{
  "best_metric": 0.2155240923166275,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.024223828172312164,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016149218781541443,
      "grad_norm": 64.24162292480469,
      "learning_rate": 1e-05,
      "loss": 6.8126,
      "step": 1
    },
    {
      "epoch": 0.00016149218781541443,
      "eval_loss": 2.066232681274414,
      "eval_runtime": 768.8275,
      "eval_samples_per_second": 13.565,
      "eval_steps_per_second": 3.392,
      "step": 1
    },
    {
      "epoch": 0.00032298437563082886,
      "grad_norm": 56.833106994628906,
      "learning_rate": 2e-05,
      "loss": 5.9843,
      "step": 2
    },
    {
      "epoch": 0.0004844765634462433,
      "grad_norm": 48.323463439941406,
      "learning_rate": 3e-05,
      "loss": 5.3251,
      "step": 3
    },
    {
      "epoch": 0.0006459687512616577,
      "grad_norm": 49.74161148071289,
      "learning_rate": 4e-05,
      "loss": 4.4457,
      "step": 4
    },
    {
      "epoch": 0.0008074609390770722,
      "grad_norm": 63.7999382019043,
      "learning_rate": 5e-05,
      "loss": 4.1268,
      "step": 5
    },
    {
      "epoch": 0.0009689531268924866,
      "grad_norm": 27.215686798095703,
      "learning_rate": 6e-05,
      "loss": 3.2284,
      "step": 6
    },
    {
      "epoch": 0.001130445314707901,
      "grad_norm": 53.638919830322266,
      "learning_rate": 7e-05,
      "loss": 2.5599,
      "step": 7
    },
    {
      "epoch": 0.0012919375025233154,
      "grad_norm": 19.307762145996094,
      "learning_rate": 8e-05,
      "loss": 2.2425,
      "step": 8
    },
    {
      "epoch": 0.0014534296903387298,
      "grad_norm": 17.659503936767578,
      "learning_rate": 9e-05,
      "loss": 2.1483,
      "step": 9
    },
    {
      "epoch": 0.0016149218781541443,
      "grad_norm": 21.160411834716797,
      "learning_rate": 0.0001,
      "loss": 1.622,
      "step": 10
    },
    {
      "epoch": 0.0017764140659695586,
      "grad_norm": 86.40902709960938,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.0168,
      "step": 11
    },
    {
      "epoch": 0.0019379062537849732,
      "grad_norm": 24.150169372558594,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.666,
      "step": 12
    },
    {
      "epoch": 0.0020993984416003875,
      "grad_norm": 15.378752708435059,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.5135,
      "step": 13
    },
    {
      "epoch": 0.002260890629415802,
      "grad_norm": 22.235591888427734,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.2294,
      "step": 14
    },
    {
      "epoch": 0.0024223828172312166,
      "grad_norm": 12.330756187438965,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4264,
      "step": 15
    },
    {
      "epoch": 0.002583875005046631,
      "grad_norm": 13.079683303833008,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.6981,
      "step": 16
    },
    {
      "epoch": 0.002745367192862045,
      "grad_norm": 7.713149070739746,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9774,
      "step": 17
    },
    {
      "epoch": 0.0029068593806774595,
      "grad_norm": 7.287616729736328,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9298,
      "step": 18
    },
    {
      "epoch": 0.0030683515684928743,
      "grad_norm": 34.157711029052734,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3756,
      "step": 19
    },
    {
      "epoch": 0.0032298437563082886,
      "grad_norm": 11.063179016113281,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1234,
      "step": 20
    },
    {
      "epoch": 0.003391335944123703,
      "grad_norm": 15.762474060058594,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.2058,
      "step": 21
    },
    {
      "epoch": 0.0035528281319391172,
      "grad_norm": 8.26089859008789,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9081,
      "step": 22
    },
    {
      "epoch": 0.003714320319754532,
      "grad_norm": 10.437385559082031,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.258,
      "step": 23
    },
    {
      "epoch": 0.0038758125075699463,
      "grad_norm": 8.177536010742188,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8721,
      "step": 24
    },
    {
      "epoch": 0.004037304695385361,
      "grad_norm": 17.914628982543945,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.4557,
      "step": 25
    },
    {
      "epoch": 0.004198796883200775,
      "grad_norm": 7.463947772979736,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.0969,
      "step": 26
    },
    {
      "epoch": 0.004360289071016189,
      "grad_norm": 5.383772850036621,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6915,
      "step": 27
    },
    {
      "epoch": 0.004521781258831604,
      "grad_norm": 7.699918746948242,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2951,
      "step": 28
    },
    {
      "epoch": 0.004683273446647019,
      "grad_norm": 8.353910446166992,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9308,
      "step": 29
    },
    {
      "epoch": 0.004844765634462433,
      "grad_norm": 6.948275566101074,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9263,
      "step": 30
    },
    {
      "epoch": 0.0050062578222778474,
      "grad_norm": 12.072859764099121,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3808,
      "step": 31
    },
    {
      "epoch": 0.005167750010093262,
      "grad_norm": 7.524881839752197,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0131,
      "step": 32
    },
    {
      "epoch": 0.005329242197908676,
      "grad_norm": 14.655591011047363,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.4809,
      "step": 33
    },
    {
      "epoch": 0.00549073438572409,
      "grad_norm": 11.227638244628906,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4832,
      "step": 34
    },
    {
      "epoch": 0.005652226573539505,
      "grad_norm": 7.202654838562012,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0635,
      "step": 35
    },
    {
      "epoch": 0.005813718761354919,
      "grad_norm": 5.849029064178467,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9063,
      "step": 36
    },
    {
      "epoch": 0.005975210949170334,
      "grad_norm": 6.742249965667725,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1368,
      "step": 37
    },
    {
      "epoch": 0.0061367031369857486,
      "grad_norm": 9.29891586303711,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2069,
      "step": 38
    },
    {
      "epoch": 0.006298195324801163,
      "grad_norm": 6.022105693817139,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6348,
      "step": 39
    },
    {
      "epoch": 0.006459687512616577,
      "grad_norm": 7.115547180175781,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1143,
      "step": 40
    },
    {
      "epoch": 0.0066211797004319915,
      "grad_norm": 7.513053894042969,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.2402,
      "step": 41
    },
    {
      "epoch": 0.006782671888247406,
      "grad_norm": 6.634003639221191,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.791,
      "step": 42
    },
    {
      "epoch": 0.00694416407606282,
      "grad_norm": 7.986715793609619,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.1034,
      "step": 43
    },
    {
      "epoch": 0.0071056562638782345,
      "grad_norm": 6.973867893218994,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0277,
      "step": 44
    },
    {
      "epoch": 0.00726714845169365,
      "grad_norm": 7.329861640930176,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.1654,
      "step": 45
    },
    {
      "epoch": 0.007428640639509064,
      "grad_norm": 6.630235195159912,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8559,
      "step": 46
    },
    {
      "epoch": 0.007590132827324478,
      "grad_norm": 7.3892621994018555,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9238,
      "step": 47
    },
    {
      "epoch": 0.007751625015139893,
      "grad_norm": 7.5705790519714355,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1495,
      "step": 48
    },
    {
      "epoch": 0.007913117202955308,
      "grad_norm": 7.095438480377197,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.2315,
      "step": 49
    },
    {
      "epoch": 0.008074609390770721,
      "grad_norm": 9.232726097106934,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.279,
      "step": 50
    },
    {
      "epoch": 0.008074609390770721,
      "eval_loss": 0.2697645127773285,
      "eval_runtime": 773.8817,
      "eval_samples_per_second": 13.476,
      "eval_steps_per_second": 3.37,
      "step": 50
    },
    {
      "epoch": 0.008236101578586136,
      "grad_norm": 20.15778160095215,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.4656,
      "step": 51
    },
    {
      "epoch": 0.00839759376640155,
      "grad_norm": 10.792618751525879,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0059,
      "step": 52
    },
    {
      "epoch": 0.008559085954216965,
      "grad_norm": 6.110121250152588,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.987,
      "step": 53
    },
    {
      "epoch": 0.008720578142032379,
      "grad_norm": 4.688563346862793,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8083,
      "step": 54
    },
    {
      "epoch": 0.008882070329847794,
      "grad_norm": 5.73980188369751,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2474,
      "step": 55
    },
    {
      "epoch": 0.009043562517663207,
      "grad_norm": 3.409475088119507,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5241,
      "step": 56
    },
    {
      "epoch": 0.009205054705478622,
      "grad_norm": 5.96190071105957,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8567,
      "step": 57
    },
    {
      "epoch": 0.009366546893294038,
      "grad_norm": 5.128782749176025,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6851,
      "step": 58
    },
    {
      "epoch": 0.009528039081109451,
      "grad_norm": 4.455477237701416,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8239,
      "step": 59
    },
    {
      "epoch": 0.009689531268924866,
      "grad_norm": 5.79195499420166,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.0797,
      "step": 60
    },
    {
      "epoch": 0.00985102345674028,
      "grad_norm": 6.7193498611450195,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7795,
      "step": 61
    },
    {
      "epoch": 0.010012515644555695,
      "grad_norm": 4.534706115722656,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8244,
      "step": 62
    },
    {
      "epoch": 0.010174007832371108,
      "grad_norm": 5.564373970031738,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6512,
      "step": 63
    },
    {
      "epoch": 0.010335500020186524,
      "grad_norm": 7.308129787445068,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8395,
      "step": 64
    },
    {
      "epoch": 0.010496992208001939,
      "grad_norm": 7.847126007080078,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0518,
      "step": 65
    },
    {
      "epoch": 0.010658484395817352,
      "grad_norm": 6.746877670288086,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.1552,
      "step": 66
    },
    {
      "epoch": 0.010819976583632767,
      "grad_norm": 5.704141139984131,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1032,
      "step": 67
    },
    {
      "epoch": 0.01098146877144818,
      "grad_norm": 4.532803058624268,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6292,
      "step": 68
    },
    {
      "epoch": 0.011142960959263596,
      "grad_norm": 3.092655897140503,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5854,
      "step": 69
    },
    {
      "epoch": 0.01130445314707901,
      "grad_norm": 12.300941467285156,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.915,
      "step": 70
    },
    {
      "epoch": 0.011465945334894425,
      "grad_norm": 5.741693019866943,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.9987,
      "step": 71
    },
    {
      "epoch": 0.011627437522709838,
      "grad_norm": 5.947897911071777,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9166,
      "step": 72
    },
    {
      "epoch": 0.011788929710525253,
      "grad_norm": 9.199006080627441,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.4229,
      "step": 73
    },
    {
      "epoch": 0.011950421898340668,
      "grad_norm": 4.8748297691345215,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8394,
      "step": 74
    },
    {
      "epoch": 0.012111914086156082,
      "grad_norm": 4.803055286407471,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7034,
      "step": 75
    },
    {
      "epoch": 0.012273406273971497,
      "grad_norm": 4.951623439788818,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9423,
      "step": 76
    },
    {
      "epoch": 0.01243489846178691,
      "grad_norm": 5.697551727294922,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.3467,
      "step": 77
    },
    {
      "epoch": 0.012596390649602326,
      "grad_norm": 6.667501926422119,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0246,
      "step": 78
    },
    {
      "epoch": 0.01275788283741774,
      "grad_norm": 5.783114910125732,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.844,
      "step": 79
    },
    {
      "epoch": 0.012919375025233154,
      "grad_norm": 4.069927215576172,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8796,
      "step": 80
    },
    {
      "epoch": 0.01308086721304857,
      "grad_norm": 6.044260501861572,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8675,
      "step": 81
    },
    {
      "epoch": 0.013242359400863983,
      "grad_norm": 9.066145896911621,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.0933,
      "step": 82
    },
    {
      "epoch": 0.013403851588679398,
      "grad_norm": 6.081099033355713,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5966,
      "step": 83
    },
    {
      "epoch": 0.013565343776494812,
      "grad_norm": 4.080660820007324,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8206,
      "step": 84
    },
    {
      "epoch": 0.013726835964310227,
      "grad_norm": 10.46330451965332,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.339,
      "step": 85
    },
    {
      "epoch": 0.01388832815212564,
      "grad_norm": 4.070284366607666,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9671,
      "step": 86
    },
    {
      "epoch": 0.014049820339941056,
      "grad_norm": 4.478235244750977,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8915,
      "step": 87
    },
    {
      "epoch": 0.014211312527756469,
      "grad_norm": 5.405301570892334,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.9657,
      "step": 88
    },
    {
      "epoch": 0.014372804715571884,
      "grad_norm": 5.201086044311523,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8831,
      "step": 89
    },
    {
      "epoch": 0.0145342969033873,
      "grad_norm": 5.0022196769714355,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9536,
      "step": 90
    },
    {
      "epoch": 0.014695789091202713,
      "grad_norm": 3.785090208053589,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.9481,
      "step": 91
    },
    {
      "epoch": 0.014857281279018128,
      "grad_norm": 3.209487199783325,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.623,
      "step": 92
    },
    {
      "epoch": 0.015018773466833541,
      "grad_norm": 3.7691524028778076,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6287,
      "step": 93
    },
    {
      "epoch": 0.015180265654648957,
      "grad_norm": 5.767764091491699,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0116,
      "step": 94
    },
    {
      "epoch": 0.01534175784246437,
      "grad_norm": 5.574740409851074,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.1322,
      "step": 95
    },
    {
      "epoch": 0.015503250030279785,
      "grad_norm": 6.865067005157471,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1674,
      "step": 96
    },
    {
      "epoch": 0.0156647422180952,
      "grad_norm": 7.697023391723633,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.2146,
      "step": 97
    },
    {
      "epoch": 0.015826234405910616,
      "grad_norm": 6.176741123199463,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7344,
      "step": 98
    },
    {
      "epoch": 0.015987726593726027,
      "grad_norm": 7.797219276428223,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9874,
      "step": 99
    },
    {
      "epoch": 0.016149218781541443,
      "grad_norm": 35.21796798706055,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.3663,
      "step": 100
    },
    {
      "epoch": 0.016149218781541443,
      "eval_loss": 0.23936980962753296,
      "eval_runtime": 773.8809,
      "eval_samples_per_second": 13.476,
      "eval_steps_per_second": 3.37,
      "step": 100
    },
    {
      "epoch": 0.016310710969356858,
      "grad_norm": 5.582284927368164,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6509,
      "step": 101
    },
    {
      "epoch": 0.016472203157172273,
      "grad_norm": 5.59496545791626,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6946,
      "step": 102
    },
    {
      "epoch": 0.016633695344987685,
      "grad_norm": 3.994982957839966,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6593,
      "step": 103
    },
    {
      "epoch": 0.0167951875328031,
      "grad_norm": 4.673209190368652,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7178,
      "step": 104
    },
    {
      "epoch": 0.016956679720618515,
      "grad_norm": 5.2176432609558105,
      "learning_rate": 5e-05,
      "loss": 0.8817,
      "step": 105
    },
    {
      "epoch": 0.01711817190843393,
      "grad_norm": 6.435986518859863,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.0187,
      "step": 106
    },
    {
      "epoch": 0.017279664096249345,
      "grad_norm": 5.802428245544434,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.785,
      "step": 107
    },
    {
      "epoch": 0.017441156284064757,
      "grad_norm": 3.944193124771118,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8857,
      "step": 108
    },
    {
      "epoch": 0.017602648471880172,
      "grad_norm": 4.268792152404785,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.965,
      "step": 109
    },
    {
      "epoch": 0.017764140659695588,
      "grad_norm": 4.114878177642822,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8447,
      "step": 110
    },
    {
      "epoch": 0.017925632847511003,
      "grad_norm": 6.73455810546875,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.2171,
      "step": 111
    },
    {
      "epoch": 0.018087125035326414,
      "grad_norm": 3.7818212509155273,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7176,
      "step": 112
    },
    {
      "epoch": 0.01824861722314183,
      "grad_norm": 5.155925273895264,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.4072,
      "step": 113
    },
    {
      "epoch": 0.018410109410957245,
      "grad_norm": 3.8666725158691406,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.637,
      "step": 114
    },
    {
      "epoch": 0.01857160159877266,
      "grad_norm": 4.598525047302246,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8549,
      "step": 115
    },
    {
      "epoch": 0.018733093786588075,
      "grad_norm": 4.935587406158447,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8454,
      "step": 116
    },
    {
      "epoch": 0.018894585974403487,
      "grad_norm": 3.9440360069274902,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7603,
      "step": 117
    },
    {
      "epoch": 0.019056078162218902,
      "grad_norm": 3.4473254680633545,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7514,
      "step": 118
    },
    {
      "epoch": 0.019217570350034317,
      "grad_norm": 3.5236740112304688,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6893,
      "step": 119
    },
    {
      "epoch": 0.019379062537849732,
      "grad_norm": 5.646050930023193,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1492,
      "step": 120
    },
    {
      "epoch": 0.019540554725665148,
      "grad_norm": 14.069942474365234,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6437,
      "step": 121
    },
    {
      "epoch": 0.01970204691348056,
      "grad_norm": 5.5176310539245605,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.1893,
      "step": 122
    },
    {
      "epoch": 0.019863539101295975,
      "grad_norm": 3.8687825202941895,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7224,
      "step": 123
    },
    {
      "epoch": 0.02002503128911139,
      "grad_norm": 4.453583240509033,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8893,
      "step": 124
    },
    {
      "epoch": 0.020186523476926805,
      "grad_norm": 4.346451759338379,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6472,
      "step": 125
    },
    {
      "epoch": 0.020348015664742217,
      "grad_norm": 3.7838120460510254,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7286,
      "step": 126
    },
    {
      "epoch": 0.020509507852557632,
      "grad_norm": 3.9823427200317383,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8001,
      "step": 127
    },
    {
      "epoch": 0.020671000040373047,
      "grad_norm": 3.862109661102295,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.73,
      "step": 128
    },
    {
      "epoch": 0.020832492228188462,
      "grad_norm": 3.2715883255004883,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.682,
      "step": 129
    },
    {
      "epoch": 0.020993984416003877,
      "grad_norm": 4.938713550567627,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8701,
      "step": 130
    },
    {
      "epoch": 0.02115547660381929,
      "grad_norm": 4.840963840484619,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2415,
      "step": 131
    },
    {
      "epoch": 0.021316968791634704,
      "grad_norm": 5.589321136474609,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.0268,
      "step": 132
    },
    {
      "epoch": 0.02147846097945012,
      "grad_norm": 4.659307479858398,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.9929,
      "step": 133
    },
    {
      "epoch": 0.021639953167265535,
      "grad_norm": 4.5604071617126465,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.0875,
      "step": 134
    },
    {
      "epoch": 0.021801445355080946,
      "grad_norm": 2.9720771312713623,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6396,
      "step": 135
    },
    {
      "epoch": 0.02196293754289636,
      "grad_norm": 2.8303656578063965,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.596,
      "step": 136
    },
    {
      "epoch": 0.022124429730711777,
      "grad_norm": 5.762628555297852,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1149,
      "step": 137
    },
    {
      "epoch": 0.022285921918527192,
      "grad_norm": 3.7539639472961426,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8207,
      "step": 138
    },
    {
      "epoch": 0.022447414106342607,
      "grad_norm": 3.3205928802490234,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6337,
      "step": 139
    },
    {
      "epoch": 0.02260890629415802,
      "grad_norm": 4.56250524520874,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6938,
      "step": 140
    },
    {
      "epoch": 0.022770398481973434,
      "grad_norm": 3.855919599533081,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6727,
      "step": 141
    },
    {
      "epoch": 0.02293189066978885,
      "grad_norm": 3.845710039138794,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5387,
      "step": 142
    },
    {
      "epoch": 0.023093382857604264,
      "grad_norm": 3.3450379371643066,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.698,
      "step": 143
    },
    {
      "epoch": 0.023254875045419676,
      "grad_norm": 3.4443554878234863,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6105,
      "step": 144
    },
    {
      "epoch": 0.02341636723323509,
      "grad_norm": 5.2029290199279785,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.9275,
      "step": 145
    },
    {
      "epoch": 0.023577859421050507,
      "grad_norm": 4.947165012359619,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.899,
      "step": 146
    },
    {
      "epoch": 0.023739351608865922,
      "grad_norm": 6.969897747039795,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9048,
      "step": 147
    },
    {
      "epoch": 0.023900843796681337,
      "grad_norm": 4.117700576782227,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7883,
      "step": 148
    },
    {
      "epoch": 0.02406233598449675,
      "grad_norm": 7.0803422927856445,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0842,
      "step": 149
    },
    {
      "epoch": 0.024223828172312164,
      "grad_norm": 14.362741470336914,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.9862,
      "step": 150
    },
    {
      "epoch": 0.024223828172312164,
      "eval_loss": 0.2155240923166275,
      "eval_runtime": 773.9774,
      "eval_samples_per_second": 13.475,
      "eval_steps_per_second": 3.37,
      "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": 2.146499429400576e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}