{
  "best_metric": 0.8842717409133911,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.73972602739726,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0136986301369863,
      "grad_norm": 2.2723445892333984,
      "learning_rate": 1e-05,
      "loss": 2.6772,
      "step": 1
    },
    {
      "epoch": 0.0136986301369863,
      "eval_loss": 2.6535723209381104,
      "eval_runtime": 17.3496,
      "eval_samples_per_second": 7.089,
      "eval_steps_per_second": 1.787,
      "step": 1
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 2.24312686920166,
      "learning_rate": 2e-05,
      "loss": 2.5427,
      "step": 2
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 2.4361393451690674,
      "learning_rate": 3e-05,
      "loss": 2.6229,
      "step": 3
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 1.9719237089157104,
      "learning_rate": 4e-05,
      "loss": 2.4264,
      "step": 4
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 1.68191659450531,
      "learning_rate": 5e-05,
      "loss": 2.3573,
      "step": 5
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 1.1799057722091675,
      "learning_rate": 6e-05,
      "loss": 2.2246,
      "step": 6
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": 0.7114689946174622,
      "learning_rate": 7e-05,
      "loss": 2.0673,
      "step": 7
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.5088303089141846,
      "learning_rate": 8e-05,
      "loss": 2.2382,
      "step": 8
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": 0.6488537192344666,
      "learning_rate": 9e-05,
      "loss": 2.0742,
      "step": 9
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.6316589117050171,
      "learning_rate": 0.0001,
      "loss": 1.9799,
      "step": 10
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": 0.7037212252616882,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.9223,
      "step": 11
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.6775087714195251,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.9981,
      "step": 12
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": 0.6623851656913757,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.9764,
      "step": 13
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.522150456905365,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6859,
      "step": 14
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.5843157768249512,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8005,
      "step": 15
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.6646741628646851,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.9406,
      "step": 16
    },
    {
      "epoch": 0.2328767123287671,
      "grad_norm": 0.6988809108734131,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.8031,
      "step": 17
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.8424138426780701,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7316,
      "step": 18
    },
    {
      "epoch": 0.2602739726027397,
      "grad_norm": 0.5436477065086365,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6322,
      "step": 19
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.596440315246582,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5715,
      "step": 20
    },
    {
      "epoch": 0.2876712328767123,
      "grad_norm": 0.5418570637702942,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4598,
      "step": 21
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.46350181102752686,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.5698,
      "step": 22
    },
    {
      "epoch": 0.3150684931506849,
      "grad_norm": 0.490932434797287,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4736,
      "step": 23
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.46368205547332764,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5218,
      "step": 24
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.4996948838233948,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.4607,
      "step": 25
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.5390800833702087,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2634,
      "step": 26
    },
    {
      "epoch": 0.3698630136986301,
      "grad_norm": 0.4711100459098816,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.444,
      "step": 27
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.46546122431755066,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4255,
      "step": 28
    },
    {
      "epoch": 0.3972602739726027,
      "grad_norm": 0.5199427008628845,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3317,
      "step": 29
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.540518045425415,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.2205,
      "step": 30
    },
    {
      "epoch": 0.4246575342465753,
      "grad_norm": 0.5566041469573975,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3695,
      "step": 31
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.5139285922050476,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2974,
      "step": 32
    },
    {
      "epoch": 0.4520547945205479,
      "grad_norm": 0.5224803686141968,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2894,
      "step": 33
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": 0.6262706518173218,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2834,
      "step": 34
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.601302444934845,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3762,
      "step": 35
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.7919737696647644,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3327,
      "step": 36
    },
    {
      "epoch": 0.5068493150684932,
      "grad_norm": 0.48969706892967224,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3136,
      "step": 37
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": 0.4718853235244751,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.257,
      "step": 38
    },
    {
      "epoch": 0.5342465753424658,
      "grad_norm": 0.5200712084770203,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.2057,
      "step": 39
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.4529687762260437,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1864,
      "step": 40
    },
    {
      "epoch": 0.5616438356164384,
      "grad_norm": 0.5341131091117859,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.189,
      "step": 41
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": 0.41976484656333923,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2496,
      "step": 42
    },
    {
      "epoch": 0.589041095890411,
      "grad_norm": 0.4597126245498657,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.2864,
      "step": 43
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.4417206346988678,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1974,
      "step": 44
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.37517061829566956,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0505,
      "step": 45
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": 0.4843452274799347,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.0901,
      "step": 46
    },
    {
      "epoch": 0.6438356164383562,
      "grad_norm": 0.4694693982601166,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2479,
      "step": 47
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.4550216794013977,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1789,
      "step": 48
    },
    {
      "epoch": 0.6712328767123288,
      "grad_norm": 0.4894697964191437,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1591,
      "step": 49
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.46560347080230713,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0118,
      "step": 50
    },
    {
      "epoch": 0.684931506849315,
      "eval_loss": 1.1601545810699463,
      "eval_runtime": 17.7628,
      "eval_samples_per_second": 6.925,
      "eval_steps_per_second": 1.745,
      "step": 50
    },
    {
      "epoch": 0.6986301369863014,
      "grad_norm": 0.5067690014839172,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3046,
      "step": 51
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.5919586420059204,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.437,
      "step": 52
    },
    {
      "epoch": 0.726027397260274,
      "grad_norm": 0.55036461353302,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1412,
      "step": 53
    },
    {
      "epoch": 0.7397260273972602,
      "grad_norm": 0.7060859203338623,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1793,
      "step": 54
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.4906173050403595,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1166,
      "step": 55
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.4804984927177429,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1413,
      "step": 56
    },
    {
      "epoch": 0.7808219178082192,
      "grad_norm": 0.4445788264274597,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0361,
      "step": 57
    },
    {
      "epoch": 0.7945205479452054,
      "grad_norm": 0.4586659371852875,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1233,
      "step": 58
    },
    {
      "epoch": 0.8082191780821918,
      "grad_norm": 0.46942317485809326,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1797,
      "step": 59
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.4590390622615814,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.18,
      "step": 60
    },
    {
      "epoch": 0.8356164383561644,
      "grad_norm": 0.43579575419425964,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0327,
      "step": 61
    },
    {
      "epoch": 0.8493150684931506,
      "grad_norm": 0.4077199101448059,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.061,
      "step": 62
    },
    {
      "epoch": 0.863013698630137,
      "grad_norm": 0.4293108284473419,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1365,
      "step": 63
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.4422175884246826,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.1829,
      "step": 64
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.4037194550037384,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0801,
      "step": 65
    },
    {
      "epoch": 0.9041095890410958,
      "grad_norm": 0.4369223713874817,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0445,
      "step": 66
    },
    {
      "epoch": 0.9178082191780822,
      "grad_norm": 0.4974297881126404,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0955,
      "step": 67
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 0.41493669152259827,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9814,
      "step": 68
    },
    {
      "epoch": 0.9452054794520548,
      "grad_norm": 0.4775225520133972,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.0769,
      "step": 69
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.5432804822921753,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.165,
      "step": 70
    },
    {
      "epoch": 0.9726027397260274,
      "grad_norm": 0.6015564799308777,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0298,
      "step": 71
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.7300246357917786,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0418,
      "step": 72
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4879606366157532,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9665,
      "step": 73
    },
    {
      "epoch": 1.0136986301369864,
      "grad_norm": 0.4434296488761902,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.0228,
      "step": 74
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 0.5075652003288269,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0205,
      "step": 75
    },
    {
      "epoch": 1.0410958904109588,
      "grad_norm": 0.40586984157562256,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0692,
      "step": 76
    },
    {
      "epoch": 1.0547945205479452,
      "grad_norm": 0.43760401010513306,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0405,
      "step": 77
    },
    {
      "epoch": 1.0684931506849316,
      "grad_norm": 0.4631575345993042,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0184,
      "step": 78
    },
    {
      "epoch": 1.0821917808219177,
      "grad_norm": 0.41342413425445557,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.865,
      "step": 79
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.449799507856369,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0308,
      "step": 80
    },
    {
      "epoch": 1.1095890410958904,
      "grad_norm": 0.43080204725265503,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9537,
      "step": 81
    },
    {
      "epoch": 1.1232876712328768,
      "grad_norm": 0.44926077127456665,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.0864,
      "step": 82
    },
    {
      "epoch": 1.1369863013698631,
      "grad_norm": 0.4401441514492035,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8644,
      "step": 83
    },
    {
      "epoch": 1.1506849315068493,
      "grad_norm": 0.4736673831939697,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9326,
      "step": 84
    },
    {
      "epoch": 1.1643835616438356,
      "grad_norm": 0.4427533447742462,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9934,
      "step": 85
    },
    {
      "epoch": 1.178082191780822,
      "grad_norm": 0.4494166970252991,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8691,
      "step": 86
    },
    {
      "epoch": 1.191780821917808,
      "grad_norm": 0.5305172204971313,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8661,
      "step": 87
    },
    {
      "epoch": 1.2054794520547945,
      "grad_norm": 0.433210164308548,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8509,
      "step": 88
    },
    {
      "epoch": 1.2191780821917808,
      "grad_norm": 0.46337318420410156,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0055,
      "step": 89
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 0.5811981558799744,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8975,
      "step": 90
    },
    {
      "epoch": 1.2465753424657535,
      "grad_norm": 0.6795594692230225,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8158,
      "step": 91
    },
    {
      "epoch": 1.2602739726027397,
      "grad_norm": 0.5404173135757446,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9054,
      "step": 92
    },
    {
      "epoch": 1.273972602739726,
      "grad_norm": 0.5495357513427734,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9883,
      "step": 93
    },
    {
      "epoch": 1.2876712328767124,
      "grad_norm": 0.587936282157898,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8952,
      "step": 94
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 0.4255267083644867,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8953,
      "step": 95
    },
    {
      "epoch": 1.3150684931506849,
      "grad_norm": 0.46071940660476685,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9704,
      "step": 96
    },
    {
      "epoch": 1.3287671232876712,
      "grad_norm": 0.49504444003105164,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8494,
      "step": 97
    },
    {
      "epoch": 1.3424657534246576,
      "grad_norm": 0.4440882205963135,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.856,
      "step": 98
    },
    {
      "epoch": 1.356164383561644,
      "grad_norm": 0.45081135630607605,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9017,
      "step": 99
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.4218074381351471,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9004,
      "step": 100
    },
    {
      "epoch": 1.36986301369863,
      "eval_loss": 0.9652940034866333,
      "eval_runtime": 17.7792,
      "eval_samples_per_second": 6.918,
      "eval_steps_per_second": 1.744,
      "step": 100
    },
    {
      "epoch": 1.3835616438356164,
      "grad_norm": 0.45532944798469543,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9198,
      "step": 101
    },
    {
      "epoch": 1.3972602739726028,
      "grad_norm": 0.4588129222393036,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.815,
      "step": 102
    },
    {
      "epoch": 1.410958904109589,
      "grad_norm": 0.4899400770664215,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9458,
      "step": 103
    },
    {
      "epoch": 1.4246575342465753,
      "grad_norm": 0.4633255898952484,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7873,
      "step": 104
    },
    {
      "epoch": 1.4383561643835616,
      "grad_norm": 0.5123822093009949,
      "learning_rate": 5e-05,
      "loss": 0.7735,
      "step": 105
    },
    {
      "epoch": 1.452054794520548,
      "grad_norm": 0.6840353012084961,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9996,
      "step": 106
    },
    {
      "epoch": 1.4657534246575343,
      "grad_norm": 0.5869365930557251,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9091,
      "step": 107
    },
    {
      "epoch": 1.4794520547945205,
      "grad_norm": 0.6082785129547119,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9044,
      "step": 108
    },
    {
      "epoch": 1.4931506849315068,
      "grad_norm": 0.8063579201698303,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8016,
      "step": 109
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 0.4705323576927185,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.0043,
      "step": 110
    },
    {
      "epoch": 1.5205479452054793,
      "grad_norm": 0.4473496675491333,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9378,
      "step": 111
    },
    {
      "epoch": 1.5342465753424657,
      "grad_norm": 0.5801135301589966,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8676,
      "step": 112
    },
    {
      "epoch": 1.547945205479452,
      "grad_norm": 0.49743950366973877,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9964,
      "step": 113
    },
    {
      "epoch": 1.5616438356164384,
      "grad_norm": 0.5174344182014465,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9564,
      "step": 114
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 0.48624131083488464,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.002,
      "step": 115
    },
    {
      "epoch": 1.589041095890411,
      "grad_norm": 0.43607619404792786,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8362,
      "step": 116
    },
    {
      "epoch": 1.6027397260273972,
      "grad_norm": 0.44581037759780884,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.909,
      "step": 117
    },
    {
      "epoch": 1.6164383561643836,
      "grad_norm": 0.42221271991729736,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9262,
      "step": 118
    },
    {
      "epoch": 1.6301369863013697,
      "grad_norm": 0.4592105746269226,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.909,
      "step": 119
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.41772693395614624,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8772,
      "step": 120
    },
    {
      "epoch": 1.6575342465753424,
      "grad_norm": 0.4366929233074188,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8764,
      "step": 121
    },
    {
      "epoch": 1.6712328767123288,
      "grad_norm": 0.494377076625824,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.94,
      "step": 122
    },
    {
      "epoch": 1.6849315068493151,
      "grad_norm": 0.4672698676586151,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7466,
      "step": 123
    },
    {
      "epoch": 1.6986301369863015,
      "grad_norm": 0.540347158908844,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9096,
      "step": 124
    },
    {
      "epoch": 1.7123287671232876,
      "grad_norm": 0.6010432243347168,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.916,
      "step": 125
    },
    {
      "epoch": 1.726027397260274,
      "grad_norm": 0.5619703531265259,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7565,
      "step": 126
    },
    {
      "epoch": 1.7397260273972601,
      "grad_norm": 0.7532036304473877,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7739,
      "step": 127
    },
    {
      "epoch": 1.7534246575342465,
      "grad_norm": 0.5412250757217407,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.9245,
      "step": 128
    },
    {
      "epoch": 1.7671232876712328,
      "grad_norm": 0.5161488056182861,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8708,
      "step": 129
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.49769195914268494,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.904,
      "step": 130
    },
    {
      "epoch": 1.7945205479452055,
      "grad_norm": 0.46421119570732117,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8364,
      "step": 131
    },
    {
      "epoch": 1.808219178082192,
      "grad_norm": 0.5016066431999207,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.9871,
      "step": 132
    },
    {
      "epoch": 1.821917808219178,
      "grad_norm": 0.4628809094429016,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8206,
      "step": 133
    },
    {
      "epoch": 1.8356164383561644,
      "grad_norm": 0.4603871703147888,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7987,
      "step": 134
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 0.43276363611221313,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8135,
      "step": 135
    },
    {
      "epoch": 1.8630136986301369,
      "grad_norm": 0.484453022480011,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8723,
      "step": 136
    },
    {
      "epoch": 1.8767123287671232,
      "grad_norm": 0.43174099922180176,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8323,
      "step": 137
    },
    {
      "epoch": 1.8904109589041096,
      "grad_norm": 0.4604308009147644,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8581,
      "step": 138
    },
    {
      "epoch": 1.904109589041096,
      "grad_norm": 0.43377089500427246,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8455,
      "step": 139
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.4600687623023987,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8795,
      "step": 140
    },
    {
      "epoch": 1.9315068493150684,
      "grad_norm": 0.46039503812789917,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8432,
      "step": 141
    },
    {
      "epoch": 1.9452054794520548,
      "grad_norm": 0.45803946256637573,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8856,
      "step": 142
    },
    {
      "epoch": 1.958904109589041,
      "grad_norm": 0.6742038726806641,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9454,
      "step": 143
    },
    {
      "epoch": 1.9726027397260273,
      "grad_norm": 0.5912793278694153,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8096,
      "step": 144
    },
    {
      "epoch": 1.9863013698630136,
      "grad_norm": 0.7360471487045288,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7939,
      "step": 145
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.516366720199585,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.813,
      "step": 146
    },
    {
      "epoch": 2.0136986301369864,
      "grad_norm": 0.4400363564491272,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7998,
      "step": 147
    },
    {
      "epoch": 2.0273972602739727,
      "grad_norm": 0.46346285939216614,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8498,
      "step": 148
    },
    {
      "epoch": 2.041095890410959,
      "grad_norm": 0.46001294255256653,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8128,
      "step": 149
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 0.4576590359210968,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7916,
      "step": 150
    },
    {
      "epoch": 2.0547945205479454,
      "eval_loss": 0.895984947681427,
      "eval_runtime": 17.7598,
      "eval_samples_per_second": 6.926,
      "eval_steps_per_second": 1.746,
      "step": 150
    },
    {
      "epoch": 2.0684931506849313,
      "grad_norm": 0.47957706451416016,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9386,
      "step": 151
    },
    {
      "epoch": 2.0821917808219177,
      "grad_norm": 0.4133041799068451,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8109,
      "step": 152
    },
    {
      "epoch": 2.095890410958904,
      "grad_norm": 0.48111674189567566,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8902,
      "step": 153
    },
    {
      "epoch": 2.1095890410958904,
      "grad_norm": 0.4706248342990875,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8945,
      "step": 154
    },
    {
      "epoch": 2.1232876712328768,
      "grad_norm": 0.4087844491004944,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.8006,
      "step": 155
    },
    {
      "epoch": 2.136986301369863,
      "grad_norm": 0.3883665204048157,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6807,
      "step": 156
    },
    {
      "epoch": 2.1506849315068495,
      "grad_norm": 0.3876743018627167,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7876,
      "step": 157
    },
    {
      "epoch": 2.1643835616438354,
      "grad_norm": 0.38811245560646057,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.781,
      "step": 158
    },
    {
      "epoch": 2.1780821917808217,
      "grad_norm": 0.4533320665359497,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8823,
      "step": 159
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.40115228295326233,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7343,
      "step": 160
    },
    {
      "epoch": 2.2054794520547945,
      "grad_norm": 0.4575008153915405,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7954,
      "step": 161
    },
    {
      "epoch": 2.219178082191781,
      "grad_norm": 0.5651206970214844,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.769,
      "step": 162
    },
    {
      "epoch": 2.232876712328767,
      "grad_norm": 0.588489294052124,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7398,
      "step": 163
    },
    {
      "epoch": 2.2465753424657535,
      "grad_norm": 0.7558596730232239,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6609,
      "step": 164
    },
    {
      "epoch": 2.26027397260274,
      "grad_norm": 0.43365684151649475,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7743,
      "step": 165
    },
    {
      "epoch": 2.2739726027397262,
      "grad_norm": 0.4219360947608948,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7851,
      "step": 166
    },
    {
      "epoch": 2.287671232876712,
      "grad_norm": 0.46471884846687317,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8341,
      "step": 167
    },
    {
      "epoch": 2.3013698630136985,
      "grad_norm": 0.443402498960495,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8097,
      "step": 168
    },
    {
      "epoch": 2.315068493150685,
      "grad_norm": 0.5079222917556763,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6999,
      "step": 169
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 0.426798939704895,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8204,
      "step": 170
    },
    {
      "epoch": 2.3424657534246576,
      "grad_norm": 0.4524076282978058,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7745,
      "step": 171
    },
    {
      "epoch": 2.356164383561644,
      "grad_norm": 0.41797712445259094,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7712,
      "step": 172
    },
    {
      "epoch": 2.3698630136986303,
      "grad_norm": 0.4687945544719696,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8873,
      "step": 173
    },
    {
      "epoch": 2.383561643835616,
      "grad_norm": 0.40561527013778687,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7591,
      "step": 174
    },
    {
      "epoch": 2.3972602739726026,
      "grad_norm": 0.41949617862701416,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8097,
      "step": 175
    },
    {
      "epoch": 2.410958904109589,
      "grad_norm": 0.44182324409484863,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8746,
      "step": 176
    },
    {
      "epoch": 2.4246575342465753,
      "grad_norm": 0.4126521646976471,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6721,
      "step": 177
    },
    {
      "epoch": 2.4383561643835616,
      "grad_norm": 0.449280709028244,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7201,
      "step": 178
    },
    {
      "epoch": 2.452054794520548,
      "grad_norm": 0.42612722516059875,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7424,
      "step": 179
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.5589396953582764,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.9689,
      "step": 180
    },
    {
      "epoch": 2.4794520547945207,
      "grad_norm": 0.5777844786643982,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.665,
      "step": 181
    },
    {
      "epoch": 2.493150684931507,
      "grad_norm": 0.7144551873207092,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6964,
      "step": 182
    },
    {
      "epoch": 2.506849315068493,
      "grad_norm": 0.4251442849636078,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8463,
      "step": 183
    },
    {
      "epoch": 2.5205479452054793,
      "grad_norm": 0.4015757739543915,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7687,
      "step": 184
    },
    {
      "epoch": 2.5342465753424657,
      "grad_norm": 0.4029443860054016,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8327,
      "step": 185
    },
    {
      "epoch": 2.547945205479452,
      "grad_norm": 0.42869704961776733,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9011,
      "step": 186
    },
    {
      "epoch": 2.5616438356164384,
      "grad_norm": 0.42311233282089233,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8914,
      "step": 187
    },
    {
      "epoch": 2.5753424657534247,
      "grad_norm": 0.42860546708106995,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8559,
      "step": 188
    },
    {
      "epoch": 2.589041095890411,
      "grad_norm": 0.395050585269928,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7822,
      "step": 189
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 0.43826475739479065,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8306,
      "step": 190
    },
    {
      "epoch": 2.616438356164384,
      "grad_norm": 0.40494588017463684,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.766,
      "step": 191
    },
    {
      "epoch": 2.6301369863013697,
      "grad_norm": 0.4274336099624634,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.781,
      "step": 192
    },
    {
      "epoch": 2.643835616438356,
      "grad_norm": 0.409477174282074,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7694,
      "step": 193
    },
    {
      "epoch": 2.6575342465753424,
      "grad_norm": 0.4418693482875824,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8603,
      "step": 194
    },
    {
      "epoch": 2.671232876712329,
      "grad_norm": 0.46309995651245117,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7817,
      "step": 195
    },
    {
      "epoch": 2.684931506849315,
      "grad_norm": 0.3981907367706299,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6408,
      "step": 196
    },
    {
      "epoch": 2.6986301369863015,
      "grad_norm": 0.45853447914123535,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7248,
      "step": 197
    },
    {
      "epoch": 2.712328767123288,
      "grad_norm": 0.4586510956287384,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6827,
      "step": 198
    },
    {
      "epoch": 2.7260273972602738,
      "grad_norm": 0.588334321975708,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7644,
      "step": 199
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.6072391867637634,
      "learning_rate": 0.0,
      "loss": 0.6352,
      "step": 200
    },
    {
      "epoch": 2.73972602739726,
      "eval_loss": 0.8842717409133911,
      "eval_runtime": 17.7574,
      "eval_samples_per_second": 6.927,
      "eval_steps_per_second": 1.746,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5.495599768849613e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}