{
  "best_metric": 0.6764784455299377,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9913258983890955,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004956629491945477,
      "grad_norm": 0.6551672220230103,
      "learning_rate": 1e-05,
      "loss": 1.1722,
      "step": 1
    },
    {
      "epoch": 0.004956629491945477,
      "eval_loss": 1.1753363609313965,
      "eval_runtime": 23.6031,
      "eval_samples_per_second": 14.405,
      "eval_steps_per_second": 3.601,
      "step": 1
    },
    {
      "epoch": 0.009913258983890954,
      "grad_norm": 0.6826586127281189,
      "learning_rate": 2e-05,
      "loss": 1.2373,
      "step": 2
    },
    {
      "epoch": 0.01486988847583643,
      "grad_norm": 0.6642441153526306,
      "learning_rate": 3e-05,
      "loss": 1.0669,
      "step": 3
    },
    {
      "epoch": 0.01982651796778191,
      "grad_norm": 0.6983931660652161,
      "learning_rate": 4e-05,
      "loss": 1.1305,
      "step": 4
    },
    {
      "epoch": 0.024783147459727387,
      "grad_norm": 0.6615077257156372,
      "learning_rate": 5e-05,
      "loss": 1.1909,
      "step": 5
    },
    {
      "epoch": 0.02973977695167286,
      "grad_norm": 0.583685576915741,
      "learning_rate": 6e-05,
      "loss": 1.1258,
      "step": 6
    },
    {
      "epoch": 0.03469640644361834,
      "grad_norm": 0.6778571009635925,
      "learning_rate": 7e-05,
      "loss": 1.1156,
      "step": 7
    },
    {
      "epoch": 0.03965303593556382,
      "grad_norm": 0.5788799524307251,
      "learning_rate": 8e-05,
      "loss": 0.9725,
      "step": 8
    },
    {
      "epoch": 0.04460966542750929,
      "grad_norm": 0.6441173553466797,
      "learning_rate": 9e-05,
      "loss": 1.0046,
      "step": 9
    },
    {
      "epoch": 0.04956629491945477,
      "grad_norm": 0.55350261926651,
      "learning_rate": 0.0001,
      "loss": 0.9701,
      "step": 10
    },
    {
      "epoch": 0.05452292441140025,
      "grad_norm": 0.5877435207366943,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9641,
      "step": 11
    },
    {
      "epoch": 0.05947955390334572,
      "grad_norm": 0.5821601152420044,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9529,
      "step": 12
    },
    {
      "epoch": 0.0644361833952912,
      "grad_norm": 0.6139052510261536,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9343,
      "step": 13
    },
    {
      "epoch": 0.06939281288723669,
      "grad_norm": 0.5948969125747681,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9363,
      "step": 14
    },
    {
      "epoch": 0.07434944237918216,
      "grad_norm": 0.5801020264625549,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8979,
      "step": 15
    },
    {
      "epoch": 0.07930607187112763,
      "grad_norm": 0.5656048059463501,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8968,
      "step": 16
    },
    {
      "epoch": 0.08426270136307311,
      "grad_norm": 0.6554778814315796,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8984,
      "step": 17
    },
    {
      "epoch": 0.08921933085501858,
      "grad_norm": 0.5542401075363159,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8711,
      "step": 18
    },
    {
      "epoch": 0.09417596034696406,
      "grad_norm": 0.5345842242240906,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7886,
      "step": 19
    },
    {
      "epoch": 0.09913258983890955,
      "grad_norm": 0.6311167478561401,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8453,
      "step": 20
    },
    {
      "epoch": 0.10408921933085502,
      "grad_norm": 0.5669831037521362,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8242,
      "step": 21
    },
    {
      "epoch": 0.1090458488228005,
      "grad_norm": 0.5808326601982117,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7666,
      "step": 22
    },
    {
      "epoch": 0.11400247831474597,
      "grad_norm": 0.5470030307769775,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.785,
      "step": 23
    },
    {
      "epoch": 0.11895910780669144,
      "grad_norm": 0.5734890103340149,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8415,
      "step": 24
    },
    {
      "epoch": 0.12391573729863693,
      "grad_norm": 0.5663146376609802,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7929,
      "step": 25
    },
    {
      "epoch": 0.1288723667905824,
      "grad_norm": 0.5330767631530762,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7838,
      "step": 26
    },
    {
      "epoch": 0.13382899628252787,
      "grad_norm": 0.5506221055984497,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.696,
      "step": 27
    },
    {
      "epoch": 0.13878562577447337,
      "grad_norm": 0.5457439422607422,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6787,
      "step": 28
    },
    {
      "epoch": 0.14374225526641884,
      "grad_norm": 0.6192253232002258,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7282,
      "step": 29
    },
    {
      "epoch": 0.14869888475836432,
      "grad_norm": 0.5618070363998413,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6956,
      "step": 30
    },
    {
      "epoch": 0.1536555142503098,
      "grad_norm": 0.6458665132522583,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.74,
      "step": 31
    },
    {
      "epoch": 0.15861214374225527,
      "grad_norm": 0.7586070895195007,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6503,
      "step": 32
    },
    {
      "epoch": 0.16356877323420074,
      "grad_norm": 0.5998969078063965,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6902,
      "step": 33
    },
    {
      "epoch": 0.16852540272614622,
      "grad_norm": 0.5648677945137024,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6133,
      "step": 34
    },
    {
      "epoch": 0.1734820322180917,
      "grad_norm": 0.5768397450447083,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5753,
      "step": 35
    },
    {
      "epoch": 0.17843866171003717,
      "grad_norm": 0.6712425947189331,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7281,
      "step": 36
    },
    {
      "epoch": 0.18339529120198264,
      "grad_norm": 0.6974000334739685,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.676,
      "step": 37
    },
    {
      "epoch": 0.18835192069392812,
      "grad_norm": 0.5842344164848328,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6485,
      "step": 38
    },
    {
      "epoch": 0.19330855018587362,
      "grad_norm": 0.6496119499206543,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6586,
      "step": 39
    },
    {
      "epoch": 0.1982651796778191,
      "grad_norm": 0.6950006484985352,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6503,
      "step": 40
    },
    {
      "epoch": 0.20322180916976457,
      "grad_norm": 0.6577513813972473,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6566,
      "step": 41
    },
    {
      "epoch": 0.20817843866171004,
      "grad_norm": 0.6512104272842407,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4909,
      "step": 42
    },
    {
      "epoch": 0.21313506815365552,
      "grad_norm": 0.693815290927887,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7017,
      "step": 43
    },
    {
      "epoch": 0.218091697645601,
      "grad_norm": 0.7533928155899048,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.665,
      "step": 44
    },
    {
      "epoch": 0.22304832713754646,
      "grad_norm": 0.6688750982284546,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5542,
      "step": 45
    },
    {
      "epoch": 0.22800495662949194,
      "grad_norm": 0.7041953206062317,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.615,
      "step": 46
    },
    {
      "epoch": 0.23296158612143741,
      "grad_norm": 0.655926525592804,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6108,
      "step": 47
    },
    {
      "epoch": 0.2379182156133829,
      "grad_norm": 0.7904329895973206,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6714,
      "step": 48
    },
    {
      "epoch": 0.24287484510532836,
      "grad_norm": 0.7624610066413879,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6604,
      "step": 49
    },
    {
      "epoch": 0.24783147459727387,
      "grad_norm": 0.8460170030593872,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5722,
      "step": 50
    },
    {
      "epoch": 0.24783147459727387,
      "eval_loss": 0.8346107006072998,
      "eval_runtime": 23.9905,
      "eval_samples_per_second": 14.172,
      "eval_steps_per_second": 3.543,
      "step": 50
    },
    {
      "epoch": 0.2527881040892193,
      "grad_norm": 0.65602046251297,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.1105,
      "step": 51
    },
    {
      "epoch": 0.2577447335811648,
      "grad_norm": 0.6289058327674866,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.03,
      "step": 52
    },
    {
      "epoch": 0.26270136307311026,
      "grad_norm": 0.5790162086486816,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0225,
      "step": 53
    },
    {
      "epoch": 0.26765799256505574,
      "grad_norm": 0.4905504882335663,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.022,
      "step": 54
    },
    {
      "epoch": 0.27261462205700127,
      "grad_norm": 0.4524228274822235,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9548,
      "step": 55
    },
    {
      "epoch": 0.27757125154894674,
      "grad_norm": 0.40620067715644836,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9094,
      "step": 56
    },
    {
      "epoch": 0.2825278810408922,
      "grad_norm": 0.41593360900878906,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9294,
      "step": 57
    },
    {
      "epoch": 0.2874845105328377,
      "grad_norm": 0.47059690952301025,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.963,
      "step": 58
    },
    {
      "epoch": 0.29244114002478316,
      "grad_norm": 0.499554842710495,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8842,
      "step": 59
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 0.5072277188301086,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.86,
      "step": 60
    },
    {
      "epoch": 0.3023543990086741,
      "grad_norm": 0.44685372710227966,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8649,
      "step": 61
    },
    {
      "epoch": 0.3073110285006196,
      "grad_norm": 0.4483942985534668,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8563,
      "step": 62
    },
    {
      "epoch": 0.31226765799256506,
      "grad_norm": 0.43982598185539246,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8089,
      "step": 63
    },
    {
      "epoch": 0.31722428748451054,
      "grad_norm": 0.4353708028793335,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8223,
      "step": 64
    },
    {
      "epoch": 0.322180916976456,
      "grad_norm": 0.4410320222377777,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8534,
      "step": 65
    },
    {
      "epoch": 0.3271375464684015,
      "grad_norm": 0.48935315012931824,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8127,
      "step": 66
    },
    {
      "epoch": 0.33209417596034696,
      "grad_norm": 0.4864257276058197,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7628,
      "step": 67
    },
    {
      "epoch": 0.33705080545229243,
      "grad_norm": 0.49484875798225403,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7977,
      "step": 68
    },
    {
      "epoch": 0.3420074349442379,
      "grad_norm": 0.4818640947341919,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8183,
      "step": 69
    },
    {
      "epoch": 0.3469640644361834,
      "grad_norm": 0.47488537430763245,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7721,
      "step": 70
    },
    {
      "epoch": 0.35192069392812886,
      "grad_norm": 0.44666656851768494,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6906,
      "step": 71
    },
    {
      "epoch": 0.35687732342007433,
      "grad_norm": 0.46575626730918884,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7328,
      "step": 72
    },
    {
      "epoch": 0.3618339529120198,
      "grad_norm": 0.5485712885856628,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7341,
      "step": 73
    },
    {
      "epoch": 0.3667905824039653,
      "grad_norm": 0.5232682228088379,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7438,
      "step": 74
    },
    {
      "epoch": 0.37174721189591076,
      "grad_norm": 0.550430178642273,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7291,
      "step": 75
    },
    {
      "epoch": 0.37670384138785623,
      "grad_norm": 0.4753236770629883,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7265,
      "step": 76
    },
    {
      "epoch": 0.38166047087980176,
      "grad_norm": 0.4926081597805023,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6355,
      "step": 77
    },
    {
      "epoch": 0.38661710037174724,
      "grad_norm": 0.4810488224029541,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6525,
      "step": 78
    },
    {
      "epoch": 0.3915737298636927,
      "grad_norm": 0.5469344258308411,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6838,
      "step": 79
    },
    {
      "epoch": 0.3965303593556382,
      "grad_norm": 0.4801713824272156,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6063,
      "step": 80
    },
    {
      "epoch": 0.40148698884758366,
      "grad_norm": 0.6041094064712524,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7271,
      "step": 81
    },
    {
      "epoch": 0.40644361833952913,
      "grad_norm": 0.6448431015014648,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7497,
      "step": 82
    },
    {
      "epoch": 0.4114002478314746,
      "grad_norm": 0.6015984416007996,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5569,
      "step": 83
    },
    {
      "epoch": 0.4163568773234201,
      "grad_norm": 0.6136460304260254,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.637,
      "step": 84
    },
    {
      "epoch": 0.42131350681536556,
      "grad_norm": 0.6079061627388,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.5966,
      "step": 85
    },
    {
      "epoch": 0.42627013630731103,
      "grad_norm": 0.5880423784255981,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5901,
      "step": 86
    },
    {
      "epoch": 0.4312267657992565,
      "grad_norm": 0.6579607725143433,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6095,
      "step": 87
    },
    {
      "epoch": 0.436183395291202,
      "grad_norm": 0.5934492945671082,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4581,
      "step": 88
    },
    {
      "epoch": 0.44114002478314746,
      "grad_norm": 0.6323069930076599,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5928,
      "step": 89
    },
    {
      "epoch": 0.44609665427509293,
      "grad_norm": 0.6292123198509216,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.567,
      "step": 90
    },
    {
      "epoch": 0.4510532837670384,
      "grad_norm": 0.6272173523902893,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.533,
      "step": 91
    },
    {
      "epoch": 0.4560099132589839,
      "grad_norm": 0.7664792537689209,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5924,
      "step": 92
    },
    {
      "epoch": 0.46096654275092935,
      "grad_norm": 0.677821695804596,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5892,
      "step": 93
    },
    {
      "epoch": 0.46592317224287483,
      "grad_norm": 0.7719601392745972,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5561,
      "step": 94
    },
    {
      "epoch": 0.4708798017348203,
      "grad_norm": 0.7773162722587585,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.5677,
      "step": 95
    },
    {
      "epoch": 0.4758364312267658,
      "grad_norm": 0.8218184113502502,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5172,
      "step": 96
    },
    {
      "epoch": 0.48079306071871125,
      "grad_norm": 0.8294799327850342,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5973,
      "step": 97
    },
    {
      "epoch": 0.4857496902106567,
      "grad_norm": 0.7562800645828247,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5482,
      "step": 98
    },
    {
      "epoch": 0.49070631970260226,
      "grad_norm": 1.0434385538101196,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5749,
      "step": 99
    },
    {
      "epoch": 0.49566294919454773,
      "grad_norm": 1.0909229516983032,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5463,
      "step": 100
    },
    {
      "epoch": 0.49566294919454773,
      "eval_loss": 0.7638482451438904,
      "eval_runtime": 24.003,
      "eval_samples_per_second": 14.165,
      "eval_steps_per_second": 3.541,
      "step": 100
    },
    {
      "epoch": 0.5006195786864932,
      "grad_norm": 0.5023981332778931,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0229,
      "step": 101
    },
    {
      "epoch": 0.5055762081784386,
      "grad_norm": 0.5211355090141296,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.973,
      "step": 102
    },
    {
      "epoch": 0.5105328376703842,
      "grad_norm": 0.4933766722679138,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9632,
      "step": 103
    },
    {
      "epoch": 0.5154894671623296,
      "grad_norm": 0.4906304180622101,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.9918,
      "step": 104
    },
    {
      "epoch": 0.5204460966542751,
      "grad_norm": 0.4567563831806183,
      "learning_rate": 5e-05,
      "loss": 0.9307,
      "step": 105
    },
    {
      "epoch": 0.5254027261462205,
      "grad_norm": 0.44538241624832153,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9375,
      "step": 106
    },
    {
      "epoch": 0.530359355638166,
      "grad_norm": 0.4188775420188904,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.928,
      "step": 107
    },
    {
      "epoch": 0.5353159851301115,
      "grad_norm": 0.434192031621933,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8674,
      "step": 108
    },
    {
      "epoch": 0.540272614622057,
      "grad_norm": 0.4122578501701355,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8052,
      "step": 109
    },
    {
      "epoch": 0.5452292441140025,
      "grad_norm": 0.42325156927108765,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8715,
      "step": 110
    },
    {
      "epoch": 0.550185873605948,
      "grad_norm": 0.42967715859413147,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8638,
      "step": 111
    },
    {
      "epoch": 0.5551425030978935,
      "grad_norm": 0.42912817001342773,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8404,
      "step": 112
    },
    {
      "epoch": 0.5600991325898389,
      "grad_norm": 0.46107280254364014,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8096,
      "step": 113
    },
    {
      "epoch": 0.5650557620817844,
      "grad_norm": 0.45877736806869507,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8399,
      "step": 114
    },
    {
      "epoch": 0.5700123915737298,
      "grad_norm": 0.4855491518974304,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8369,
      "step": 115
    },
    {
      "epoch": 0.5749690210656754,
      "grad_norm": 0.4686594605445862,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7819,
      "step": 116
    },
    {
      "epoch": 0.5799256505576208,
      "grad_norm": 0.49340590834617615,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7497,
      "step": 117
    },
    {
      "epoch": 0.5848822800495663,
      "grad_norm": 0.5167107582092285,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8218,
      "step": 118
    },
    {
      "epoch": 0.5898389095415117,
      "grad_norm": 0.5384970307350159,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8151,
      "step": 119
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 0.4882941246032715,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7938,
      "step": 120
    },
    {
      "epoch": 0.5997521685254027,
      "grad_norm": 0.5063373446464539,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7772,
      "step": 121
    },
    {
      "epoch": 0.6047087980173482,
      "grad_norm": 0.4765776991844177,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7102,
      "step": 122
    },
    {
      "epoch": 0.6096654275092936,
      "grad_norm": 0.5131629109382629,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7152,
      "step": 123
    },
    {
      "epoch": 0.6146220570012392,
      "grad_norm": 0.47607874870300293,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7172,
      "step": 124
    },
    {
      "epoch": 0.6195786864931846,
      "grad_norm": 0.4758664071559906,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.659,
      "step": 125
    },
    {
      "epoch": 0.6245353159851301,
      "grad_norm": 0.5227712392807007,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7159,
      "step": 126
    },
    {
      "epoch": 0.6294919454770755,
      "grad_norm": 0.5005256533622742,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6824,
      "step": 127
    },
    {
      "epoch": 0.6344485749690211,
      "grad_norm": 0.48185092210769653,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6837,
      "step": 128
    },
    {
      "epoch": 0.6394052044609665,
      "grad_norm": 0.5223903059959412,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6007,
      "step": 129
    },
    {
      "epoch": 0.644361833952912,
      "grad_norm": 0.48540663719177246,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6396,
      "step": 130
    },
    {
      "epoch": 0.6493184634448576,
      "grad_norm": 0.5397007465362549,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6168,
      "step": 131
    },
    {
      "epoch": 0.654275092936803,
      "grad_norm": 0.5073583722114563,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5625,
      "step": 132
    },
    {
      "epoch": 0.6592317224287485,
      "grad_norm": 0.5540064573287964,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6417,
      "step": 133
    },
    {
      "epoch": 0.6641883519206939,
      "grad_norm": 0.4741589426994324,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5587,
      "step": 134
    },
    {
      "epoch": 0.6691449814126395,
      "grad_norm": 0.5689728856086731,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6155,
      "step": 135
    },
    {
      "epoch": 0.6741016109045849,
      "grad_norm": 0.5467251539230347,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5297,
      "step": 136
    },
    {
      "epoch": 0.6790582403965304,
      "grad_norm": 0.5826081037521362,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.613,
      "step": 137
    },
    {
      "epoch": 0.6840148698884758,
      "grad_norm": 0.6468902230262756,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5672,
      "step": 138
    },
    {
      "epoch": 0.6889714993804213,
      "grad_norm": 0.5582059025764465,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5052,
      "step": 139
    },
    {
      "epoch": 0.6939281288723668,
      "grad_norm": 0.6163714528083801,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5872,
      "step": 140
    },
    {
      "epoch": 0.6988847583643123,
      "grad_norm": 0.7038082480430603,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5229,
      "step": 141
    },
    {
      "epoch": 0.7038413878562577,
      "grad_norm": 0.5957319140434265,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5916,
      "step": 142
    },
    {
      "epoch": 0.7087980173482032,
      "grad_norm": 0.6092044115066528,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.487,
      "step": 143
    },
    {
      "epoch": 0.7137546468401487,
      "grad_norm": 0.6871031522750854,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5066,
      "step": 144
    },
    {
      "epoch": 0.7187112763320942,
      "grad_norm": 0.7052800059318542,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5413,
      "step": 145
    },
    {
      "epoch": 0.7236679058240396,
      "grad_norm": 0.6775354146957397,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.4682,
      "step": 146
    },
    {
      "epoch": 0.7286245353159851,
      "grad_norm": 0.6493685245513916,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.476,
      "step": 147
    },
    {
      "epoch": 0.7335811648079306,
      "grad_norm": 0.8085284233093262,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5415,
      "step": 148
    },
    {
      "epoch": 0.7385377942998761,
      "grad_norm": 0.7537986636161804,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4219,
      "step": 149
    },
    {
      "epoch": 0.7434944237918215,
      "grad_norm": 0.9588333964347839,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4383,
      "step": 150
    },
    {
      "epoch": 0.7434944237918215,
      "eval_loss": 0.6916682720184326,
      "eval_runtime": 23.9989,
      "eval_samples_per_second": 14.167,
      "eval_steps_per_second": 3.542,
      "step": 150
    },
    {
      "epoch": 0.748451053283767,
      "grad_norm": 0.37449488043785095,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9619,
      "step": 151
    },
    {
      "epoch": 0.7534076827757125,
      "grad_norm": 0.43213382363319397,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.9232,
      "step": 152
    },
    {
      "epoch": 0.758364312267658,
      "grad_norm": 0.45836374163627625,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.9903,
      "step": 153
    },
    {
      "epoch": 0.7633209417596035,
      "grad_norm": 0.5066783428192139,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.9275,
      "step": 154
    },
    {
      "epoch": 0.7682775712515489,
      "grad_norm": 0.48809510469436646,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.882,
      "step": 155
    },
    {
      "epoch": 0.7732342007434945,
      "grad_norm": 0.49593353271484375,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.885,
      "step": 156
    },
    {
      "epoch": 0.7781908302354399,
      "grad_norm": 0.49897220730781555,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8804,
      "step": 157
    },
    {
      "epoch": 0.7831474597273854,
      "grad_norm": 0.4909217655658722,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8431,
      "step": 158
    },
    {
      "epoch": 0.7881040892193308,
      "grad_norm": 0.4961768686771393,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8399,
      "step": 159
    },
    {
      "epoch": 0.7930607187112764,
      "grad_norm": 0.49854597449302673,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.8276,
      "step": 160
    },
    {
      "epoch": 0.7980173482032218,
      "grad_norm": 0.5040866732597351,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8531,
      "step": 161
    },
    {
      "epoch": 0.8029739776951673,
      "grad_norm": 0.4929218292236328,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8556,
      "step": 162
    },
    {
      "epoch": 0.8079306071871127,
      "grad_norm": 0.4669797718524933,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7864,
      "step": 163
    },
    {
      "epoch": 0.8128872366790583,
      "grad_norm": 0.497049480676651,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7606,
      "step": 164
    },
    {
      "epoch": 0.8178438661710037,
      "grad_norm": 0.48361045122146606,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.803,
      "step": 165
    },
    {
      "epoch": 0.8228004956629492,
      "grad_norm": 0.4763268828392029,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7564,
      "step": 166
    },
    {
      "epoch": 0.8277571251548946,
      "grad_norm": 0.4631034731864929,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6861,
      "step": 167
    },
    {
      "epoch": 0.8327137546468402,
      "grad_norm": 0.48590320348739624,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7368,
      "step": 168
    },
    {
      "epoch": 0.8376703841387856,
      "grad_norm": 0.519325852394104,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.767,
      "step": 169
    },
    {
      "epoch": 0.8426270136307311,
      "grad_norm": 0.4915248453617096,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7024,
      "step": 170
    },
    {
      "epoch": 0.8475836431226765,
      "grad_norm": 0.5298077464103699,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7153,
      "step": 171
    },
    {
      "epoch": 0.8525402726146221,
      "grad_norm": 0.4844955503940582,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6788,
      "step": 172
    },
    {
      "epoch": 0.8574969021065675,
      "grad_norm": 0.5077272653579712,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.675,
      "step": 173
    },
    {
      "epoch": 0.862453531598513,
      "grad_norm": 0.4895120859146118,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6149,
      "step": 174
    },
    {
      "epoch": 0.8674101610904585,
      "grad_norm": 0.5041832327842712,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.637,
      "step": 175
    },
    {
      "epoch": 0.872366790582404,
      "grad_norm": 0.5601372122764587,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6558,
      "step": 176
    },
    {
      "epoch": 0.8773234200743495,
      "grad_norm": 0.491409569978714,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6046,
      "step": 177
    },
    {
      "epoch": 0.8822800495662949,
      "grad_norm": 0.5299381017684937,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6699,
      "step": 178
    },
    {
      "epoch": 0.8872366790582404,
      "grad_norm": 0.5036606788635254,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5917,
      "step": 179
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 0.5434388518333435,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5672,
      "step": 180
    },
    {
      "epoch": 0.8971499380421314,
      "grad_norm": 0.5118383765220642,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5665,
      "step": 181
    },
    {
      "epoch": 0.9021065675340768,
      "grad_norm": 0.5556491017341614,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6259,
      "step": 182
    },
    {
      "epoch": 0.9070631970260223,
      "grad_norm": 0.5863553285598755,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6292,
      "step": 183
    },
    {
      "epoch": 0.9120198265179678,
      "grad_norm": 0.5912315249443054,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.633,
      "step": 184
    },
    {
      "epoch": 0.9169764560099133,
      "grad_norm": 0.5177478194236755,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5359,
      "step": 185
    },
    {
      "epoch": 0.9219330855018587,
      "grad_norm": 0.5891361236572266,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6327,
      "step": 186
    },
    {
      "epoch": 0.9268897149938042,
      "grad_norm": 0.5574577450752258,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6283,
      "step": 187
    },
    {
      "epoch": 0.9318463444857497,
      "grad_norm": 0.5842224955558777,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5784,
      "step": 188
    },
    {
      "epoch": 0.9368029739776952,
      "grad_norm": 0.5487937927246094,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.5638,
      "step": 189
    },
    {
      "epoch": 0.9417596034696406,
      "grad_norm": 0.5943487286567688,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5963,
      "step": 190
    },
    {
      "epoch": 0.9467162329615861,
      "grad_norm": 0.5466452240943909,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.4837,
      "step": 191
    },
    {
      "epoch": 0.9516728624535316,
      "grad_norm": 0.5706185698509216,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4582,
      "step": 192
    },
    {
      "epoch": 0.9566294919454771,
      "grad_norm": 0.6219942569732666,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5593,
      "step": 193
    },
    {
      "epoch": 0.9615861214374225,
      "grad_norm": 0.5846962928771973,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5216,
      "step": 194
    },
    {
      "epoch": 0.966542750929368,
      "grad_norm": 0.6944490075111389,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4804,
      "step": 195
    },
    {
      "epoch": 0.9714993804213135,
      "grad_norm": 0.601812481880188,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4776,
      "step": 196
    },
    {
      "epoch": 0.976456009913259,
      "grad_norm": 0.667896032333374,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.4606,
      "step": 197
    },
    {
      "epoch": 0.9814126394052045,
      "grad_norm": 0.7974829077720642,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4716,
      "step": 198
    },
    {
      "epoch": 0.9863692688971499,
      "grad_norm": 0.7776198387145996,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4357,
      "step": 199
    },
    {
      "epoch": 0.9913258983890955,
      "grad_norm": 0.8794264793395996,
      "learning_rate": 0.0,
      "loss": 0.4425,
      "step": 200
    },
    {
      "epoch": 0.9913258983890955,
      "eval_loss": 0.6764784455299377,
      "eval_runtime": 24.0047,
      "eval_samples_per_second": 14.164,
      "eval_steps_per_second": 3.541,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.660991548522496e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}