{
  "best_metric": 0.5327957272529602,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.09757684176288828,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006505122784192552,
      "grad_norm": 2.2949790954589844,
      "learning_rate": 1e-05,
      "loss": 0.8464,
      "step": 1
    },
    {
      "epoch": 0.0006505122784192552,
      "eval_loss": 1.1010671854019165,
      "eval_runtime": 225.9342,
      "eval_samples_per_second": 11.459,
      "eval_steps_per_second": 2.868,
      "step": 1
    },
    {
      "epoch": 0.0013010245568385104,
      "grad_norm": 2.2324092388153076,
      "learning_rate": 2e-05,
      "loss": 0.9257,
      "step": 2
    },
    {
      "epoch": 0.0019515368352577655,
      "grad_norm": 2.1922740936279297,
      "learning_rate": 3e-05,
      "loss": 0.9139,
      "step": 3
    },
    {
      "epoch": 0.002602049113677021,
      "grad_norm": 1.8555798530578613,
      "learning_rate": 4e-05,
      "loss": 0.8596,
      "step": 4
    },
    {
      "epoch": 0.0032525613920962758,
      "grad_norm": 1.3310691118240356,
      "learning_rate": 5e-05,
      "loss": 0.8129,
      "step": 5
    },
    {
      "epoch": 0.003903073670515531,
      "grad_norm": 1.4598994255065918,
      "learning_rate": 6e-05,
      "loss": 0.8001,
      "step": 6
    },
    {
      "epoch": 0.004553585948934786,
      "grad_norm": 1.0326259136199951,
      "learning_rate": 7e-05,
      "loss": 0.8037,
      "step": 7
    },
    {
      "epoch": 0.005204098227354042,
      "grad_norm": 0.9346097111701965,
      "learning_rate": 8e-05,
      "loss": 0.7213,
      "step": 8
    },
    {
      "epoch": 0.005854610505773296,
      "grad_norm": 1.0862377882003784,
      "learning_rate": 9e-05,
      "loss": 0.6712,
      "step": 9
    },
    {
      "epoch": 0.0065051227841925515,
      "grad_norm": 1.018910527229309,
      "learning_rate": 0.0001,
      "loss": 0.667,
      "step": 10
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.6956149339675903,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6102,
      "step": 11
    },
    {
      "epoch": 0.007806147341031062,
      "grad_norm": 0.6657171249389648,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6175,
      "step": 12
    },
    {
      "epoch": 0.008456659619450317,
      "grad_norm": 0.7219452857971191,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6315,
      "step": 13
    },
    {
      "epoch": 0.009107171897869573,
      "grad_norm": 0.62117999792099,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.65,
      "step": 14
    },
    {
      "epoch": 0.009757684176288828,
      "grad_norm": 0.6254481077194214,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6393,
      "step": 15
    },
    {
      "epoch": 0.010408196454708083,
      "grad_norm": 0.6195070147514343,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.592,
      "step": 16
    },
    {
      "epoch": 0.011058708733127337,
      "grad_norm": 0.5411797165870667,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6459,
      "step": 17
    },
    {
      "epoch": 0.011709221011546592,
      "grad_norm": 0.5817526578903198,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5603,
      "step": 18
    },
    {
      "epoch": 0.012359733289965848,
      "grad_norm": 0.6312760710716248,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6331,
      "step": 19
    },
    {
      "epoch": 0.013010245568385103,
      "grad_norm": 0.6199807524681091,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.629,
      "step": 20
    },
    {
      "epoch": 0.013660757846804358,
      "grad_norm": 0.6306931376457214,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5431,
      "step": 21
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 0.6139870285987854,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.5755,
      "step": 22
    },
    {
      "epoch": 0.014961782403642869,
      "grad_norm": 0.6658226251602173,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5684,
      "step": 23
    },
    {
      "epoch": 0.015612294682062124,
      "grad_norm": 0.7177361249923706,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6777,
      "step": 24
    },
    {
      "epoch": 0.01626280696048138,
      "grad_norm": 0.6909174919128418,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5737,
      "step": 25
    },
    {
      "epoch": 0.016913319238900635,
      "grad_norm": 0.7341168522834778,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6242,
      "step": 26
    },
    {
      "epoch": 0.01756383151731989,
      "grad_norm": 0.8555698990821838,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5939,
      "step": 27
    },
    {
      "epoch": 0.018214343795739146,
      "grad_norm": 0.7126067876815796,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.5509,
      "step": 28
    },
    {
      "epoch": 0.0188648560741584,
      "grad_norm": 0.8014953136444092,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5955,
      "step": 29
    },
    {
      "epoch": 0.019515368352577656,
      "grad_norm": 0.7740756273269653,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5317,
      "step": 30
    },
    {
      "epoch": 0.02016588063099691,
      "grad_norm": 0.8383130431175232,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4973,
      "step": 31
    },
    {
      "epoch": 0.020816392909416167,
      "grad_norm": 0.8901905417442322,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.5898,
      "step": 32
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 0.929298460483551,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5496,
      "step": 33
    },
    {
      "epoch": 0.022117417466254674,
      "grad_norm": 0.9338362812995911,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5409,
      "step": 34
    },
    {
      "epoch": 0.02276792974467393,
      "grad_norm": 1.0635957717895508,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6963,
      "step": 35
    },
    {
      "epoch": 0.023418442023093185,
      "grad_norm": 1.1843456029891968,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6314,
      "step": 36
    },
    {
      "epoch": 0.02406895430151244,
      "grad_norm": 1.212092399597168,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7096,
      "step": 37
    },
    {
      "epoch": 0.024719466579931695,
      "grad_norm": 1.2463839054107666,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6429,
      "step": 38
    },
    {
      "epoch": 0.02536997885835095,
      "grad_norm": 1.3894529342651367,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6124,
      "step": 39
    },
    {
      "epoch": 0.026020491136770206,
      "grad_norm": 1.2939448356628418,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.553,
      "step": 40
    },
    {
      "epoch": 0.02667100341518946,
      "grad_norm": 1.412766456604004,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7204,
      "step": 41
    },
    {
      "epoch": 0.027321515693608717,
      "grad_norm": 1.5141947269439697,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.5901,
      "step": 42
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 2.5415799617767334,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7202,
      "step": 43
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 1.7570736408233643,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.726,
      "step": 44
    },
    {
      "epoch": 0.029273052528866483,
      "grad_norm": 1.7827636003494263,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8471,
      "step": 45
    },
    {
      "epoch": 0.029923564807285738,
      "grad_norm": 1.8962596654891968,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7818,
      "step": 46
    },
    {
      "epoch": 0.030574077085704993,
      "grad_norm": 2.1778807640075684,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7733,
      "step": 47
    },
    {
      "epoch": 0.03122458936412425,
      "grad_norm": 3.002967119216919,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1326,
      "step": 48
    },
    {
      "epoch": 0.0318751016425435,
      "grad_norm": 3.5161192417144775,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0833,
      "step": 49
    },
    {
      "epoch": 0.03252561392096276,
      "grad_norm": 5.6279520988464355,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.9583,
      "step": 50
    },
    {
      "epoch": 0.03252561392096276,
      "eval_loss": 0.7558156847953796,
      "eval_runtime": 228.1278,
      "eval_samples_per_second": 11.349,
      "eval_steps_per_second": 2.841,
      "step": 50
    },
    {
      "epoch": 0.03317612619938201,
      "grad_norm": 2.402822971343994,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7257,
      "step": 51
    },
    {
      "epoch": 0.03382663847780127,
      "grad_norm": 0.8722525238990784,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6421,
      "step": 52
    },
    {
      "epoch": 0.03447715075622052,
      "grad_norm": 0.5016583204269409,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.561,
      "step": 53
    },
    {
      "epoch": 0.03512766303463978,
      "grad_norm": 0.46404463052749634,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5807,
      "step": 54
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 0.48941487073898315,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5669,
      "step": 55
    },
    {
      "epoch": 0.03642868759147829,
      "grad_norm": 0.47314688563346863,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5636,
      "step": 56
    },
    {
      "epoch": 0.03707919986989754,
      "grad_norm": 0.39816829562187195,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5548,
      "step": 57
    },
    {
      "epoch": 0.0377297121483168,
      "grad_norm": 0.34830227494239807,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5047,
      "step": 58
    },
    {
      "epoch": 0.038380224426736054,
      "grad_norm": 0.3596019446849823,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5081,
      "step": 59
    },
    {
      "epoch": 0.03903073670515531,
      "grad_norm": 0.4330965280532837,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5034,
      "step": 60
    },
    {
      "epoch": 0.039681248983574564,
      "grad_norm": 0.4778791069984436,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.5388,
      "step": 61
    },
    {
      "epoch": 0.04033176126199382,
      "grad_norm": 0.4124755561351776,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5341,
      "step": 62
    },
    {
      "epoch": 0.040982273540413075,
      "grad_norm": 0.4322037398815155,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5308,
      "step": 63
    },
    {
      "epoch": 0.041632785818832334,
      "grad_norm": 0.37707215547561646,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5351,
      "step": 64
    },
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 0.38587695360183716,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5245,
      "step": 65
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 0.3754536807537079,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5087,
      "step": 66
    },
    {
      "epoch": 0.043584322654090096,
      "grad_norm": 0.4021326005458832,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5064,
      "step": 67
    },
    {
      "epoch": 0.04423483493250935,
      "grad_norm": 0.40743595361709595,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4882,
      "step": 68
    },
    {
      "epoch": 0.04488534721092861,
      "grad_norm": 0.4270361363887787,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4885,
      "step": 69
    },
    {
      "epoch": 0.04553585948934786,
      "grad_norm": 0.48390692472457886,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5603,
      "step": 70
    },
    {
      "epoch": 0.04618637176776712,
      "grad_norm": 0.4888385236263275,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5221,
      "step": 71
    },
    {
      "epoch": 0.04683688404618637,
      "grad_norm": 0.5319409370422363,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5328,
      "step": 72
    },
    {
      "epoch": 0.04748739632460563,
      "grad_norm": 0.5580947995185852,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5087,
      "step": 73
    },
    {
      "epoch": 0.04813790860302488,
      "grad_norm": 0.525851845741272,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4954,
      "step": 74
    },
    {
      "epoch": 0.04878842088144414,
      "grad_norm": 0.5526361465454102,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5223,
      "step": 75
    },
    {
      "epoch": 0.04943893315986339,
      "grad_norm": 0.6409172415733337,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5512,
      "step": 76
    },
    {
      "epoch": 0.05008944543828265,
      "grad_norm": 0.6490181088447571,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5253,
      "step": 77
    },
    {
      "epoch": 0.0507399577167019,
      "grad_norm": 0.6886270046234131,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5336,
      "step": 78
    },
    {
      "epoch": 0.05139046999512116,
      "grad_norm": 0.737156867980957,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4642,
      "step": 79
    },
    {
      "epoch": 0.05204098227354041,
      "grad_norm": 0.7656813859939575,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4769,
      "step": 80
    },
    {
      "epoch": 0.05269149455195967,
      "grad_norm": 0.7651960253715515,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.613,
      "step": 81
    },
    {
      "epoch": 0.05334200683037892,
      "grad_norm": 0.8492389917373657,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5773,
      "step": 82
    },
    {
      "epoch": 0.05399251910879818,
      "grad_norm": 1.0014947652816772,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4905,
      "step": 83
    },
    {
      "epoch": 0.05464303138721743,
      "grad_norm": 0.9230720400810242,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6105,
      "step": 84
    },
    {
      "epoch": 0.05529354366563669,
      "grad_norm": 1.0558102130889893,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.594,
      "step": 85
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 1.084924340248108,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4895,
      "step": 86
    },
    {
      "epoch": 0.056594568222475196,
      "grad_norm": 1.0449389219284058,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5494,
      "step": 87
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 1.2263356447219849,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6002,
      "step": 88
    },
    {
      "epoch": 0.057895592779313707,
      "grad_norm": 1.04475998878479,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5376,
      "step": 89
    },
    {
      "epoch": 0.058546105057732965,
      "grad_norm": 1.0622400045394897,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5262,
      "step": 90
    },
    {
      "epoch": 0.05919661733615222,
      "grad_norm": 1.1666251420974731,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5517,
      "step": 91
    },
    {
      "epoch": 0.059847129614571476,
      "grad_norm": 1.2639423608779907,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5709,
      "step": 92
    },
    {
      "epoch": 0.06049764189299073,
      "grad_norm": 1.8228390216827393,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.8093,
      "step": 93
    },
    {
      "epoch": 0.06114815417140999,
      "grad_norm": 1.2995976209640503,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6058,
      "step": 94
    },
    {
      "epoch": 0.06179866644982924,
      "grad_norm": 2.259472131729126,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7706,
      "step": 95
    },
    {
      "epoch": 0.0624491787282485,
      "grad_norm": 1.6438156366348267,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6221,
      "step": 96
    },
    {
      "epoch": 0.06309969100666775,
      "grad_norm": 2.0552380084991455,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6719,
      "step": 97
    },
    {
      "epoch": 0.063750203285087,
      "grad_norm": 2.218015432357788,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8165,
      "step": 98
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 2.8057336807250977,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9923,
      "step": 99
    },
    {
      "epoch": 0.06505122784192552,
      "grad_norm": 3.799156665802002,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5307,
      "step": 100
    },
    {
      "epoch": 0.06505122784192552,
      "eval_loss": 0.6059337258338928,
      "eval_runtime": 227.6134,
      "eval_samples_per_second": 11.375,
      "eval_steps_per_second": 2.847,
      "step": 100
    },
    {
      "epoch": 0.06570174012034477,
      "grad_norm": 0.637094259262085,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5253,
      "step": 101
    },
    {
      "epoch": 0.06635225239876402,
      "grad_norm": 0.599916398525238,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5528,
      "step": 102
    },
    {
      "epoch": 0.06700276467718329,
      "grad_norm": 0.4817359745502472,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5153,
      "step": 103
    },
    {
      "epoch": 0.06765327695560254,
      "grad_norm": 0.39705970883369446,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5489,
      "step": 104
    },
    {
      "epoch": 0.06830378923402179,
      "grad_norm": 0.34305521845817566,
      "learning_rate": 5e-05,
      "loss": 0.5207,
      "step": 105
    },
    {
      "epoch": 0.06895430151244104,
      "grad_norm": 0.32512378692626953,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5064,
      "step": 106
    },
    {
      "epoch": 0.06960481379086031,
      "grad_norm": 0.3627694547176361,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4779,
      "step": 107
    },
    {
      "epoch": 0.07025532606927956,
      "grad_norm": 0.3716387450695038,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4603,
      "step": 108
    },
    {
      "epoch": 0.07090583834769881,
      "grad_norm": 0.35102540254592896,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5064,
      "step": 109
    },
    {
      "epoch": 0.07155635062611806,
      "grad_norm": 0.3579176068305969,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.455,
      "step": 110
    },
    {
      "epoch": 0.07220686290453732,
      "grad_norm": 0.3392593264579773,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.4652,
      "step": 111
    },
    {
      "epoch": 0.07285737518295658,
      "grad_norm": 0.34145838022232056,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.467,
      "step": 112
    },
    {
      "epoch": 0.07350788746137583,
      "grad_norm": 0.37018686532974243,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4932,
      "step": 113
    },
    {
      "epoch": 0.07415839973979509,
      "grad_norm": 0.3474339544773102,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4796,
      "step": 114
    },
    {
      "epoch": 0.07480891201821434,
      "grad_norm": 0.3826667368412018,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4802,
      "step": 115
    },
    {
      "epoch": 0.0754594242966336,
      "grad_norm": 0.3888989984989166,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4936,
      "step": 116
    },
    {
      "epoch": 0.07610993657505286,
      "grad_norm": 0.432449609041214,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5144,
      "step": 117
    },
    {
      "epoch": 0.07676044885347211,
      "grad_norm": 0.41924527287483215,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4909,
      "step": 118
    },
    {
      "epoch": 0.07741096113189136,
      "grad_norm": 0.41541555523872375,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5197,
      "step": 119
    },
    {
      "epoch": 0.07806147341031063,
      "grad_norm": 0.4510447382926941,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5248,
      "step": 120
    },
    {
      "epoch": 0.07871198568872988,
      "grad_norm": 0.4221785068511963,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4601,
      "step": 121
    },
    {
      "epoch": 0.07936249796714913,
      "grad_norm": 0.46180105209350586,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5048,
      "step": 122
    },
    {
      "epoch": 0.08001301024556838,
      "grad_norm": 0.4956487715244293,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5569,
      "step": 123
    },
    {
      "epoch": 0.08066352252398765,
      "grad_norm": 0.4890901446342468,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4804,
      "step": 124
    },
    {
      "epoch": 0.0813140348024069,
      "grad_norm": 0.5268025398254395,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4963,
      "step": 125
    },
    {
      "epoch": 0.08196454708082615,
      "grad_norm": 0.5740827918052673,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.4952,
      "step": 126
    },
    {
      "epoch": 0.0826150593592454,
      "grad_norm": 0.5646161437034607,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5361,
      "step": 127
    },
    {
      "epoch": 0.08326557163766467,
      "grad_norm": 0.6213480830192566,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5249,
      "step": 128
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 0.6687480807304382,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5012,
      "step": 129
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 0.7159056663513184,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4773,
      "step": 130
    },
    {
      "epoch": 0.08521710847292242,
      "grad_norm": 0.6956769227981567,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4477,
      "step": 131
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 0.7657418251037598,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.515,
      "step": 132
    },
    {
      "epoch": 0.08651813302976094,
      "grad_norm": 0.7959651350975037,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5104,
      "step": 133
    },
    {
      "epoch": 0.08716864530818019,
      "grad_norm": 0.8080943822860718,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.516,
      "step": 134
    },
    {
      "epoch": 0.08781915758659944,
      "grad_norm": 0.7299286723136902,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4539,
      "step": 135
    },
    {
      "epoch": 0.0884696698650187,
      "grad_norm": 1.051796317100525,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5395,
      "step": 136
    },
    {
      "epoch": 0.08912018214343796,
      "grad_norm": 0.9961816072463989,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5078,
      "step": 137
    },
    {
      "epoch": 0.08977069442185721,
      "grad_norm": 0.8709666132926941,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4263,
      "step": 138
    },
    {
      "epoch": 0.09042120670027647,
      "grad_norm": 1.115434169769287,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6271,
      "step": 139
    },
    {
      "epoch": 0.09107171897869572,
      "grad_norm": 0.9747127890586853,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.4777,
      "step": 140
    },
    {
      "epoch": 0.09172223125711498,
      "grad_norm": 1.0018984079360962,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3506,
      "step": 141
    },
    {
      "epoch": 0.09237274353553424,
      "grad_norm": 1.0737371444702148,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5032,
      "step": 142
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 1.1634116172790527,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6872,
      "step": 143
    },
    {
      "epoch": 0.09367376809237274,
      "grad_norm": 1.504170298576355,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5959,
      "step": 144
    },
    {
      "epoch": 0.094324280370792,
      "grad_norm": 1.6308207511901855,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7022,
      "step": 145
    },
    {
      "epoch": 0.09497479264921126,
      "grad_norm": 1.188438892364502,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5,
      "step": 146
    },
    {
      "epoch": 0.09562530492763051,
      "grad_norm": 1.8830289840698242,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6046,
      "step": 147
    },
    {
      "epoch": 0.09627581720604976,
      "grad_norm": 1.6358462572097778,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.648,
      "step": 148
    },
    {
      "epoch": 0.09692632948446903,
      "grad_norm": 2.61712646484375,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.9717,
      "step": 149
    },
    {
      "epoch": 0.09757684176288828,
      "grad_norm": 2.530785083770752,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9381,
      "step": 150
    },
    {
      "epoch": 0.09757684176288828,
      "eval_loss": 0.5327957272529602,
      "eval_runtime": 227.4047,
      "eval_samples_per_second": 11.385,
      "eval_steps_per_second": 2.85,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.545616664133632e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}