0099470615386963,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.9245,
      "step": 70
    },
    {
      "epoch": 0.23986486486486486,
      "grad_norm": 1.0175057649612427,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.0411,
      "step": 71
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.9246781468391418,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.9697,
      "step": 72
    },
    {
      "epoch": 0.24662162162162163,
      "grad_norm": 0.9959827661514282,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.936,
      "step": 73
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.1503347158432007,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9295,
      "step": 74
    },
    {
      "epoch": 0.2533783783783784,
      "grad_norm": 1.245553731918335,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.1697,
      "step": 75
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 1.1103030443191528,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.851,
      "step": 76
    },
    {
      "epoch": 0.26013513513513514,
      "grad_norm": 1.039109468460083,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.9779,
      "step": 77
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 1.1795552968978882,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.0418,
      "step": 78
    },
    {
      "epoch": 0.2668918918918919,
      "grad_norm": 1.2785820960998535,
      "learning_rate": 7.575190374550272e-05,
      "loss": 1.1016,
      "step": 79
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.204482913017273,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.136,
      "step": 80
    },
    {
      "epoch": 0.27364864864864863,
      "grad_norm": 1.3328748941421509,
      "learning_rate": 7.424048101231686e-05,
      "loss": 1.1576,
      "step": 81
    },
    {
      "epoch": 0.27702702702702703,
      "grad_norm": 1.5070085525512695,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.2457,
      "step": 82
    },
    {
      "epoch": 0.28040540540540543,
      "grad_norm": 1.3167310953140259,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.0597,
      "step": 83
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 1.436022400856018,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0113,
      "step": 84
    },
    {
      "epoch": 0.28716216216216217,
      "grad_norm": 1.5455635786056519,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.046,
      "step": 85
    },
    {
      "epoch": 0.2905405405405405,
      "grad_norm": 1.286605954170227,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.979,
      "step": 86
    },
    {
      "epoch": 0.2939189189189189,
      "grad_norm": 1.3941338062286377,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.9772,
      "step": 87
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 1.5202627182006836,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0439,
      "step": 88
    },
    {
      "epoch": 0.30067567567567566,
      "grad_norm": 1.6103655099868774,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.1001,
      "step": 89
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 1.8977413177490234,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.1716,
      "step": 90
    },
    {
      "epoch": 0.30743243243243246,
      "grad_norm": 1.7053625583648682,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.853,
      "step": 91
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 1.7277348041534424,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0563,
      "step": 92
    },
    {
      "epoch": 0.3141891891891892,
      "grad_norm": 1.7474844455718994,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.8952,
      "step": 93
    },
    {
      "epoch": 0.31756756756756754,
      "grad_norm": 1.7933131456375122,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.9742,
      "step": 94
    },
    {
      "epoch": 0.32094594594594594,
      "grad_norm": 1.790142297744751,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9332,
      "step": 95
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 2.3483188152313232,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8821,
      "step": 96
    },
    {
      "epoch": 0.3277027027027027,
      "grad_norm": 2.0624172687530518,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.7516,
      "step": 97
    },
    {
      "epoch": 0.3310810810810811,
      "grad_norm": 2.341597318649292,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.7419,
      "step": 98
    },
    {
      "epoch": 0.3344594594594595,
      "grad_norm": 2.4898014068603516,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.8187,
      "step": 99
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 3.681002140045166,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0257,
      "step": 100
    },
    {
      "epoch": 0.33783783783783783,
      "eval_loss": 0.9962962865829468,
      "eval_runtime": 46.3235,
      "eval_samples_per_second": 10.772,
      "eval_steps_per_second": 5.397,
      "step": 100
    },
    {
      "epoch": 0.34121621621621623,
      "grad_norm": 1.0150301456451416,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.8399,
      "step": 101
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 0.9101819396018982,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8332,
      "step": 102
    },
    {
      "epoch": 0.34797297297297297,
      "grad_norm": 0.7298635244369507,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.7701,
      "step": 103
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 0.7302980422973633,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8608,
      "step": 104
    },
    {
      "epoch": 0.3547297297297297,
      "grad_norm": 0.7403108477592468,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.8571,
      "step": 105
    },
    {
      "epoch": 0.3581081081081081,
      "grad_norm": 0.7119635939598083,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8834,
      "step": 106
    },
    {
      "epoch": 0.3614864864864865,
      "grad_norm": 0.7150499820709229,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.8476,
      "step": 107
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 2.773348331451416,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8951,
      "step": 108
    },
    {
      "epoch": 0.36824324324324326,
      "grad_norm": 0.7925100326538086,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.8753,
      "step": 109
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 0.9120268821716309,
      "learning_rate": 5e-05,
      "loss": 0.9304,
      "step": 110
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.923784613609314,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.9109,
      "step": 111
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.7621331214904785,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8805,
      "step": 112
    },
    {
      "epoch": 0.38175675675675674,
      "grad_norm": 0.989507794380188,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.9356,
      "step": 113
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 1.1281342506408691,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.9762,
      "step": 114
    },
    {
      "epoch": 0.3885135135135135,
      "grad_norm": 1.0303744077682495,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.9971,
      "step": 115
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 0.8193778991699219,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.9003,
      "step": 116
    },
    {
      "epoch": 0.3952702702702703,
      "grad_norm": 0.8731766939163208,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.9704,
      "step": 117
    },
    {
      "epoch": 0.39864864864864863,
      "grad_norm": 1.064092755317688,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.0779,
      "step": 118
    },
    {
      "epoch": 0.40202702702702703,
      "grad_norm": 0.8438169360160828,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.9074,
      "step": 119
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 0.8278259634971619,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.9602,
      "step": 120
    },
    {
      "epoch": 0.40878378378378377,
      "grad_norm": 0.8631948232650757,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.8994,
      "step": 121
    },
    {
      "epoch": 0.41216216216216217,
      "grad_norm": 0.9589402079582214,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0671,
      "step": 122
    },
    {
      "epoch": 0.4155405405405405,
      "grad_norm": 0.9513259530067444,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.0584,
      "step": 123
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 1.0139130353927612,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9865,
      "step": 124
    },
    {
      "epoch": 0.4222972972972973,
      "grad_norm": 0.9505813121795654,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.9182,
      "step": 125
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 0.9823381900787354,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9159,
      "step": 126
    },
    {
      "epoch": 0.42905405405405406,
      "grad_norm": 1.0299394130706787,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.9573,
      "step": 127
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.2664399147033691,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1676,
      "step": 128
    },
    {
      "epoch": 0.4358108108108108,
      "grad_norm": 1.107443928718567,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.9744,
      "step": 129
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 1.2630161046981812,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0434,
      "step": 130
    },
    {
      "epoch": 0.44256756756756754,
      "grad_norm": 1.2209265232086182,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.9721,
      "step": 131
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 1.1842795610427856,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.9618,
      "step": 132
    },
    {
      "epoch": 0.44932432432432434,
      "grad_norm": 1.22838294506073,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.981,
      "step": 133
    },
    {
      "epoch": 0.4527027027027027,
      "grad_norm": 1.260001301765442,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.9968,
      "step": 134
    },
    {
      "epoch": 0.4560810810810811,
      "grad_norm": 1.4171466827392578,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.0873,
      "step": 135
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 1.376778244972229,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0623,
      "step": 136
    },
    {
      "epoch": 0.46283783783783783,
      "grad_norm": 1.6616677045822144,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.1181,
      "step": 137
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 1.489789605140686,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.0679,
      "step": 138
    },
    {
      "epoch": 0.46959459459459457,
      "grad_norm": 1.6120611429214478,
      "learning_rate": 2.575951898768315e-05,
      "loss": 1.1404,
      "step": 139
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 1.7737764120101929,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0704,
      "step": 140
    },
    {
      "epoch": 0.47635135135135137,
      "grad_norm": 1.4966835975646973,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.903,
      "step": 141
    },
    {
      "epoch": 0.4797297297297297,
      "grad_norm": 1.6529886722564697,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.9047,
      "step": 142
    },
    {
      "epoch": 0.4831081081081081,
      "grad_norm": 1.9524998664855957,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.9717,
      "step": 143
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 1.7451844215393066,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.9651,
      "step": 144
    },
    {
      "epoch": 0.48986486486486486,
      "grad_norm": 1.7876458168029785,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.9632,
      "step": 145
    },
    {
      "epoch": 0.49324324324324326,
      "grad_norm": 1.8912980556488037,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9248,
      "step": 146
    },
    {
      "epoch": 0.4966216216216216,
      "grad_norm": 2.041308641433716,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.826,
      "step": 147
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.146843433380127,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8596,
      "step": 148
    },
    {
      "epoch": 0.5033783783783784,
      "grad_norm": 3.079761028289795,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 1.0932,
      "step": 149
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 4.34760046005249,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.9517,
      "step": 150
    },
    {
      "epoch": 0.5067567567567568,
      "eval_loss": 0.910146951675415,
      "eval_runtime": 46.335,
      "eval_samples_per_second": 10.769,
      "eval_steps_per_second": 5.395,
      "step": 150
    },
    {
      "epoch": 0.5101351351351351,
      "grad_norm": 0.617638111114502,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.7233,
      "step": 151
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 0.8564380407333374,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.9559,
      "step": 152
    },
    {
      "epoch": 0.5168918918918919,
      "grad_norm": 0.6549626588821411,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.7579,
      "step": 153
    },
    {
      "epoch": 0.5202702702702703,
      "grad_norm": 0.6548464894294739,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7968,
      "step": 154
    },
    {
      "epoch": 0.5236486486486487,
      "grad_norm": 0.6791085004806519,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8266,
      "step": 155
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 0.6822385191917419,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.8525,
      "step": 156
    },
    {
      "epoch": 0.5304054054054054,
      "grad_norm": 0.699497640132904,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.8513,
      "step": 157
    },
    {
      "epoch": 0.5337837837837838,
      "grad_norm": 0.8761206865310669,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.8481,
      "step": 158
    },
    {
      "epoch": 0.5371621621621622,
      "grad_norm": 0.7131243944168091,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.8898,
      "step": 159
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.7251644730567932,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.8904,
      "step": 160
    },
    {
      "epoch": 0.543918918918919,
      "grad_norm": 0.7635348439216614,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.8293,
      "step": 161
    },
    {
      "epoch": 0.5472972972972973,
      "grad_norm": 0.796482503414154,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.9214,
      "step": 162
    },
    {
      "epoch": 0.5506756756756757,
      "grad_norm": 0.7892021536827087,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.8489,
      "step": 163
    },
    {
      "epoch": 0.5540540540540541,
      "grad_norm": 0.7896630764007568,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8908,
      "step": 164
    },
    {
      "epoch": 0.5574324324324325,
      "grad_norm": 0.9114834070205688,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.8966,
      "step": 165
    },
    {
      "epoch": 0.5608108108108109,
      "grad_norm": 0.7687644958496094,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.8819,
      "step": 166
    },
    {
      "epoch": 0.5641891891891891,
      "grad_norm": 0.860630214214325,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.923,
      "step": 167
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 0.8365357518196106,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.9266,
      "step": 168
    },
    {
      "epoch": 0.5709459459459459,
      "grad_norm": 0.8165171146392822,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.838,
      "step": 169
    },
    {
      "epoch": 0.5743243243243243,
      "grad_norm": 0.864069938659668,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.934,
      "step": 170
    },
    {
      "epoch": 0.5777027027027027,
      "grad_norm": 0.9135668873786926,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.9902,
      "step": 171
    },
    {
      "epoch": 0.581081081081081,
      "grad_norm": 0.8596118688583374,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8607,
      "step": 172
    },
    {
      "epoch": 0.5844594594594594,
      "grad_norm": 1.0075477361679077,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.006,
      "step": 173
    },
    {
      "epoch": 0.5878378378378378,
      "grad_norm": 0.9625608325004578,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.9199,
      "step": 174
    },
    {
      "epoch": 0.5912162162162162,
      "grad_norm": 1.0007152557373047,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.9741,
      "step": 175
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 1.2116408348083496,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1235,
      "step": 176
    },
    {
      "epoch": 0.597972972972973,
      "grad_norm": 1.0656737089157104,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.9497,
      "step": 177
    },
    {
      "epoch": 0.6013513513513513,
      "grad_norm": 1.095234751701355,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0694,
      "step": 178
    },
    {
      "epoch": 0.6047297297297297,
      "grad_norm": 1.0279932022094727,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.9642,
      "step": 179
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.1247590780258179,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.9799,
      "step": 180
    },
    {
      "epoch": 0.6114864864864865,
      "grad_norm": 1.228450894355774,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.9902,
      "step": 181
    },
    {
      "epoch": 0.6148648648648649,
      "grad_norm": 1.2460905313491821,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0458,
      "step": 182
    },
    {
      "epoch": 0.6182432432432432,
      "grad_norm": 1.3238197565078735,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 1.0183,
      "step": 183
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 1.2620553970336914,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0289,
      "step": 184
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.400741457939148,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.0397,
      "step": 185
    },
    {
      "epoch": 0.6283783783783784,
      "grad_norm": 1.3458335399627686,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.922,
      "step": 186
    },
    {
      "epoch": 0.6317567567567568,
      "grad_norm": 1.3344112634658813,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.9703,
      "step": 187
    },
    {
      "epoch": 0.6351351351351351,
      "grad_norm": 1.5010539293289185,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.0322,
      "step": 188
    },
    {
      "epoch": 0.6385135135135135,
      "grad_norm": 1.4925593137741089,
      "learning_rate": 9.186408276168013e-07,
      "loss": 1.0375,
      "step": 189
    },
    {
      "epoch": 0.6418918918918919,
      "grad_norm": 1.4849199056625366,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.9365,
      "step": 190
    },
    {
      "epoch": 0.6452702702702703,
      "grad_norm": 1.4886884689331055,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.9195,
      "step": 191
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.625990390777588,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.9385,
      "step": 192
    },
    {
      "epoch": 0.652027027027027,
      "grad_norm": 1.832520842552185,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.8738,
      "step": 193
    },
    {
      "epoch": 0.6554054054054054,
      "grad_norm": 2.0530941486358643,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.035,
      "step": 194
    },
    {
      "epoch": 0.6587837837837838,
      "grad_norm": 2.198253870010376,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.955,
      "step": 195
    },
    {
      "epoch": 0.6621621621621622,
      "grad_norm": 1.8382649421691895,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.8156,
      "step": 196
    },
    {
      "epoch": 0.6655405405405406,
      "grad_norm": 1.9348886013031006,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.8991,
      "step": 197
    },
    {
      "epoch": 0.668918918918919,
      "grad_norm": 2.128573417663574,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.7261,
      "step": 198
    },
    {
      "epoch": 0.6722972972972973,
      "grad_norm": 2.5201845169067383,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.921,
      "step": 199
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 3.6946332454681396,
      "learning_rate": 0.0,
      "loss": 0.9138,
      "step": 200
    },
    {
      "epoch": 0.6756756756756757,
      "eval_loss": 0.8919714689254761,
      "eval_runtime": 46.3883,
      "eval_samples_per_second": 10.757,
      "eval_steps_per_second": 5.389,
      "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": 3.1421973496489574e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}