{
  "best_metric": 0.5652009844779968,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10064159013712416,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005032079506856208,
      "grad_norm": 0.19626334309577942,
      "learning_rate": 6e-06,
      "loss": 0.4518,
      "step": 1
    },
    {
      "epoch": 0.0005032079506856208,
      "eval_loss": 0.7585222125053406,
      "eval_runtime": 252.2259,
      "eval_samples_per_second": 13.27,
      "eval_steps_per_second": 3.318,
      "step": 1
    },
    {
      "epoch": 0.0010064159013712416,
      "grad_norm": 0.30448371171951294,
      "learning_rate": 1.2e-05,
      "loss": 0.4876,
      "step": 2
    },
    {
      "epoch": 0.0015096238520568624,
      "grad_norm": 0.21121546626091003,
      "learning_rate": 1.8e-05,
      "loss": 0.4507,
      "step": 3
    },
    {
      "epoch": 0.0020128318027424832,
      "grad_norm": 0.188644677400589,
      "learning_rate": 2.4e-05,
      "loss": 0.4889,
      "step": 4
    },
    {
      "epoch": 0.002516039753428104,
      "grad_norm": 0.18691356480121613,
      "learning_rate": 3e-05,
      "loss": 0.5132,
      "step": 5
    },
    {
      "epoch": 0.003019247704113725,
      "grad_norm": 0.18799184262752533,
      "learning_rate": 3.6e-05,
      "loss": 0.4601,
      "step": 6
    },
    {
      "epoch": 0.0035224556547993457,
      "grad_norm": 0.1896747350692749,
      "learning_rate": 4.2e-05,
      "loss": 0.4814,
      "step": 7
    },
    {
      "epoch": 0.0040256636054849665,
      "grad_norm": 0.2057279497385025,
      "learning_rate": 4.8e-05,
      "loss": 0.5705,
      "step": 8
    },
    {
      "epoch": 0.004528871556170587,
      "grad_norm": 0.20948195457458496,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.553,
      "step": 9
    },
    {
      "epoch": 0.005032079506856208,
      "grad_norm": 0.2336476594209671,
      "learning_rate": 6e-05,
      "loss": 0.579,
      "step": 10
    },
    {
      "epoch": 0.005535287457541829,
      "grad_norm": 0.2711414694786072,
      "learning_rate": 5.999589914977407e-05,
      "loss": 0.6268,
      "step": 11
    },
    {
      "epoch": 0.00603849540822745,
      "grad_norm": 0.22779054939746857,
      "learning_rate": 5.998359772022778e-05,
      "loss": 0.5297,
      "step": 12
    },
    {
      "epoch": 0.0065417033589130705,
      "grad_norm": 0.250547856092453,
      "learning_rate": 5.996309907444915e-05,
      "loss": 0.5664,
      "step": 13
    },
    {
      "epoch": 0.007044911309598691,
      "grad_norm": 0.2737247049808502,
      "learning_rate": 5.9934408816563236e-05,
      "loss": 0.617,
      "step": 14
    },
    {
      "epoch": 0.007548119260284312,
      "grad_norm": 0.2832566797733307,
      "learning_rate": 5.98975347902001e-05,
      "loss": 0.57,
      "step": 15
    },
    {
      "epoch": 0.008051327210969933,
      "grad_norm": 0.28667423129081726,
      "learning_rate": 5.9852487076350345e-05,
      "loss": 0.64,
      "step": 16
    },
    {
      "epoch": 0.008554535161655554,
      "grad_norm": 0.27054816484451294,
      "learning_rate": 5.979927799060915e-05,
      "loss": 0.5815,
      "step": 17
    },
    {
      "epoch": 0.009057743112341175,
      "grad_norm": 0.2659466564655304,
      "learning_rate": 5.9737922079809257e-05,
      "loss": 0.6226,
      "step": 18
    },
    {
      "epoch": 0.009560951063026795,
      "grad_norm": 0.2718023955821991,
      "learning_rate": 5.9668436118044054e-05,
      "loss": 0.6168,
      "step": 19
    },
    {
      "epoch": 0.010064159013712416,
      "grad_norm": 0.2833111584186554,
      "learning_rate": 5.959083910208167e-05,
      "loss": 0.6044,
      "step": 20
    },
    {
      "epoch": 0.010567366964398037,
      "grad_norm": 0.2512868344783783,
      "learning_rate": 5.9505152246171474e-05,
      "loss": 0.5856,
      "step": 21
    },
    {
      "epoch": 0.011070574915083658,
      "grad_norm": 0.27297303080558777,
      "learning_rate": 5.941139897624428e-05,
      "loss": 0.5529,
      "step": 22
    },
    {
      "epoch": 0.011573782865769279,
      "grad_norm": 0.28323543071746826,
      "learning_rate": 5.9309604923507984e-05,
      "loss": 0.6048,
      "step": 23
    },
    {
      "epoch": 0.0120769908164549,
      "grad_norm": 0.26660263538360596,
      "learning_rate": 5.9199797917440176e-05,
      "loss": 0.549,
      "step": 24
    },
    {
      "epoch": 0.01258019876714052,
      "grad_norm": 0.3093823492527008,
      "learning_rate": 5.908200797817991e-05,
      "loss": 0.6472,
      "step": 25
    },
    {
      "epoch": 0.013083406717826141,
      "grad_norm": 0.31198737025260925,
      "learning_rate": 5.895626730832046e-05,
      "loss": 0.6084,
      "step": 26
    },
    {
      "epoch": 0.013586614668511762,
      "grad_norm": 0.31961148977279663,
      "learning_rate": 5.882261028410545e-05,
      "loss": 0.6121,
      "step": 27
    },
    {
      "epoch": 0.014089822619197383,
      "grad_norm": 0.32909640669822693,
      "learning_rate": 5.8681073446030734e-05,
      "loss": 0.6067,
      "step": 28
    },
    {
      "epoch": 0.014593030569883004,
      "grad_norm": 0.323501855134964,
      "learning_rate": 5.853169548885461e-05,
      "loss": 0.5354,
      "step": 29
    },
    {
      "epoch": 0.015096238520568624,
      "grad_norm": 0.31914564967155457,
      "learning_rate": 5.8374517251019035e-05,
      "loss": 0.5996,
      "step": 30
    },
    {
      "epoch": 0.015599446471254245,
      "grad_norm": 0.3329504132270813,
      "learning_rate": 5.820958170348484e-05,
      "loss": 0.5777,
      "step": 31
    },
    {
      "epoch": 0.016102654421939866,
      "grad_norm": 0.3308003544807434,
      "learning_rate": 5.8036933937983825e-05,
      "loss": 0.5634,
      "step": 32
    },
    {
      "epoch": 0.01660586237262549,
      "grad_norm": 0.36641833186149597,
      "learning_rate": 5.7856621154691217e-05,
      "loss": 0.6525,
      "step": 33
    },
    {
      "epoch": 0.017109070323311108,
      "grad_norm": 0.3300469219684601,
      "learning_rate": 5.766869264932154e-05,
      "loss": 0.5274,
      "step": 34
    },
    {
      "epoch": 0.01761227827399673,
      "grad_norm": 0.3546065092086792,
      "learning_rate": 5.747319979965172e-05,
      "loss": 0.5598,
      "step": 35
    },
    {
      "epoch": 0.01811548622468235,
      "grad_norm": 0.4386902153491974,
      "learning_rate": 5.727019605147488e-05,
      "loss": 0.8685,
      "step": 36
    },
    {
      "epoch": 0.018618694175367972,
      "grad_norm": 0.43339911103248596,
      "learning_rate": 5.7059736903988775e-05,
      "loss": 0.7248,
      "step": 37
    },
    {
      "epoch": 0.01912190212605359,
      "grad_norm": 0.4233013093471527,
      "learning_rate": 5.684187989462291e-05,
      "loss": 0.648,
      "step": 38
    },
    {
      "epoch": 0.019625110076739213,
      "grad_norm": 0.4389207065105438,
      "learning_rate": 5.661668458330836e-05,
      "loss": 0.6882,
      "step": 39
    },
    {
      "epoch": 0.020128318027424832,
      "grad_norm": 0.4583698809146881,
      "learning_rate": 5.638421253619467e-05,
      "loss": 0.5618,
      "step": 40
    },
    {
      "epoch": 0.020631525978110455,
      "grad_norm": 0.491459459066391,
      "learning_rate": 5.614452730881832e-05,
      "loss": 0.7178,
      "step": 41
    },
    {
      "epoch": 0.021134733928796074,
      "grad_norm": 0.5180851221084595,
      "learning_rate": 5.589769442872722e-05,
      "loss": 0.7387,
      "step": 42
    },
    {
      "epoch": 0.021637941879481697,
      "grad_norm": 0.5554367899894714,
      "learning_rate": 5.5643781377566175e-05,
      "loss": 0.8553,
      "step": 43
    },
    {
      "epoch": 0.022141149830167316,
      "grad_norm": 0.5855110883712769,
      "learning_rate": 5.538285757262806e-05,
      "loss": 0.832,
      "step": 44
    },
    {
      "epoch": 0.022644357780852938,
      "grad_norm": 0.5783973336219788,
      "learning_rate": 5.5114994347875856e-05,
      "loss": 0.7501,
      "step": 45
    },
    {
      "epoch": 0.023147565731538557,
      "grad_norm": 0.5938670039176941,
      "learning_rate": 5.48402649344406e-05,
      "loss": 0.7538,
      "step": 46
    },
    {
      "epoch": 0.02365077368222418,
      "grad_norm": 0.6935916543006897,
      "learning_rate": 5.455874444060078e-05,
      "loss": 0.8464,
      "step": 47
    },
    {
      "epoch": 0.0241539816329098,
      "grad_norm": 0.8236449360847473,
      "learning_rate": 5.427050983124843e-05,
      "loss": 0.8105,
      "step": 48
    },
    {
      "epoch": 0.02465718958359542,
      "grad_norm": 0.7551760673522949,
      "learning_rate": 5.397563990684774e-05,
      "loss": 0.7802,
      "step": 49
    },
    {
      "epoch": 0.02516039753428104,
      "grad_norm": 1.2499607801437378,
      "learning_rate": 5.367421528189181e-05,
      "loss": 0.7255,
      "step": 50
    },
    {
      "epoch": 0.02516039753428104,
      "eval_loss": 0.5974706411361694,
      "eval_runtime": 254.4898,
      "eval_samples_per_second": 13.152,
      "eval_steps_per_second": 3.289,
      "step": 50
    },
    {
      "epoch": 0.025663605484966663,
      "grad_norm": 0.15739761292934418,
      "learning_rate": 5.336631836286338e-05,
      "loss": 0.4266,
      "step": 51
    },
    {
      "epoch": 0.026166813435652282,
      "grad_norm": 0.23158961534500122,
      "learning_rate": 5.3052033325705774e-05,
      "loss": 0.4448,
      "step": 52
    },
    {
      "epoch": 0.026670021386337905,
      "grad_norm": 0.1935783177614212,
      "learning_rate": 5.2731446092810044e-05,
      "loss": 0.4144,
      "step": 53
    },
    {
      "epoch": 0.027173229337023524,
      "grad_norm": 0.22006827592849731,
      "learning_rate": 5.240464430952462e-05,
      "loss": 0.4695,
      "step": 54
    },
    {
      "epoch": 0.027676437287709146,
      "grad_norm": 0.1802680343389511,
      "learning_rate": 5.207171732019395e-05,
      "loss": 0.386,
      "step": 55
    },
    {
      "epoch": 0.028179645238394765,
      "grad_norm": 0.1901884824037552,
      "learning_rate": 5.1732756143732675e-05,
      "loss": 0.4352,
      "step": 56
    },
    {
      "epoch": 0.028682853189080388,
      "grad_norm": 0.18005871772766113,
      "learning_rate": 5.1387853448741916e-05,
      "loss": 0.4333,
      "step": 57
    },
    {
      "epoch": 0.029186061139766007,
      "grad_norm": 0.22896796464920044,
      "learning_rate": 5.103710352817465e-05,
      "loss": 0.5558,
      "step": 58
    },
    {
      "epoch": 0.02968926909045163,
      "grad_norm": 0.21318134665489197,
      "learning_rate": 5.068060227355698e-05,
      "loss": 0.5144,
      "step": 59
    },
    {
      "epoch": 0.03019247704113725,
      "grad_norm": 0.21284860372543335,
      "learning_rate": 5.0318447148772234e-05,
      "loss": 0.5527,
      "step": 60
    },
    {
      "epoch": 0.03069568499182287,
      "grad_norm": 0.2154277116060257,
      "learning_rate": 4.995073716341545e-05,
      "loss": 0.5311,
      "step": 61
    },
    {
      "epoch": 0.03119889294250849,
      "grad_norm": 0.2523919343948364,
      "learning_rate": 4.957757284572506e-05,
      "loss": 0.655,
      "step": 62
    },
    {
      "epoch": 0.03170210089319411,
      "grad_norm": 0.23587137460708618,
      "learning_rate": 4.91990562150995e-05,
      "loss": 0.544,
      "step": 63
    },
    {
      "epoch": 0.03220530884387973,
      "grad_norm": 0.23593641817569733,
      "learning_rate": 4.881529075420611e-05,
      "loss": 0.5612,
      "step": 64
    },
    {
      "epoch": 0.03270851679456535,
      "grad_norm": 0.22735022008419037,
      "learning_rate": 4.8426381380690036e-05,
      "loss": 0.5327,
      "step": 65
    },
    {
      "epoch": 0.03321172474525098,
      "grad_norm": 0.22545917332172394,
      "learning_rate": 4.8032434418490753e-05,
      "loss": 0.503,
      "step": 66
    },
    {
      "epoch": 0.033714932695936596,
      "grad_norm": 0.2511047124862671,
      "learning_rate": 4.7633557568774194e-05,
      "loss": 0.5861,
      "step": 67
    },
    {
      "epoch": 0.034218140646622215,
      "grad_norm": 0.2359696924686432,
      "learning_rate": 4.722985988048831e-05,
      "loss": 0.5534,
      "step": 68
    },
    {
      "epoch": 0.034721348597307834,
      "grad_norm": 0.2564294636249542,
      "learning_rate": 4.6821451720550184e-05,
      "loss": 0.6447,
      "step": 69
    },
    {
      "epoch": 0.03522455654799346,
      "grad_norm": 0.2513071298599243,
      "learning_rate": 4.640844474367282e-05,
      "loss": 0.5644,
      "step": 70
    },
    {
      "epoch": 0.03572776449867908,
      "grad_norm": 0.24491123855113983,
      "learning_rate": 4.5990951861839815e-05,
      "loss": 0.4969,
      "step": 71
    },
    {
      "epoch": 0.0362309724493647,
      "grad_norm": 0.24428901076316833,
      "learning_rate": 4.5569087213436455e-05,
      "loss": 0.5217,
      "step": 72
    },
    {
      "epoch": 0.03673418040005032,
      "grad_norm": 0.2760137617588043,
      "learning_rate": 4.514296613204532e-05,
      "loss": 0.5472,
      "step": 73
    },
    {
      "epoch": 0.037237388350735943,
      "grad_norm": 0.25575271248817444,
      "learning_rate": 4.471270511491525e-05,
      "loss": 0.5878,
      "step": 74
    },
    {
      "epoch": 0.03774059630142156,
      "grad_norm": 0.266168475151062,
      "learning_rate": 4.427842179111221e-05,
      "loss": 0.5504,
      "step": 75
    },
    {
      "epoch": 0.03824380425210718,
      "grad_norm": 0.28042110800743103,
      "learning_rate": 4.3840234889360634e-05,
      "loss": 0.552,
      "step": 76
    },
    {
      "epoch": 0.0387470122027928,
      "grad_norm": 0.280648797750473,
      "learning_rate": 4.33982642055842e-05,
      "loss": 0.5441,
      "step": 77
    },
    {
      "epoch": 0.03925022015347843,
      "grad_norm": 0.30172908306121826,
      "learning_rate": 4.2952630570154785e-05,
      "loss": 0.5446,
      "step": 78
    },
    {
      "epoch": 0.039753428104164046,
      "grad_norm": 0.307185560464859,
      "learning_rate": 4.250345581485871e-05,
      "loss": 0.5098,
      "step": 79
    },
    {
      "epoch": 0.040256636054849665,
      "grad_norm": 0.2987576425075531,
      "learning_rate": 4.205086273958909e-05,
      "loss": 0.617,
      "step": 80
    },
    {
      "epoch": 0.04075984400553529,
      "grad_norm": 0.33857035636901855,
      "learning_rate": 4.1594975078773565e-05,
      "loss": 0.5953,
      "step": 81
    },
    {
      "epoch": 0.04126305195622091,
      "grad_norm": 0.32701051235198975,
      "learning_rate": 4.113591746754662e-05,
      "loss": 0.5831,
      "step": 82
    },
    {
      "epoch": 0.04176625990690653,
      "grad_norm": 0.348977267742157,
      "learning_rate": 4.06738154076755e-05,
      "loss": 0.6561,
      "step": 83
    },
    {
      "epoch": 0.04226946785759215,
      "grad_norm": 0.34455883502960205,
      "learning_rate": 4.020879523324929e-05,
      "loss": 0.5913,
      "step": 84
    },
    {
      "epoch": 0.042772675808277774,
      "grad_norm": 0.3653380274772644,
      "learning_rate": 3.974098407614051e-05,
      "loss": 0.5919,
      "step": 85
    },
    {
      "epoch": 0.04327588375896339,
      "grad_norm": 0.34481897950172424,
      "learning_rate": 3.927050983124842e-05,
      "loss": 0.5184,
      "step": 86
    },
    {
      "epoch": 0.04377909170964901,
      "grad_norm": 0.39044079184532166,
      "learning_rate": 3.8797501121533946e-05,
      "loss": 0.5558,
      "step": 87
    },
    {
      "epoch": 0.04428229966033463,
      "grad_norm": 0.39954426884651184,
      "learning_rate": 3.832208726285534e-05,
      "loss": 0.5965,
      "step": 88
    },
    {
      "epoch": 0.04478550761102026,
      "grad_norm": 0.39517641067504883,
      "learning_rate": 3.784439822861459e-05,
      "loss": 0.6189,
      "step": 89
    },
    {
      "epoch": 0.045288715561705876,
      "grad_norm": 0.4464763402938843,
      "learning_rate": 3.7364564614223976e-05,
      "loss": 0.6486,
      "step": 90
    },
    {
      "epoch": 0.045791923512391496,
      "grad_norm": 0.38363519310951233,
      "learning_rate": 3.688271760140255e-05,
      "loss": 0.6086,
      "step": 91
    },
    {
      "epoch": 0.046295131463077115,
      "grad_norm": 0.46449124813079834,
      "learning_rate": 3.6398988922312406e-05,
      "loss": 0.6679,
      "step": 92
    },
    {
      "epoch": 0.04679833941376274,
      "grad_norm": 0.5523172616958618,
      "learning_rate": 3.591351082354441e-05,
      "loss": 0.6837,
      "step": 93
    },
    {
      "epoch": 0.04730154736444836,
      "grad_norm": 0.5623148083686829,
      "learning_rate": 3.54264160299633e-05,
      "loss": 0.6155,
      "step": 94
    },
    {
      "epoch": 0.04780475531513398,
      "grad_norm": 0.5504065155982971,
      "learning_rate": 3.493783770842202e-05,
      "loss": 0.7059,
      "step": 95
    },
    {
      "epoch": 0.0483079632658196,
      "grad_norm": 0.6645230650901794,
      "learning_rate": 3.444790943135526e-05,
      "loss": 0.9868,
      "step": 96
    },
    {
      "epoch": 0.048811171216505224,
      "grad_norm": 0.611153781414032,
      "learning_rate": 3.3956765140262074e-05,
      "loss": 0.7392,
      "step": 97
    },
    {
      "epoch": 0.04931437916719084,
      "grad_norm": 0.814527153968811,
      "learning_rate": 3.346453910908759e-05,
      "loss": 0.9215,
      "step": 98
    },
    {
      "epoch": 0.04981758711787646,
      "grad_norm": 0.7997450828552246,
      "learning_rate": 3.297136590751389e-05,
      "loss": 0.8145,
      "step": 99
    },
    {
      "epoch": 0.05032079506856208,
      "grad_norm": 1.5503517389297485,
      "learning_rate": 3.247738036416998e-05,
      "loss": 0.6772,
      "step": 100
    },
    {
      "epoch": 0.05032079506856208,
      "eval_loss": 0.5783679485321045,
      "eval_runtime": 254.195,
      "eval_samples_per_second": 13.167,
      "eval_steps_per_second": 3.293,
      "step": 100
    },
    {
      "epoch": 0.05082400301924771,
      "grad_norm": 0.18010476231575012,
      "learning_rate": 3.1982717529770985e-05,
      "loss": 0.5,
      "step": 101
    },
    {
      "epoch": 0.051327210969933326,
      "grad_norm": 0.22267109155654907,
      "learning_rate": 3.148751264019667e-05,
      "loss": 0.3969,
      "step": 102
    },
    {
      "epoch": 0.051830418920618945,
      "grad_norm": 0.1962970346212387,
      "learning_rate": 3.099190107951924e-05,
      "loss": 0.4625,
      "step": 103
    },
    {
      "epoch": 0.052333626871304564,
      "grad_norm": 0.15853288769721985,
      "learning_rate": 3.049601834299076e-05,
      "loss": 0.3765,
      "step": 104
    },
    {
      "epoch": 0.05283683482199019,
      "grad_norm": 0.19093449413776398,
      "learning_rate": 3e-05,
      "loss": 0.4571,
      "step": 105
    },
    {
      "epoch": 0.05334004277267581,
      "grad_norm": 0.2059127241373062,
      "learning_rate": 2.9503981657009246e-05,
      "loss": 0.4567,
      "step": 106
    },
    {
      "epoch": 0.05384325072336143,
      "grad_norm": 0.20610228180885315,
      "learning_rate": 2.9008098920480752e-05,
      "loss": 0.4818,
      "step": 107
    },
    {
      "epoch": 0.05434645867404705,
      "grad_norm": 0.23367397487163544,
      "learning_rate": 2.851248735980333e-05,
      "loss": 0.5348,
      "step": 108
    },
    {
      "epoch": 0.054849666624732674,
      "grad_norm": 0.22638417780399323,
      "learning_rate": 2.801728247022902e-05,
      "loss": 0.5071,
      "step": 109
    },
    {
      "epoch": 0.05535287457541829,
      "grad_norm": 0.20274679362773895,
      "learning_rate": 2.7522619635830034e-05,
      "loss": 0.5044,
      "step": 110
    },
    {
      "epoch": 0.05585608252610391,
      "grad_norm": 0.2186352163553238,
      "learning_rate": 2.702863409248612e-05,
      "loss": 0.5595,
      "step": 111
    },
    {
      "epoch": 0.05635929047678953,
      "grad_norm": 0.20844176411628723,
      "learning_rate": 2.6535460890912416e-05,
      "loss": 0.5094,
      "step": 112
    },
    {
      "epoch": 0.05686249842747516,
      "grad_norm": 0.22327400743961334,
      "learning_rate": 2.604323485973793e-05,
      "loss": 0.5239,
      "step": 113
    },
    {
      "epoch": 0.057365706378160776,
      "grad_norm": 0.23537015914916992,
      "learning_rate": 2.555209056864474e-05,
      "loss": 0.5821,
      "step": 114
    },
    {
      "epoch": 0.057868914328846395,
      "grad_norm": 0.24699418246746063,
      "learning_rate": 2.5062162291577978e-05,
      "loss": 0.6081,
      "step": 115
    },
    {
      "epoch": 0.058372122279532014,
      "grad_norm": 0.2425052374601364,
      "learning_rate": 2.4573583970036712e-05,
      "loss": 0.5266,
      "step": 116
    },
    {
      "epoch": 0.05887533023021764,
      "grad_norm": 0.24295969307422638,
      "learning_rate": 2.4086489176455595e-05,
      "loss": 0.5312,
      "step": 117
    },
    {
      "epoch": 0.05937853818090326,
      "grad_norm": 0.2615973651409149,
      "learning_rate": 2.36010110776876e-05,
      "loss": 0.5429,
      "step": 118
    },
    {
      "epoch": 0.05988174613158888,
      "grad_norm": 0.24734695255756378,
      "learning_rate": 2.3117282398597456e-05,
      "loss": 0.5302,
      "step": 119
    },
    {
      "epoch": 0.0603849540822745,
      "grad_norm": 0.23504269123077393,
      "learning_rate": 2.263543538577603e-05,
      "loss": 0.5405,
      "step": 120
    },
    {
      "epoch": 0.06088816203296012,
      "grad_norm": 0.2592087984085083,
      "learning_rate": 2.215560177138541e-05,
      "loss": 0.5861,
      "step": 121
    },
    {
      "epoch": 0.06139136998364574,
      "grad_norm": 0.2521650493144989,
      "learning_rate": 2.167791273714467e-05,
      "loss": 0.527,
      "step": 122
    },
    {
      "epoch": 0.06189457793433136,
      "grad_norm": 0.25712549686431885,
      "learning_rate": 2.1202498878466062e-05,
      "loss": 0.5457,
      "step": 123
    },
    {
      "epoch": 0.06239778588501698,
      "grad_norm": 0.2880991995334625,
      "learning_rate": 2.072949016875158e-05,
      "loss": 0.5749,
      "step": 124
    },
    {
      "epoch": 0.0629009938357026,
      "grad_norm": 0.27867549657821655,
      "learning_rate": 2.0259015923859498e-05,
      "loss": 0.5011,
      "step": 125
    },
    {
      "epoch": 0.06340420178638823,
      "grad_norm": 0.2826562523841858,
      "learning_rate": 1.979120476675071e-05,
      "loss": 0.5346,
      "step": 126
    },
    {
      "epoch": 0.06390740973707384,
      "grad_norm": 0.2988441586494446,
      "learning_rate": 1.9326184592324503e-05,
      "loss": 0.5603,
      "step": 127
    },
    {
      "epoch": 0.06441061768775946,
      "grad_norm": 0.2898251414299011,
      "learning_rate": 1.8864082532453373e-05,
      "loss": 0.507,
      "step": 128
    },
    {
      "epoch": 0.06491382563844508,
      "grad_norm": 0.32140111923217773,
      "learning_rate": 1.840502492122644e-05,
      "loss": 0.6455,
      "step": 129
    },
    {
      "epoch": 0.0654170335891307,
      "grad_norm": 0.3469868004322052,
      "learning_rate": 1.7949137260410924e-05,
      "loss": 0.5695,
      "step": 130
    },
    {
      "epoch": 0.06592024153981633,
      "grad_norm": 0.3464687168598175,
      "learning_rate": 1.7496544185141295e-05,
      "loss": 0.5572,
      "step": 131
    },
    {
      "epoch": 0.06642344949050195,
      "grad_norm": 0.34423115849494934,
      "learning_rate": 1.7047369429845216e-05,
      "loss": 0.5648,
      "step": 132
    },
    {
      "epoch": 0.06692665744118757,
      "grad_norm": 0.3686448931694031,
      "learning_rate": 1.6601735794415806e-05,
      "loss": 0.6383,
      "step": 133
    },
    {
      "epoch": 0.06742986539187319,
      "grad_norm": 0.384225994348526,
      "learning_rate": 1.615976511063937e-05,
      "loss": 0.6585,
      "step": 134
    },
    {
      "epoch": 0.06793307334255881,
      "grad_norm": 0.3864382207393646,
      "learning_rate": 1.5721578208887793e-05,
      "loss": 0.6614,
      "step": 135
    },
    {
      "epoch": 0.06843628129324443,
      "grad_norm": 0.3584439158439636,
      "learning_rate": 1.5287294885084766e-05,
      "loss": 0.5458,
      "step": 136
    },
    {
      "epoch": 0.06893948924393005,
      "grad_norm": 0.4031902849674225,
      "learning_rate": 1.4857033867954697e-05,
      "loss": 0.5622,
      "step": 137
    },
    {
      "epoch": 0.06944269719461567,
      "grad_norm": 0.39044708013534546,
      "learning_rate": 1.4430912786563554e-05,
      "loss": 0.6072,
      "step": 138
    },
    {
      "epoch": 0.0699459051453013,
      "grad_norm": 0.46195873618125916,
      "learning_rate": 1.4009048138160195e-05,
      "loss": 0.6443,
      "step": 139
    },
    {
      "epoch": 0.07044911309598692,
      "grad_norm": 0.4306737780570984,
      "learning_rate": 1.3591555256327199e-05,
      "loss": 0.6096,
      "step": 140
    },
    {
      "epoch": 0.07095232104667254,
      "grad_norm": 0.48494911193847656,
      "learning_rate": 1.3178548279449822e-05,
      "loss": 0.6201,
      "step": 141
    },
    {
      "epoch": 0.07145552899735816,
      "grad_norm": 0.5814257264137268,
      "learning_rate": 1.2770140119511693e-05,
      "loss": 0.7133,
      "step": 142
    },
    {
      "epoch": 0.07195873694804378,
      "grad_norm": 0.5437437891960144,
      "learning_rate": 1.2366442431225809e-05,
      "loss": 0.6867,
      "step": 143
    },
    {
      "epoch": 0.0724619448987294,
      "grad_norm": 0.5070156455039978,
      "learning_rate": 1.1967565581509248e-05,
      "loss": 0.6195,
      "step": 144
    },
    {
      "epoch": 0.07296515284941502,
      "grad_norm": 0.5307262539863586,
      "learning_rate": 1.1573618619309965e-05,
      "loss": 0.6332,
      "step": 145
    },
    {
      "epoch": 0.07346836080010063,
      "grad_norm": 0.5888293385505676,
      "learning_rate": 1.1184709245793889e-05,
      "loss": 0.6182,
      "step": 146
    },
    {
      "epoch": 0.07397156875078627,
      "grad_norm": 0.7398355007171631,
      "learning_rate": 1.0800943784900502e-05,
      "loss": 0.8288,
      "step": 147
    },
    {
      "epoch": 0.07447477670147189,
      "grad_norm": 0.7838959097862244,
      "learning_rate": 1.042242715427494e-05,
      "loss": 0.8208,
      "step": 148
    },
    {
      "epoch": 0.0749779846521575,
      "grad_norm": 0.8182078003883362,
      "learning_rate": 1.004926283658455e-05,
      "loss": 0.8139,
      "step": 149
    },
    {
      "epoch": 0.07548119260284313,
      "grad_norm": 1.063940167427063,
      "learning_rate": 9.681552851227774e-06,
      "loss": 0.73,
      "step": 150
    },
    {
      "epoch": 0.07548119260284313,
      "eval_loss": 0.5688919425010681,
      "eval_runtime": 254.4571,
      "eval_samples_per_second": 13.153,
      "eval_steps_per_second": 3.289,
      "step": 150
    },
    {
      "epoch": 0.07598440055352874,
      "grad_norm": 0.15580938756465912,
      "learning_rate": 9.319397726443026e-06,
      "loss": 0.3906,
      "step": 151
    },
    {
      "epoch": 0.07648760850421436,
      "grad_norm": 0.1713186800479889,
      "learning_rate": 8.962896471825342e-06,
      "loss": 0.3607,
      "step": 152
    },
    {
      "epoch": 0.07699081645489998,
      "grad_norm": 0.14851051568984985,
      "learning_rate": 8.61214655125809e-06,
      "loss": 0.3026,
      "step": 153
    },
    {
      "epoch": 0.0774940244055856,
      "grad_norm": 0.16961897909641266,
      "learning_rate": 8.267243856267331e-06,
      "loss": 0.4263,
      "step": 154
    },
    {
      "epoch": 0.07799723235627123,
      "grad_norm": 0.16877688467502594,
      "learning_rate": 7.928282679806052e-06,
      "loss": 0.4287,
      "step": 155
    },
    {
      "epoch": 0.07850044030695685,
      "grad_norm": 0.18662862479686737,
      "learning_rate": 7.595355690475393e-06,
      "loss": 0.441,
      "step": 156
    },
    {
      "epoch": 0.07900364825764247,
      "grad_norm": 0.18855053186416626,
      "learning_rate": 7.268553907189964e-06,
      "loss": 0.4605,
      "step": 157
    },
    {
      "epoch": 0.07950685620832809,
      "grad_norm": 0.1952023059129715,
      "learning_rate": 6.947966674294236e-06,
      "loss": 0.4671,
      "step": 158
    },
    {
      "epoch": 0.08001006415901371,
      "grad_norm": 0.21269835531711578,
      "learning_rate": 6.6336816371366305e-06,
      "loss": 0.4806,
      "step": 159
    },
    {
      "epoch": 0.08051327210969933,
      "grad_norm": 0.25548070669174194,
      "learning_rate": 6.325784718108196e-06,
      "loss": 0.5457,
      "step": 160
    },
    {
      "epoch": 0.08101648006038495,
      "grad_norm": 0.1886155754327774,
      "learning_rate": 6.0243600931522595e-06,
      "loss": 0.4731,
      "step": 161
    },
    {
      "epoch": 0.08151968801107058,
      "grad_norm": 0.25480321049690247,
      "learning_rate": 5.72949016875158e-06,
      "loss": 0.5558,
      "step": 162
    },
    {
      "epoch": 0.0820228959617562,
      "grad_norm": 0.21774064004421234,
      "learning_rate": 5.44125555939923e-06,
      "loss": 0.4662,
      "step": 163
    },
    {
      "epoch": 0.08252610391244182,
      "grad_norm": 0.2598278224468231,
      "learning_rate": 5.159735065559399e-06,
      "loss": 0.5068,
      "step": 164
    },
    {
      "epoch": 0.08302931186312744,
      "grad_norm": 0.23235322535037994,
      "learning_rate": 4.885005652124144e-06,
      "loss": 0.5284,
      "step": 165
    },
    {
      "epoch": 0.08353251981381306,
      "grad_norm": 0.24846144020557404,
      "learning_rate": 4.617142427371934e-06,
      "loss": 0.528,
      "step": 166
    },
    {
      "epoch": 0.08403572776449868,
      "grad_norm": 0.2524101436138153,
      "learning_rate": 4.3562186224338265e-06,
      "loss": 0.5393,
      "step": 167
    },
    {
      "epoch": 0.0845389357151843,
      "grad_norm": 0.27268919348716736,
      "learning_rate": 4.102305571272783e-06,
      "loss": 0.5399,
      "step": 168
    },
    {
      "epoch": 0.08504214366586992,
      "grad_norm": 0.27849826216697693,
      "learning_rate": 3.855472691181678e-06,
      "loss": 0.5982,
      "step": 169
    },
    {
      "epoch": 0.08554535161655555,
      "grad_norm": 0.25703251361846924,
      "learning_rate": 3.615787463805331e-06,
      "loss": 0.536,
      "step": 170
    },
    {
      "epoch": 0.08604855956724117,
      "grad_norm": 0.2339390069246292,
      "learning_rate": 3.383315416691646e-06,
      "loss": 0.4956,
      "step": 171
    },
    {
      "epoch": 0.08655176751792679,
      "grad_norm": 0.24889124929904938,
      "learning_rate": 3.158120105377096e-06,
      "loss": 0.5069,
      "step": 172
    },
    {
      "epoch": 0.0870549754686124,
      "grad_norm": 0.31317636370658875,
      "learning_rate": 2.940263096011233e-06,
      "loss": 0.5525,
      "step": 173
    },
    {
      "epoch": 0.08755818341929802,
      "grad_norm": 0.2804161012172699,
      "learning_rate": 2.729803948525125e-06,
      "loss": 0.5245,
      "step": 174
    },
    {
      "epoch": 0.08806139136998364,
      "grad_norm": 0.27213919162750244,
      "learning_rate": 2.526800200348275e-06,
      "loss": 0.5107,
      "step": 175
    },
    {
      "epoch": 0.08856459932066926,
      "grad_norm": 0.3125113844871521,
      "learning_rate": 2.3313073506784575e-06,
      "loss": 0.5916,
      "step": 176
    },
    {
      "epoch": 0.08906780727135488,
      "grad_norm": 0.2948758006095886,
      "learning_rate": 2.143378845308791e-06,
      "loss": 0.5938,
      "step": 177
    },
    {
      "epoch": 0.08957101522204051,
      "grad_norm": 0.29406407475471497,
      "learning_rate": 1.9630660620161777e-06,
      "loss": 0.5673,
      "step": 178
    },
    {
      "epoch": 0.09007422317272613,
      "grad_norm": 0.2734048366546631,
      "learning_rate": 1.790418296515165e-06,
      "loss": 0.4739,
      "step": 179
    },
    {
      "epoch": 0.09057743112341175,
      "grad_norm": 0.3486558198928833,
      "learning_rate": 1.625482748980961e-06,
      "loss": 0.6841,
      "step": 180
    },
    {
      "epoch": 0.09108063907409737,
      "grad_norm": 0.3210769593715668,
      "learning_rate": 1.4683045111453942e-06,
      "loss": 0.5371,
      "step": 181
    },
    {
      "epoch": 0.09158384702478299,
      "grad_norm": 0.31035321950912476,
      "learning_rate": 1.3189265539692707e-06,
      "loss": 0.6067,
      "step": 182
    },
    {
      "epoch": 0.09208705497546861,
      "grad_norm": 0.31384459137916565,
      "learning_rate": 1.1773897158945557e-06,
      "loss": 0.5278,
      "step": 183
    },
    {
      "epoch": 0.09259026292615423,
      "grad_norm": 0.3650054335594177,
      "learning_rate": 1.0437326916795432e-06,
      "loss": 0.577,
      "step": 184
    },
    {
      "epoch": 0.09309347087683985,
      "grad_norm": 0.38539010286331177,
      "learning_rate": 9.179920218200888e-07,
      "loss": 0.5645,
      "step": 185
    },
    {
      "epoch": 0.09359667882752548,
      "grad_norm": 0.39987921714782715,
      "learning_rate": 8.002020825598277e-07,
      "loss": 0.5572,
      "step": 186
    },
    {
      "epoch": 0.0940998867782111,
      "grad_norm": 0.4194090664386749,
      "learning_rate": 6.90395076492022e-07,
      "loss": 0.5343,
      "step": 187
    },
    {
      "epoch": 0.09460309472889672,
      "grad_norm": 0.4510478675365448,
      "learning_rate": 5.886010237557194e-07,
      "loss": 0.6081,
      "step": 188
    },
    {
      "epoch": 0.09510630267958234,
      "grad_norm": 0.4582996666431427,
      "learning_rate": 4.94847753828529e-07,
      "loss": 0.563,
      "step": 189
    },
    {
      "epoch": 0.09560951063026796,
      "grad_norm": 0.4537375569343567,
      "learning_rate": 4.091608979183303e-07,
      "loss": 0.5794,
      "step": 190
    },
    {
      "epoch": 0.09611271858095358,
      "grad_norm": 0.5008410215377808,
      "learning_rate": 3.315638819559452e-07,
      "loss": 0.6695,
      "step": 191
    },
    {
      "epoch": 0.0966159265316392,
      "grad_norm": 0.465094655752182,
      "learning_rate": 2.6207792019074414e-07,
      "loss": 0.5689,
      "step": 192
    },
    {
      "epoch": 0.09711913448232481,
      "grad_norm": 0.5791743993759155,
      "learning_rate": 2.0072200939085573e-07,
      "loss": 0.6526,
      "step": 193
    },
    {
      "epoch": 0.09762234243301045,
      "grad_norm": 0.5798547267913818,
      "learning_rate": 1.475129236496575e-07,
      "loss": 0.7114,
      "step": 194
    },
    {
      "epoch": 0.09812555038369607,
      "grad_norm": 0.5288845300674438,
      "learning_rate": 1.0246520979990459e-07,
      "loss": 0.5862,
      "step": 195
    },
    {
      "epoch": 0.09862875833438169,
      "grad_norm": 0.603554368019104,
      "learning_rate": 6.559118343676396e-08,
      "loss": 0.6302,
      "step": 196
    },
    {
      "epoch": 0.0991319662850673,
      "grad_norm": 0.7485440969467163,
      "learning_rate": 3.690092555085789e-08,
      "loss": 0.8085,
      "step": 197
    },
    {
      "epoch": 0.09963517423575292,
      "grad_norm": 0.6907915472984314,
      "learning_rate": 1.640227977221853e-08,
      "loss": 0.7443,
      "step": 198
    },
    {
      "epoch": 0.10013838218643854,
      "grad_norm": 0.9386430382728577,
      "learning_rate": 4.1008502259298755e-09,
      "loss": 0.8441,
      "step": 199
    },
    {
      "epoch": 0.10064159013712416,
      "grad_norm": 1.2875903844833374,
      "learning_rate": 0.0,
      "loss": 0.8794,
      "step": 200
    },
    {
      "epoch": 0.10064159013712416,
      "eval_loss": 0.5652009844779968,
      "eval_runtime": 254.6485,
      "eval_samples_per_second": 13.144,
      "eval_steps_per_second": 3.287,
      "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": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.985966239219712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}