{
  "best_metric": 1.25753653049469,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.029961424665742857,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014980712332871428,
      "grad_norm": 0.8416824340820312,
      "learning_rate": 1e-05,
      "loss": 1.108,
      "step": 1
    },
    {
      "epoch": 0.00014980712332871428,
      "eval_loss": 1.3832623958587646,
      "eval_runtime": 212.1958,
      "eval_samples_per_second": 52.984,
      "eval_steps_per_second": 13.247,
      "step": 1
    },
    {
      "epoch": 0.00029961424665742855,
      "grad_norm": 0.8456633687019348,
      "learning_rate": 2e-05,
      "loss": 1.0502,
      "step": 2
    },
    {
      "epoch": 0.00044942136998614283,
      "grad_norm": 1.1890586614608765,
      "learning_rate": 3e-05,
      "loss": 1.1755,
      "step": 3
    },
    {
      "epoch": 0.0005992284933148571,
      "grad_norm": 0.9741934537887573,
      "learning_rate": 4e-05,
      "loss": 1.1805,
      "step": 4
    },
    {
      "epoch": 0.0007490356166435714,
      "grad_norm": 0.7530410885810852,
      "learning_rate": 5e-05,
      "loss": 1.2913,
      "step": 5
    },
    {
      "epoch": 0.0008988427399722857,
      "grad_norm": 0.7736694812774658,
      "learning_rate": 6e-05,
      "loss": 1.3387,
      "step": 6
    },
    {
      "epoch": 0.001048649863301,
      "grad_norm": 0.7105048894882202,
      "learning_rate": 7e-05,
      "loss": 1.2599,
      "step": 7
    },
    {
      "epoch": 0.0011984569866297142,
      "grad_norm": 0.7769776582717896,
      "learning_rate": 8e-05,
      "loss": 1.409,
      "step": 8
    },
    {
      "epoch": 0.0013482641099584285,
      "grad_norm": 0.799020528793335,
      "learning_rate": 9e-05,
      "loss": 1.4235,
      "step": 9
    },
    {
      "epoch": 0.0014980712332871428,
      "grad_norm": 0.7377203702926636,
      "learning_rate": 0.0001,
      "loss": 1.3642,
      "step": 10
    },
    {
      "epoch": 0.001647878356615857,
      "grad_norm": 0.7292687892913818,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3733,
      "step": 11
    },
    {
      "epoch": 0.0017976854799445713,
      "grad_norm": 0.7816072106361389,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2799,
      "step": 12
    },
    {
      "epoch": 0.0019474926032732856,
      "grad_norm": 0.8299136161804199,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4062,
      "step": 13
    },
    {
      "epoch": 0.002097299726602,
      "grad_norm": 0.7175158858299255,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.3682,
      "step": 14
    },
    {
      "epoch": 0.0022471068499307144,
      "grad_norm": 0.8346515893936157,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1378,
      "step": 15
    },
    {
      "epoch": 0.0023969139732594284,
      "grad_norm": 0.8569032549858093,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.35,
      "step": 16
    },
    {
      "epoch": 0.002546721096588143,
      "grad_norm": 0.9427520632743835,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.3538,
      "step": 17
    },
    {
      "epoch": 0.002696528219916857,
      "grad_norm": 0.8261644244194031,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3267,
      "step": 18
    },
    {
      "epoch": 0.0028463353432455715,
      "grad_norm": 0.834083080291748,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3982,
      "step": 19
    },
    {
      "epoch": 0.0029961424665742855,
      "grad_norm": 0.9793573021888733,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.3774,
      "step": 20
    },
    {
      "epoch": 0.003145949589903,
      "grad_norm": 0.890082597732544,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1741,
      "step": 21
    },
    {
      "epoch": 0.003295756713231714,
      "grad_norm": 0.8142857551574707,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1079,
      "step": 22
    },
    {
      "epoch": 0.0034455638365604286,
      "grad_norm": 0.9374775290489197,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2381,
      "step": 23
    },
    {
      "epoch": 0.0035953709598891426,
      "grad_norm": 0.9725097417831421,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2834,
      "step": 24
    },
    {
      "epoch": 0.003745178083217857,
      "grad_norm": 0.8001689910888672,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.1564,
      "step": 25
    },
    {
      "epoch": 0.003894985206546571,
      "grad_norm": 0.8218423128128052,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.4056,
      "step": 26
    },
    {
      "epoch": 0.004044792329875285,
      "grad_norm": 0.7508614659309387,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.2295,
      "step": 27
    },
    {
      "epoch": 0.004194599453204,
      "grad_norm": 0.8375084400177002,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2604,
      "step": 28
    },
    {
      "epoch": 0.004344406576532714,
      "grad_norm": 0.8266900181770325,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1488,
      "step": 29
    },
    {
      "epoch": 0.004494213699861429,
      "grad_norm": 0.7884365916252136,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1769,
      "step": 30
    },
    {
      "epoch": 0.004644020823190142,
      "grad_norm": 0.8397653102874756,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.266,
      "step": 31
    },
    {
      "epoch": 0.004793827946518857,
      "grad_norm": 0.7986391186714172,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2439,
      "step": 32
    },
    {
      "epoch": 0.004943635069847571,
      "grad_norm": 0.8862866163253784,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1056,
      "step": 33
    },
    {
      "epoch": 0.005093442193176286,
      "grad_norm": 0.8518185615539551,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.052,
      "step": 34
    },
    {
      "epoch": 0.0052432493165049995,
      "grad_norm": 0.9025084376335144,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2215,
      "step": 35
    },
    {
      "epoch": 0.005393056439833714,
      "grad_norm": 0.9923230409622192,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.2796,
      "step": 36
    },
    {
      "epoch": 0.0055428635631624285,
      "grad_norm": 0.876867413520813,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1873,
      "step": 37
    },
    {
      "epoch": 0.005692670686491143,
      "grad_norm": 1.0643788576126099,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3207,
      "step": 38
    },
    {
      "epoch": 0.005842477809819857,
      "grad_norm": 0.9992518424987793,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.4191,
      "step": 39
    },
    {
      "epoch": 0.005992284933148571,
      "grad_norm": 1.0284870862960815,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.4293,
      "step": 40
    },
    {
      "epoch": 0.0061420920564772856,
      "grad_norm": 0.9340959787368774,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.008,
      "step": 41
    },
    {
      "epoch": 0.006291899179806,
      "grad_norm": 1.0773531198501587,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.308,
      "step": 42
    },
    {
      "epoch": 0.006441706303134714,
      "grad_norm": 1.16355299949646,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.238,
      "step": 43
    },
    {
      "epoch": 0.006591513426463428,
      "grad_norm": 1.331459641456604,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.3748,
      "step": 44
    },
    {
      "epoch": 0.006741320549792143,
      "grad_norm": 1.3905109167099,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3759,
      "step": 45
    },
    {
      "epoch": 0.006891127673120857,
      "grad_norm": 1.2792233228683472,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.3216,
      "step": 46
    },
    {
      "epoch": 0.007040934796449571,
      "grad_norm": 1.5716098546981812,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.5484,
      "step": 47
    },
    {
      "epoch": 0.007190741919778285,
      "grad_norm": 1.8005694150924683,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4232,
      "step": 48
    },
    {
      "epoch": 0.007340549043107,
      "grad_norm": 2.075828790664673,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.6109,
      "step": 49
    },
    {
      "epoch": 0.007490356166435714,
      "grad_norm": 2.8633785247802734,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5112,
      "step": 50
    },
    {
      "epoch": 0.007490356166435714,
      "eval_loss": 1.2952868938446045,
      "eval_runtime": 212.2019,
      "eval_samples_per_second": 52.983,
      "eval_steps_per_second": 13.247,
      "step": 50
    },
    {
      "epoch": 0.007640163289764428,
      "grad_norm": 0.6332350373268127,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.1968,
      "step": 51
    },
    {
      "epoch": 0.007789970413093142,
      "grad_norm": 0.6210179328918457,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1792,
      "step": 52
    },
    {
      "epoch": 0.007939777536421857,
      "grad_norm": 0.8244756460189819,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0284,
      "step": 53
    },
    {
      "epoch": 0.00808958465975057,
      "grad_norm": 0.7848068475723267,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2713,
      "step": 54
    },
    {
      "epoch": 0.008239391783079286,
      "grad_norm": 0.5899185538291931,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1248,
      "step": 55
    },
    {
      "epoch": 0.008389198906408,
      "grad_norm": 0.5908650755882263,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2451,
      "step": 56
    },
    {
      "epoch": 0.008539006029736713,
      "grad_norm": 0.5692049264907837,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.1877,
      "step": 57
    },
    {
      "epoch": 0.008688813153065428,
      "grad_norm": 0.6065800189971924,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3251,
      "step": 58
    },
    {
      "epoch": 0.008838620276394142,
      "grad_norm": 0.5871240496635437,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.225,
      "step": 59
    },
    {
      "epoch": 0.008988427399722857,
      "grad_norm": 0.5764657855033875,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.3186,
      "step": 60
    },
    {
      "epoch": 0.009138234523051571,
      "grad_norm": 0.5643742680549622,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3644,
      "step": 61
    },
    {
      "epoch": 0.009288041646380285,
      "grad_norm": 0.5923104286193848,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.2491,
      "step": 62
    },
    {
      "epoch": 0.009437848769709,
      "grad_norm": 0.5960894227027893,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3522,
      "step": 63
    },
    {
      "epoch": 0.009587655893037714,
      "grad_norm": 0.6497281789779663,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.2148,
      "step": 64
    },
    {
      "epoch": 0.009737463016366429,
      "grad_norm": 0.6208597421646118,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1932,
      "step": 65
    },
    {
      "epoch": 0.009887270139695143,
      "grad_norm": 0.6854526996612549,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.2126,
      "step": 66
    },
    {
      "epoch": 0.010037077263023856,
      "grad_norm": 0.7062629461288452,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2984,
      "step": 67
    },
    {
      "epoch": 0.010186884386352572,
      "grad_norm": 0.7459825873374939,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.0701,
      "step": 68
    },
    {
      "epoch": 0.010336691509681285,
      "grad_norm": 0.7247086763381958,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.4269,
      "step": 69
    },
    {
      "epoch": 0.010486498633009999,
      "grad_norm": 0.6482049822807312,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2306,
      "step": 70
    },
    {
      "epoch": 0.010636305756338714,
      "grad_norm": 0.6704904437065125,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.1925,
      "step": 71
    },
    {
      "epoch": 0.010786112879667428,
      "grad_norm": 0.9185197949409485,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0465,
      "step": 72
    },
    {
      "epoch": 0.010935920002996143,
      "grad_norm": 0.6978965997695923,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2484,
      "step": 73
    },
    {
      "epoch": 0.011085727126324857,
      "grad_norm": 0.6785476803779602,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.1714,
      "step": 74
    },
    {
      "epoch": 0.01123553424965357,
      "grad_norm": 0.7337586283683777,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2292,
      "step": 75
    },
    {
      "epoch": 0.011385341372982286,
      "grad_norm": 0.7189891934394836,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.2943,
      "step": 76
    },
    {
      "epoch": 0.011535148496311,
      "grad_norm": 0.6964775919914246,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2251,
      "step": 77
    },
    {
      "epoch": 0.011684955619639713,
      "grad_norm": 0.7245413661003113,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0629,
      "step": 78
    },
    {
      "epoch": 0.011834762742968429,
      "grad_norm": 0.8027443289756775,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3193,
      "step": 79
    },
    {
      "epoch": 0.011984569866297142,
      "grad_norm": 0.7252655625343323,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.3003,
      "step": 80
    },
    {
      "epoch": 0.012134376989625857,
      "grad_norm": 0.6839256286621094,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2096,
      "step": 81
    },
    {
      "epoch": 0.012284184112954571,
      "grad_norm": 0.787334144115448,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3145,
      "step": 82
    },
    {
      "epoch": 0.012433991236283285,
      "grad_norm": 0.7616652846336365,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.1901,
      "step": 83
    },
    {
      "epoch": 0.012583798359612,
      "grad_norm": 0.7656141519546509,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.3405,
      "step": 84
    },
    {
      "epoch": 0.012733605482940714,
      "grad_norm": 0.8246110081672668,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2628,
      "step": 85
    },
    {
      "epoch": 0.012883412606269427,
      "grad_norm": 0.8016843795776367,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0433,
      "step": 86
    },
    {
      "epoch": 0.013033219729598143,
      "grad_norm": 0.7872653603553772,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.0575,
      "step": 87
    },
    {
      "epoch": 0.013183026852926856,
      "grad_norm": 0.869793176651001,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.191,
      "step": 88
    },
    {
      "epoch": 0.013332833976255572,
      "grad_norm": 0.8165619373321533,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.1168,
      "step": 89
    },
    {
      "epoch": 0.013482641099584285,
      "grad_norm": 0.9148740768432617,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.1937,
      "step": 90
    },
    {
      "epoch": 0.013632448222912999,
      "grad_norm": 0.9416880011558533,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1547,
      "step": 91
    },
    {
      "epoch": 0.013782255346241714,
      "grad_norm": 1.03351891040802,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.2628,
      "step": 92
    },
    {
      "epoch": 0.013932062469570428,
      "grad_norm": 1.141595721244812,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2859,
      "step": 93
    },
    {
      "epoch": 0.014081869592899142,
      "grad_norm": 1.1944646835327148,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.058,
      "step": 94
    },
    {
      "epoch": 0.014231676716227857,
      "grad_norm": 1.2365891933441162,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.0763,
      "step": 95
    },
    {
      "epoch": 0.01438148383955657,
      "grad_norm": 1.3501421213150024,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.4778,
      "step": 96
    },
    {
      "epoch": 0.014531290962885286,
      "grad_norm": 1.4268779754638672,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.5924,
      "step": 97
    },
    {
      "epoch": 0.014681098086214,
      "grad_norm": 2.2394773960113525,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.4694,
      "step": 98
    },
    {
      "epoch": 0.014830905209542713,
      "grad_norm": 2.2251193523406982,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.4556,
      "step": 99
    },
    {
      "epoch": 0.014980712332871429,
      "grad_norm": 2.76419997215271,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5404,
      "step": 100
    },
    {
      "epoch": 0.014980712332871429,
      "eval_loss": 1.2689018249511719,
      "eval_runtime": 212.1668,
      "eval_samples_per_second": 52.991,
      "eval_steps_per_second": 13.249,
      "step": 100
    },
    {
      "epoch": 0.015130519456200142,
      "grad_norm": 0.562955915927887,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.2251,
      "step": 101
    },
    {
      "epoch": 0.015280326579528856,
      "grad_norm": 0.7312610149383545,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.1437,
      "step": 102
    },
    {
      "epoch": 0.015430133702857571,
      "grad_norm": 0.6145124435424805,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8511,
      "step": 103
    },
    {
      "epoch": 0.015579940826186285,
      "grad_norm": 1.177874207496643,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.116,
      "step": 104
    },
    {
      "epoch": 0.015729747949515,
      "grad_norm": 0.5854660868644714,
      "learning_rate": 5e-05,
      "loss": 1.0903,
      "step": 105
    },
    {
      "epoch": 0.015879555072843714,
      "grad_norm": 0.5717855095863342,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.3579,
      "step": 106
    },
    {
      "epoch": 0.016029362196172427,
      "grad_norm": 0.6061097383499146,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.4909,
      "step": 107
    },
    {
      "epoch": 0.01617916931950114,
      "grad_norm": 0.5581495761871338,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.3921,
      "step": 108
    },
    {
      "epoch": 0.016328976442829858,
      "grad_norm": 0.528045117855072,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.1971,
      "step": 109
    },
    {
      "epoch": 0.01647878356615857,
      "grad_norm": 0.6216000318527222,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.3903,
      "step": 110
    },
    {
      "epoch": 0.016628590689487285,
      "grad_norm": 0.6433857083320618,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.2694,
      "step": 111
    },
    {
      "epoch": 0.016778397812816,
      "grad_norm": 0.5676413178443909,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.4193,
      "step": 112
    },
    {
      "epoch": 0.016928204936144713,
      "grad_norm": 0.562670111656189,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.3706,
      "step": 113
    },
    {
      "epoch": 0.017078012059473426,
      "grad_norm": 0.5929762721061707,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.2658,
      "step": 114
    },
    {
      "epoch": 0.017227819182802143,
      "grad_norm": 0.669247567653656,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.3116,
      "step": 115
    },
    {
      "epoch": 0.017377626306130857,
      "grad_norm": 0.6218504905700684,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2707,
      "step": 116
    },
    {
      "epoch": 0.01752743342945957,
      "grad_norm": 0.6539035439491272,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.3079,
      "step": 117
    },
    {
      "epoch": 0.017677240552788284,
      "grad_norm": 0.7109789252281189,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.1234,
      "step": 118
    },
    {
      "epoch": 0.017827047676116998,
      "grad_norm": 0.7230955958366394,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.3176,
      "step": 119
    },
    {
      "epoch": 0.017976854799445715,
      "grad_norm": 0.7343471050262451,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.2192,
      "step": 120
    },
    {
      "epoch": 0.01812666192277443,
      "grad_norm": 0.682965099811554,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.1665,
      "step": 121
    },
    {
      "epoch": 0.018276469046103142,
      "grad_norm": 0.7259899973869324,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.2293,
      "step": 122
    },
    {
      "epoch": 0.018426276169431856,
      "grad_norm": 0.8501508831977844,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.1932,
      "step": 123
    },
    {
      "epoch": 0.01857608329276057,
      "grad_norm": 0.6927886605262756,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.117,
      "step": 124
    },
    {
      "epoch": 0.018725890416089287,
      "grad_norm": 0.71158367395401,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3288,
      "step": 125
    },
    {
      "epoch": 0.018875697539418,
      "grad_norm": 0.7121936678886414,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2155,
      "step": 126
    },
    {
      "epoch": 0.019025504662746714,
      "grad_norm": 0.7002630233764648,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.0413,
      "step": 127
    },
    {
      "epoch": 0.019175311786075427,
      "grad_norm": 0.7453745603561401,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.0846,
      "step": 128
    },
    {
      "epoch": 0.01932511890940414,
      "grad_norm": 0.7211044430732727,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.0788,
      "step": 129
    },
    {
      "epoch": 0.019474926032732858,
      "grad_norm": 0.7318615913391113,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0619,
      "step": 130
    },
    {
      "epoch": 0.019624733156061572,
      "grad_norm": 0.7178171873092651,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.201,
      "step": 131
    },
    {
      "epoch": 0.019774540279390285,
      "grad_norm": 0.6753542423248291,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.0555,
      "step": 132
    },
    {
      "epoch": 0.019924347402719,
      "grad_norm": 0.8013312220573425,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.3032,
      "step": 133
    },
    {
      "epoch": 0.020074154526047713,
      "grad_norm": 0.7693833112716675,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.1242,
      "step": 134
    },
    {
      "epoch": 0.020223961649376426,
      "grad_norm": 0.7697752714157104,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2202,
      "step": 135
    },
    {
      "epoch": 0.020373768772705143,
      "grad_norm": 0.8076735138893127,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.17,
      "step": 136
    },
    {
      "epoch": 0.020523575896033857,
      "grad_norm": 0.8046029210090637,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.3088,
      "step": 137
    },
    {
      "epoch": 0.02067338301936257,
      "grad_norm": 0.7976809740066528,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0482,
      "step": 138
    },
    {
      "epoch": 0.020823190142691284,
      "grad_norm": 1.0324242115020752,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.2284,
      "step": 139
    },
    {
      "epoch": 0.020972997266019998,
      "grad_norm": 0.7962802648544312,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0574,
      "step": 140
    },
    {
      "epoch": 0.021122804389348715,
      "grad_norm": 0.8662652969360352,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.056,
      "step": 141
    },
    {
      "epoch": 0.02127261151267743,
      "grad_norm": 0.9411537051200867,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.1197,
      "step": 142
    },
    {
      "epoch": 0.021422418636006142,
      "grad_norm": 1.092484712600708,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1818,
      "step": 143
    },
    {
      "epoch": 0.021572225759334856,
      "grad_norm": 1.1731982231140137,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.3829,
      "step": 144
    },
    {
      "epoch": 0.02172203288266357,
      "grad_norm": 1.1861002445220947,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1755,
      "step": 145
    },
    {
      "epoch": 0.021871840005992287,
      "grad_norm": 1.315170168876648,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2864,
      "step": 146
    },
    {
      "epoch": 0.022021647129321,
      "grad_norm": 1.6993236541748047,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.5576,
      "step": 147
    },
    {
      "epoch": 0.022171454252649714,
      "grad_norm": 1.9727485179901123,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.328,
      "step": 148
    },
    {
      "epoch": 0.022321261375978427,
      "grad_norm": 2.5295138359069824,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.2508,
      "step": 149
    },
    {
      "epoch": 0.02247106849930714,
      "grad_norm": 2.519742012023926,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3669,
      "step": 150
    },
    {
      "epoch": 0.02247106849930714,
      "eval_loss": 1.2603070735931396,
      "eval_runtime": 211.8995,
      "eval_samples_per_second": 53.058,
      "eval_steps_per_second": 13.266,
      "step": 150
    },
    {
      "epoch": 0.022620875622635855,
      "grad_norm": 0.5140734314918518,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.1063,
      "step": 151
    },
    {
      "epoch": 0.022770682745964572,
      "grad_norm": 0.5728786587715149,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.0374,
      "step": 152
    },
    {
      "epoch": 0.022920489869293285,
      "grad_norm": 0.8557982444763184,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.0461,
      "step": 153
    },
    {
      "epoch": 0.023070296992622,
      "grad_norm": 0.5744186639785767,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.0405,
      "step": 154
    },
    {
      "epoch": 0.023220104115950713,
      "grad_norm": 0.5100783705711365,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.184,
      "step": 155
    },
    {
      "epoch": 0.023369911239279426,
      "grad_norm": 0.5310792922973633,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.1675,
      "step": 156
    },
    {
      "epoch": 0.023519718362608143,
      "grad_norm": 0.5873476266860962,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.3679,
      "step": 157
    },
    {
      "epoch": 0.023669525485936857,
      "grad_norm": 0.5490432381629944,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.4396,
      "step": 158
    },
    {
      "epoch": 0.02381933260926557,
      "grad_norm": 0.5423150658607483,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.3423,
      "step": 159
    },
    {
      "epoch": 0.023969139732594284,
      "grad_norm": 0.5367304682731628,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2553,
      "step": 160
    },
    {
      "epoch": 0.024118946855922998,
      "grad_norm": 0.5803803205490112,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.3702,
      "step": 161
    },
    {
      "epoch": 0.024268753979251715,
      "grad_norm": 0.5762766003608704,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2927,
      "step": 162
    },
    {
      "epoch": 0.02441856110258043,
      "grad_norm": 0.5983667969703674,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3589,
      "step": 163
    },
    {
      "epoch": 0.024568368225909142,
      "grad_norm": 0.7154777646064758,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.3239,
      "step": 164
    },
    {
      "epoch": 0.024718175349237856,
      "grad_norm": 0.6455360651016235,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.1508,
      "step": 165
    },
    {
      "epoch": 0.02486798247256657,
      "grad_norm": 0.6302279829978943,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.3153,
      "step": 166
    },
    {
      "epoch": 0.025017789595895283,
      "grad_norm": 0.7640451788902283,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.2594,
      "step": 167
    },
    {
      "epoch": 0.025167596719224,
      "grad_norm": 0.6551406979560852,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.1333,
      "step": 168
    },
    {
      "epoch": 0.025317403842552714,
      "grad_norm": 0.7191906571388245,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2238,
      "step": 169
    },
    {
      "epoch": 0.025467210965881427,
      "grad_norm": 0.6581866145133972,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2398,
      "step": 170
    },
    {
      "epoch": 0.02561701808921014,
      "grad_norm": 0.7158983945846558,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.3394,
      "step": 171
    },
    {
      "epoch": 0.025766825212538855,
      "grad_norm": 0.7117244601249695,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.0219,
      "step": 172
    },
    {
      "epoch": 0.025916632335867572,
      "grad_norm": 0.6462054252624512,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.2295,
      "step": 173
    },
    {
      "epoch": 0.026066439459196285,
      "grad_norm": 0.7175354957580566,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3749,
      "step": 174
    },
    {
      "epoch": 0.026216246582525,
      "grad_norm": 0.7314172983169556,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1972,
      "step": 175
    },
    {
      "epoch": 0.026366053705853713,
      "grad_norm": 0.7079600095748901,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.0818,
      "step": 176
    },
    {
      "epoch": 0.026515860829182426,
      "grad_norm": 0.7221912145614624,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.1754,
      "step": 177
    },
    {
      "epoch": 0.026665667952511143,
      "grad_norm": 0.7075243592262268,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1303,
      "step": 178
    },
    {
      "epoch": 0.026815475075839857,
      "grad_norm": 0.7320074439048767,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2319,
      "step": 179
    },
    {
      "epoch": 0.02696528219916857,
      "grad_norm": 0.7525650858879089,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.0852,
      "step": 180
    },
    {
      "epoch": 0.027115089322497284,
      "grad_norm": 0.7716807723045349,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1252,
      "step": 181
    },
    {
      "epoch": 0.027264896445825998,
      "grad_norm": 0.7430640459060669,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3351,
      "step": 182
    },
    {
      "epoch": 0.027414703569154715,
      "grad_norm": 0.7228444218635559,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.199,
      "step": 183
    },
    {
      "epoch": 0.02756451069248343,
      "grad_norm": 0.7958812713623047,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.1063,
      "step": 184
    },
    {
      "epoch": 0.027714317815812142,
      "grad_norm": 0.8028236031532288,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.1753,
      "step": 185
    },
    {
      "epoch": 0.027864124939140856,
      "grad_norm": 0.7617059946060181,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.1463,
      "step": 186
    },
    {
      "epoch": 0.02801393206246957,
      "grad_norm": 0.8760780692100525,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.347,
      "step": 187
    },
    {
      "epoch": 0.028163739185798283,
      "grad_norm": 0.8513113260269165,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.1706,
      "step": 188
    },
    {
      "epoch": 0.028313546309127,
      "grad_norm": 0.9344687461853027,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.2148,
      "step": 189
    },
    {
      "epoch": 0.028463353432455714,
      "grad_norm": 0.8653374314308167,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.0781,
      "step": 190
    },
    {
      "epoch": 0.028613160555784427,
      "grad_norm": 1.053428292274475,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.2361,
      "step": 191
    },
    {
      "epoch": 0.02876296767911314,
      "grad_norm": 1.1018505096435547,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.3333,
      "step": 192
    },
    {
      "epoch": 0.028912774802441855,
      "grad_norm": 0.9986382722854614,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.1363,
      "step": 193
    },
    {
      "epoch": 0.029062581925770572,
      "grad_norm": 1.0806999206542969,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.1895,
      "step": 194
    },
    {
      "epoch": 0.029212389049099285,
      "grad_norm": 1.0584535598754883,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.4493,
      "step": 195
    },
    {
      "epoch": 0.029362196172428,
      "grad_norm": 1.3989263772964478,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.5348,
      "step": 196
    },
    {
      "epoch": 0.029512003295756713,
      "grad_norm": 1.4781029224395752,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.5,
      "step": 197
    },
    {
      "epoch": 0.029661810419085426,
      "grad_norm": 1.4467251300811768,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.4891,
      "step": 198
    },
    {
      "epoch": 0.029811617542414143,
      "grad_norm": 1.7664724588394165,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.6251,
      "step": 199
    },
    {
      "epoch": 0.029961424665742857,
      "grad_norm": 2.6659719944000244,
      "learning_rate": 0.0,
      "loss": 1.3753,
      "step": 200
    },
    {
      "epoch": 0.029961424665742857,
      "eval_loss": 1.25753653049469,
      "eval_runtime": 212.0189,
      "eval_samples_per_second": 53.028,
      "eval_steps_per_second": 13.258,
      "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": 1.6596916022280192e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}