{
  "best_metric": 0.5063894391059875,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.07582938388625593,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003791469194312796,
      "grad_norm": 2.3607397079467773,
      "learning_rate": 6e-06,
      "loss": 2.3674,
      "step": 1
    },
    {
      "epoch": 0.0003791469194312796,
      "eval_loss": 1.6981829404830933,
      "eval_runtime": 342.6691,
      "eval_samples_per_second": 12.963,
      "eval_steps_per_second": 3.242,
      "step": 1
    },
    {
      "epoch": 0.0007582938388625592,
      "grad_norm": 2.2280433177948,
      "learning_rate": 1.2e-05,
      "loss": 1.7743,
      "step": 2
    },
    {
      "epoch": 0.001137440758293839,
      "grad_norm": 2.1979401111602783,
      "learning_rate": 1.8e-05,
      "loss": 1.7584,
      "step": 3
    },
    {
      "epoch": 0.0015165876777251184,
      "grad_norm": 2.395792245864868,
      "learning_rate": 2.4e-05,
      "loss": 1.7522,
      "step": 4
    },
    {
      "epoch": 0.0018957345971563982,
      "grad_norm": 2.4676456451416016,
      "learning_rate": 3e-05,
      "loss": 1.6792,
      "step": 5
    },
    {
      "epoch": 0.002274881516587678,
      "grad_norm": 1.9544316530227661,
      "learning_rate": 3.6e-05,
      "loss": 1.5587,
      "step": 6
    },
    {
      "epoch": 0.002654028436018957,
      "grad_norm": 1.9189141988754272,
      "learning_rate": 4.2e-05,
      "loss": 1.5178,
      "step": 7
    },
    {
      "epoch": 0.003033175355450237,
      "grad_norm": 1.8870714902877808,
      "learning_rate": 4.8e-05,
      "loss": 1.4159,
      "step": 8
    },
    {
      "epoch": 0.0034123222748815166,
      "grad_norm": 2.4351065158843994,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.297,
      "step": 9
    },
    {
      "epoch": 0.0037914691943127963,
      "grad_norm": 2.2076759338378906,
      "learning_rate": 6e-05,
      "loss": 1.1759,
      "step": 10
    },
    {
      "epoch": 0.004170616113744076,
      "grad_norm": 1.7516471147537231,
      "learning_rate": 5.999589914977407e-05,
      "loss": 1.1303,
      "step": 11
    },
    {
      "epoch": 0.004549763033175356,
      "grad_norm": 1.5598973035812378,
      "learning_rate": 5.998359772022778e-05,
      "loss": 0.9447,
      "step": 12
    },
    {
      "epoch": 0.0049289099526066355,
      "grad_norm": 1.4637537002563477,
      "learning_rate": 5.996309907444915e-05,
      "loss": 0.9049,
      "step": 13
    },
    {
      "epoch": 0.005308056872037914,
      "grad_norm": 1.9019067287445068,
      "learning_rate": 5.9934408816563236e-05,
      "loss": 0.8778,
      "step": 14
    },
    {
      "epoch": 0.005687203791469194,
      "grad_norm": 1.5424095392227173,
      "learning_rate": 5.98975347902001e-05,
      "loss": 0.8591,
      "step": 15
    },
    {
      "epoch": 0.006066350710900474,
      "grad_norm": 1.3776594400405884,
      "learning_rate": 5.9852487076350345e-05,
      "loss": 0.7328,
      "step": 16
    },
    {
      "epoch": 0.0064454976303317535,
      "grad_norm": 1.3162641525268555,
      "learning_rate": 5.979927799060915e-05,
      "loss": 0.7089,
      "step": 17
    },
    {
      "epoch": 0.006824644549763033,
      "grad_norm": 1.2267054319381714,
      "learning_rate": 5.9737922079809257e-05,
      "loss": 0.7679,
      "step": 18
    },
    {
      "epoch": 0.007203791469194313,
      "grad_norm": 1.1532204151153564,
      "learning_rate": 5.9668436118044054e-05,
      "loss": 0.7228,
      "step": 19
    },
    {
      "epoch": 0.007582938388625593,
      "grad_norm": 1.3049921989440918,
      "learning_rate": 5.959083910208167e-05,
      "loss": 0.7155,
      "step": 20
    },
    {
      "epoch": 0.007962085308056872,
      "grad_norm": 1.3345766067504883,
      "learning_rate": 5.9505152246171474e-05,
      "loss": 0.7048,
      "step": 21
    },
    {
      "epoch": 0.008341232227488152,
      "grad_norm": 1.353661060333252,
      "learning_rate": 5.941139897624428e-05,
      "loss": 0.77,
      "step": 22
    },
    {
      "epoch": 0.008720379146919432,
      "grad_norm": 1.2893695831298828,
      "learning_rate": 5.9309604923507984e-05,
      "loss": 0.7045,
      "step": 23
    },
    {
      "epoch": 0.009099526066350712,
      "grad_norm": 1.139123558998108,
      "learning_rate": 5.9199797917440176e-05,
      "loss": 0.6403,
      "step": 24
    },
    {
      "epoch": 0.009478672985781991,
      "grad_norm": 1.1754416227340698,
      "learning_rate": 5.908200797817991e-05,
      "loss": 0.6316,
      "step": 25
    },
    {
      "epoch": 0.009857819905213271,
      "grad_norm": 1.3844693899154663,
      "learning_rate": 5.895626730832046e-05,
      "loss": 0.6302,
      "step": 26
    },
    {
      "epoch": 0.010236966824644549,
      "grad_norm": 1.0756479501724243,
      "learning_rate": 5.882261028410545e-05,
      "loss": 0.5767,
      "step": 27
    },
    {
      "epoch": 0.010616113744075829,
      "grad_norm": 1.1990379095077515,
      "learning_rate": 5.8681073446030734e-05,
      "loss": 0.5942,
      "step": 28
    },
    {
      "epoch": 0.010995260663507108,
      "grad_norm": 1.2510521411895752,
      "learning_rate": 5.853169548885461e-05,
      "loss": 0.6293,
      "step": 29
    },
    {
      "epoch": 0.011374407582938388,
      "grad_norm": 1.0987434387207031,
      "learning_rate": 5.8374517251019035e-05,
      "loss": 0.5444,
      "step": 30
    },
    {
      "epoch": 0.011753554502369668,
      "grad_norm": 0.9962146878242493,
      "learning_rate": 5.820958170348484e-05,
      "loss": 0.5284,
      "step": 31
    },
    {
      "epoch": 0.012132701421800948,
      "grad_norm": 1.1842890977859497,
      "learning_rate": 5.8036933937983825e-05,
      "loss": 0.5764,
      "step": 32
    },
    {
      "epoch": 0.012511848341232227,
      "grad_norm": 1.1667747497558594,
      "learning_rate": 5.7856621154691217e-05,
      "loss": 0.6086,
      "step": 33
    },
    {
      "epoch": 0.012890995260663507,
      "grad_norm": 1.1322537660598755,
      "learning_rate": 5.766869264932154e-05,
      "loss": 0.5379,
      "step": 34
    },
    {
      "epoch": 0.013270142180094787,
      "grad_norm": 1.07042396068573,
      "learning_rate": 5.747319979965172e-05,
      "loss": 0.5195,
      "step": 35
    },
    {
      "epoch": 0.013649289099526066,
      "grad_norm": 1.023470163345337,
      "learning_rate": 5.727019605147488e-05,
      "loss": 0.543,
      "step": 36
    },
    {
      "epoch": 0.014028436018957346,
      "grad_norm": 1.1579279899597168,
      "learning_rate": 5.7059736903988775e-05,
      "loss": 0.5042,
      "step": 37
    },
    {
      "epoch": 0.014407582938388626,
      "grad_norm": 1.0734813213348389,
      "learning_rate": 5.684187989462291e-05,
      "loss": 0.5276,
      "step": 38
    },
    {
      "epoch": 0.014786729857819906,
      "grad_norm": 1.0260837078094482,
      "learning_rate": 5.661668458330836e-05,
      "loss": 0.4359,
      "step": 39
    },
    {
      "epoch": 0.015165876777251185,
      "grad_norm": 0.9480069279670715,
      "learning_rate": 5.638421253619467e-05,
      "loss": 0.437,
      "step": 40
    },
    {
      "epoch": 0.015545023696682465,
      "grad_norm": 1.0021203756332397,
      "learning_rate": 5.614452730881832e-05,
      "loss": 0.487,
      "step": 41
    },
    {
      "epoch": 0.015924170616113745,
      "grad_norm": 0.9898553490638733,
      "learning_rate": 5.589769442872722e-05,
      "loss": 0.4045,
      "step": 42
    },
    {
      "epoch": 0.016303317535545023,
      "grad_norm": 1.1742738485336304,
      "learning_rate": 5.5643781377566175e-05,
      "loss": 0.4673,
      "step": 43
    },
    {
      "epoch": 0.016682464454976304,
      "grad_norm": 1.0911322832107544,
      "learning_rate": 5.538285757262806e-05,
      "loss": 0.4501,
      "step": 44
    },
    {
      "epoch": 0.017061611374407582,
      "grad_norm": 1.2655229568481445,
      "learning_rate": 5.5114994347875856e-05,
      "loss": 0.4084,
      "step": 45
    },
    {
      "epoch": 0.017440758293838864,
      "grad_norm": 1.3887434005737305,
      "learning_rate": 5.48402649344406e-05,
      "loss": 0.3981,
      "step": 46
    },
    {
      "epoch": 0.01781990521327014,
      "grad_norm": 1.1302635669708252,
      "learning_rate": 5.455874444060078e-05,
      "loss": 0.4061,
      "step": 47
    },
    {
      "epoch": 0.018199052132701423,
      "grad_norm": 0.8546876907348633,
      "learning_rate": 5.427050983124843e-05,
      "loss": 0.3365,
      "step": 48
    },
    {
      "epoch": 0.0185781990521327,
      "grad_norm": 0.8889405727386475,
      "learning_rate": 5.397563990684774e-05,
      "loss": 0.2457,
      "step": 49
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 0.9020243883132935,
      "learning_rate": 5.367421528189181e-05,
      "loss": 0.2258,
      "step": 50
    },
    {
      "epoch": 0.018957345971563982,
      "eval_loss": 0.6159882545471191,
      "eval_runtime": 344.9982,
      "eval_samples_per_second": 12.875,
      "eval_steps_per_second": 3.22,
      "step": 50
    },
    {
      "epoch": 0.01933649289099526,
      "grad_norm": 2.4133408069610596,
      "learning_rate": 5.336631836286338e-05,
      "loss": 1.5293,
      "step": 51
    },
    {
      "epoch": 0.019715639810426542,
      "grad_norm": 1.7940583229064941,
      "learning_rate": 5.3052033325705774e-05,
      "loss": 0.8329,
      "step": 52
    },
    {
      "epoch": 0.02009478672985782,
      "grad_norm": 1.4519822597503662,
      "learning_rate": 5.2731446092810044e-05,
      "loss": 0.7793,
      "step": 53
    },
    {
      "epoch": 0.020473933649289098,
      "grad_norm": 1.110809326171875,
      "learning_rate": 5.240464430952462e-05,
      "loss": 0.7678,
      "step": 54
    },
    {
      "epoch": 0.02085308056872038,
      "grad_norm": 1.0020638704299927,
      "learning_rate": 5.207171732019395e-05,
      "loss": 0.7016,
      "step": 55
    },
    {
      "epoch": 0.021232227488151657,
      "grad_norm": 1.0127681493759155,
      "learning_rate": 5.1732756143732675e-05,
      "loss": 0.6799,
      "step": 56
    },
    {
      "epoch": 0.02161137440758294,
      "grad_norm": 1.004103422164917,
      "learning_rate": 5.1387853448741916e-05,
      "loss": 0.7143,
      "step": 57
    },
    {
      "epoch": 0.021990521327014217,
      "grad_norm": 1.1212753057479858,
      "learning_rate": 5.103710352817465e-05,
      "loss": 0.6442,
      "step": 58
    },
    {
      "epoch": 0.022369668246445498,
      "grad_norm": 1.13973069190979,
      "learning_rate": 5.068060227355698e-05,
      "loss": 0.7217,
      "step": 59
    },
    {
      "epoch": 0.022748815165876776,
      "grad_norm": 1.1548775434494019,
      "learning_rate": 5.0318447148772234e-05,
      "loss": 0.708,
      "step": 60
    },
    {
      "epoch": 0.023127962085308058,
      "grad_norm": 1.039237380027771,
      "learning_rate": 4.995073716341545e-05,
      "loss": 0.6506,
      "step": 61
    },
    {
      "epoch": 0.023507109004739336,
      "grad_norm": 1.0963629484176636,
      "learning_rate": 4.957757284572506e-05,
      "loss": 0.6685,
      "step": 62
    },
    {
      "epoch": 0.023886255924170617,
      "grad_norm": 1.0616074800491333,
      "learning_rate": 4.91990562150995e-05,
      "loss": 0.6461,
      "step": 63
    },
    {
      "epoch": 0.024265402843601895,
      "grad_norm": 1.0263690948486328,
      "learning_rate": 4.881529075420611e-05,
      "loss": 0.5949,
      "step": 64
    },
    {
      "epoch": 0.024644549763033177,
      "grad_norm": 1.1550185680389404,
      "learning_rate": 4.8426381380690036e-05,
      "loss": 0.6779,
      "step": 65
    },
    {
      "epoch": 0.025023696682464455,
      "grad_norm": 0.9933828115463257,
      "learning_rate": 4.8032434418490753e-05,
      "loss": 0.6456,
      "step": 66
    },
    {
      "epoch": 0.025402843601895736,
      "grad_norm": 1.00188410282135,
      "learning_rate": 4.7633557568774194e-05,
      "loss": 0.6354,
      "step": 67
    },
    {
      "epoch": 0.025781990521327014,
      "grad_norm": 1.0373916625976562,
      "learning_rate": 4.722985988048831e-05,
      "loss": 0.6082,
      "step": 68
    },
    {
      "epoch": 0.026161137440758295,
      "grad_norm": 0.9275899529457092,
      "learning_rate": 4.6821451720550184e-05,
      "loss": 0.6274,
      "step": 69
    },
    {
      "epoch": 0.026540284360189573,
      "grad_norm": 0.9165945649147034,
      "learning_rate": 4.640844474367282e-05,
      "loss": 0.6005,
      "step": 70
    },
    {
      "epoch": 0.02691943127962085,
      "grad_norm": 0.9279446601867676,
      "learning_rate": 4.5990951861839815e-05,
      "loss": 0.5644,
      "step": 71
    },
    {
      "epoch": 0.027298578199052133,
      "grad_norm": 0.856342077255249,
      "learning_rate": 4.5569087213436455e-05,
      "loss": 0.5951,
      "step": 72
    },
    {
      "epoch": 0.02767772511848341,
      "grad_norm": 0.95192950963974,
      "learning_rate": 4.514296613204532e-05,
      "loss": 0.5506,
      "step": 73
    },
    {
      "epoch": 0.028056872037914692,
      "grad_norm": 1.0360265970230103,
      "learning_rate": 4.471270511491525e-05,
      "loss": 0.64,
      "step": 74
    },
    {
      "epoch": 0.02843601895734597,
      "grad_norm": 0.9761951565742493,
      "learning_rate": 4.427842179111221e-05,
      "loss": 0.5912,
      "step": 75
    },
    {
      "epoch": 0.02881516587677725,
      "grad_norm": 0.8985703587532043,
      "learning_rate": 4.3840234889360634e-05,
      "loss": 0.5406,
      "step": 76
    },
    {
      "epoch": 0.02919431279620853,
      "grad_norm": 0.9850453734397888,
      "learning_rate": 4.33982642055842e-05,
      "loss": 0.6044,
      "step": 77
    },
    {
      "epoch": 0.02957345971563981,
      "grad_norm": 0.9527453184127808,
      "learning_rate": 4.2952630570154785e-05,
      "loss": 0.5498,
      "step": 78
    },
    {
      "epoch": 0.02995260663507109,
      "grad_norm": 0.8898606300354004,
      "learning_rate": 4.250345581485871e-05,
      "loss": 0.498,
      "step": 79
    },
    {
      "epoch": 0.03033175355450237,
      "grad_norm": 1.0251396894454956,
      "learning_rate": 4.205086273958909e-05,
      "loss": 0.5551,
      "step": 80
    },
    {
      "epoch": 0.03071090047393365,
      "grad_norm": 0.9887294173240662,
      "learning_rate": 4.1594975078773565e-05,
      "loss": 0.5348,
      "step": 81
    },
    {
      "epoch": 0.03109004739336493,
      "grad_norm": 0.9571895599365234,
      "learning_rate": 4.113591746754662e-05,
      "loss": 0.5147,
      "step": 82
    },
    {
      "epoch": 0.03146919431279621,
      "grad_norm": 0.8705043792724609,
      "learning_rate": 4.06738154076755e-05,
      "loss": 0.4836,
      "step": 83
    },
    {
      "epoch": 0.03184834123222749,
      "grad_norm": 0.9828000068664551,
      "learning_rate": 4.020879523324929e-05,
      "loss": 0.5008,
      "step": 84
    },
    {
      "epoch": 0.03222748815165877,
      "grad_norm": 0.9241380095481873,
      "learning_rate": 3.974098407614051e-05,
      "loss": 0.4675,
      "step": 85
    },
    {
      "epoch": 0.032606635071090045,
      "grad_norm": 0.9122922420501709,
      "learning_rate": 3.927050983124842e-05,
      "loss": 0.5142,
      "step": 86
    },
    {
      "epoch": 0.03298578199052133,
      "grad_norm": 0.8403096795082092,
      "learning_rate": 3.8797501121533946e-05,
      "loss": 0.4439,
      "step": 87
    },
    {
      "epoch": 0.03336492890995261,
      "grad_norm": 0.910892128944397,
      "learning_rate": 3.832208726285534e-05,
      "loss": 0.4519,
      "step": 88
    },
    {
      "epoch": 0.033744075829383886,
      "grad_norm": 0.9453192353248596,
      "learning_rate": 3.784439822861459e-05,
      "loss": 0.4743,
      "step": 89
    },
    {
      "epoch": 0.034123222748815164,
      "grad_norm": 0.9362481832504272,
      "learning_rate": 3.7364564614223976e-05,
      "loss": 0.4588,
      "step": 90
    },
    {
      "epoch": 0.03450236966824644,
      "grad_norm": 0.8357151746749878,
      "learning_rate": 3.688271760140255e-05,
      "loss": 0.3989,
      "step": 91
    },
    {
      "epoch": 0.03488151658767773,
      "grad_norm": 0.9535480737686157,
      "learning_rate": 3.6398988922312406e-05,
      "loss": 0.4292,
      "step": 92
    },
    {
      "epoch": 0.035260663507109005,
      "grad_norm": 0.8818041086196899,
      "learning_rate": 3.591351082354441e-05,
      "loss": 0.376,
      "step": 93
    },
    {
      "epoch": 0.03563981042654028,
      "grad_norm": 0.9949309229850769,
      "learning_rate": 3.54264160299633e-05,
      "loss": 0.4139,
      "step": 94
    },
    {
      "epoch": 0.03601895734597156,
      "grad_norm": 0.8851547837257385,
      "learning_rate": 3.493783770842202e-05,
      "loss": 0.3293,
      "step": 95
    },
    {
      "epoch": 0.036398104265402846,
      "grad_norm": 0.8010683059692383,
      "learning_rate": 3.444790943135526e-05,
      "loss": 0.3311,
      "step": 96
    },
    {
      "epoch": 0.036777251184834124,
      "grad_norm": 0.7428768873214722,
      "learning_rate": 3.3956765140262074e-05,
      "loss": 0.2844,
      "step": 97
    },
    {
      "epoch": 0.0371563981042654,
      "grad_norm": 0.9548898339271545,
      "learning_rate": 3.346453910908759e-05,
      "loss": 0.376,
      "step": 98
    },
    {
      "epoch": 0.03753554502369668,
      "grad_norm": 1.0641423463821411,
      "learning_rate": 3.297136590751389e-05,
      "loss": 0.3601,
      "step": 99
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 0.7730882167816162,
      "learning_rate": 3.247738036416998e-05,
      "loss": 0.2464,
      "step": 100
    },
    {
      "epoch": 0.037914691943127965,
      "eval_loss": 0.5508739948272705,
      "eval_runtime": 345.5738,
      "eval_samples_per_second": 12.854,
      "eval_steps_per_second": 3.215,
      "step": 100
    },
    {
      "epoch": 0.03829383886255924,
      "grad_norm": 1.8822741508483887,
      "learning_rate": 3.1982717529770985e-05,
      "loss": 1.4074,
      "step": 101
    },
    {
      "epoch": 0.03867298578199052,
      "grad_norm": 1.272026777267456,
      "learning_rate": 3.148751264019667e-05,
      "loss": 0.7856,
      "step": 102
    },
    {
      "epoch": 0.0390521327014218,
      "grad_norm": 1.161899209022522,
      "learning_rate": 3.099190107951924e-05,
      "loss": 0.6956,
      "step": 103
    },
    {
      "epoch": 0.039431279620853084,
      "grad_norm": 1.0137699842453003,
      "learning_rate": 3.049601834299076e-05,
      "loss": 0.6313,
      "step": 104
    },
    {
      "epoch": 0.03981042654028436,
      "grad_norm": 1.0051027536392212,
      "learning_rate": 3e-05,
      "loss": 0.6899,
      "step": 105
    },
    {
      "epoch": 0.04018957345971564,
      "grad_norm": 0.9395660758018494,
      "learning_rate": 2.9503981657009246e-05,
      "loss": 0.6345,
      "step": 106
    },
    {
      "epoch": 0.04056872037914692,
      "grad_norm": 0.8711168766021729,
      "learning_rate": 2.9008098920480752e-05,
      "loss": 0.6447,
      "step": 107
    },
    {
      "epoch": 0.040947867298578196,
      "grad_norm": 1.1823228597640991,
      "learning_rate": 2.851248735980333e-05,
      "loss": 0.663,
      "step": 108
    },
    {
      "epoch": 0.04132701421800948,
      "grad_norm": 0.9468877911567688,
      "learning_rate": 2.801728247022902e-05,
      "loss": 0.6448,
      "step": 109
    },
    {
      "epoch": 0.04170616113744076,
      "grad_norm": 0.8840280175209045,
      "learning_rate": 2.7522619635830034e-05,
      "loss": 0.6168,
      "step": 110
    },
    {
      "epoch": 0.04208530805687204,
      "grad_norm": 0.9660087823867798,
      "learning_rate": 2.702863409248612e-05,
      "loss": 0.6257,
      "step": 111
    },
    {
      "epoch": 0.042464454976303315,
      "grad_norm": 0.9464119076728821,
      "learning_rate": 2.6535460890912416e-05,
      "loss": 0.6864,
      "step": 112
    },
    {
      "epoch": 0.0428436018957346,
      "grad_norm": 1.0040414333343506,
      "learning_rate": 2.604323485973793e-05,
      "loss": 0.6249,
      "step": 113
    },
    {
      "epoch": 0.04322274881516588,
      "grad_norm": 0.9637667536735535,
      "learning_rate": 2.555209056864474e-05,
      "loss": 0.5605,
      "step": 114
    },
    {
      "epoch": 0.043601895734597156,
      "grad_norm": 0.9878002405166626,
      "learning_rate": 2.5062162291577978e-05,
      "loss": 0.536,
      "step": 115
    },
    {
      "epoch": 0.043981042654028434,
      "grad_norm": 1.0215932130813599,
      "learning_rate": 2.4573583970036712e-05,
      "loss": 0.6054,
      "step": 116
    },
    {
      "epoch": 0.04436018957345972,
      "grad_norm": 0.9616793394088745,
      "learning_rate": 2.4086489176455595e-05,
      "loss": 0.5458,
      "step": 117
    },
    {
      "epoch": 0.044739336492890996,
      "grad_norm": 0.9715977311134338,
      "learning_rate": 2.36010110776876e-05,
      "loss": 0.5747,
      "step": 118
    },
    {
      "epoch": 0.045118483412322274,
      "grad_norm": 0.9184060096740723,
      "learning_rate": 2.3117282398597456e-05,
      "loss": 0.5391,
      "step": 119
    },
    {
      "epoch": 0.04549763033175355,
      "grad_norm": 0.9710631370544434,
      "learning_rate": 2.263543538577603e-05,
      "loss": 0.5382,
      "step": 120
    },
    {
      "epoch": 0.04587677725118484,
      "grad_norm": 0.8977413773536682,
      "learning_rate": 2.215560177138541e-05,
      "loss": 0.5466,
      "step": 121
    },
    {
      "epoch": 0.046255924170616115,
      "grad_norm": 0.9749202728271484,
      "learning_rate": 2.167791273714467e-05,
      "loss": 0.5813,
      "step": 122
    },
    {
      "epoch": 0.04663507109004739,
      "grad_norm": 1.0063494443893433,
      "learning_rate": 2.1202498878466062e-05,
      "loss": 0.5904,
      "step": 123
    },
    {
      "epoch": 0.04701421800947867,
      "grad_norm": 1.0267138481140137,
      "learning_rate": 2.072949016875158e-05,
      "loss": 0.5809,
      "step": 124
    },
    {
      "epoch": 0.04739336492890995,
      "grad_norm": 0.916971743106842,
      "learning_rate": 2.0259015923859498e-05,
      "loss": 0.5226,
      "step": 125
    },
    {
      "epoch": 0.047772511848341234,
      "grad_norm": 0.9448188543319702,
      "learning_rate": 1.979120476675071e-05,
      "loss": 0.5503,
      "step": 126
    },
    {
      "epoch": 0.04815165876777251,
      "grad_norm": 0.8960833549499512,
      "learning_rate": 1.9326184592324503e-05,
      "loss": 0.5472,
      "step": 127
    },
    {
      "epoch": 0.04853080568720379,
      "grad_norm": 0.9310248494148254,
      "learning_rate": 1.8864082532453373e-05,
      "loss": 0.554,
      "step": 128
    },
    {
      "epoch": 0.04890995260663507,
      "grad_norm": 0.8872618675231934,
      "learning_rate": 1.840502492122644e-05,
      "loss": 0.5129,
      "step": 129
    },
    {
      "epoch": 0.04928909952606635,
      "grad_norm": 0.9954771399497986,
      "learning_rate": 1.7949137260410924e-05,
      "loss": 0.5348,
      "step": 130
    },
    {
      "epoch": 0.04966824644549763,
      "grad_norm": 0.8588917255401611,
      "learning_rate": 1.7496544185141295e-05,
      "loss": 0.4947,
      "step": 131
    },
    {
      "epoch": 0.05004739336492891,
      "grad_norm": 0.8972111940383911,
      "learning_rate": 1.7047369429845216e-05,
      "loss": 0.5559,
      "step": 132
    },
    {
      "epoch": 0.05042654028436019,
      "grad_norm": 0.8581748008728027,
      "learning_rate": 1.6601735794415806e-05,
      "loss": 0.4764,
      "step": 133
    },
    {
      "epoch": 0.05080568720379147,
      "grad_norm": 0.8218798041343689,
      "learning_rate": 1.615976511063937e-05,
      "loss": 0.4472,
      "step": 134
    },
    {
      "epoch": 0.05118483412322275,
      "grad_norm": 0.8914713859558105,
      "learning_rate": 1.5721578208887793e-05,
      "loss": 0.4507,
      "step": 135
    },
    {
      "epoch": 0.05156398104265403,
      "grad_norm": 0.891606330871582,
      "learning_rate": 1.5287294885084766e-05,
      "loss": 0.4769,
      "step": 136
    },
    {
      "epoch": 0.051943127962085306,
      "grad_norm": 0.9011698365211487,
      "learning_rate": 1.4857033867954697e-05,
      "loss": 0.5192,
      "step": 137
    },
    {
      "epoch": 0.05232227488151659,
      "grad_norm": 0.8463770151138306,
      "learning_rate": 1.4430912786563554e-05,
      "loss": 0.4164,
      "step": 138
    },
    {
      "epoch": 0.05270142180094787,
      "grad_norm": 0.9531325101852417,
      "learning_rate": 1.4009048138160195e-05,
      "loss": 0.4199,
      "step": 139
    },
    {
      "epoch": 0.05308056872037915,
      "grad_norm": 0.8462571501731873,
      "learning_rate": 1.3591555256327199e-05,
      "loss": 0.4274,
      "step": 140
    },
    {
      "epoch": 0.053459715639810425,
      "grad_norm": 0.862342894077301,
      "learning_rate": 1.3178548279449822e-05,
      "loss": 0.3976,
      "step": 141
    },
    {
      "epoch": 0.0538388625592417,
      "grad_norm": 0.7988135814666748,
      "learning_rate": 1.2770140119511693e-05,
      "loss": 0.3224,
      "step": 142
    },
    {
      "epoch": 0.05421800947867299,
      "grad_norm": 0.8891763091087341,
      "learning_rate": 1.2366442431225809e-05,
      "loss": 0.4034,
      "step": 143
    },
    {
      "epoch": 0.054597156398104266,
      "grad_norm": 0.9104804396629333,
      "learning_rate": 1.1967565581509248e-05,
      "loss": 0.3469,
      "step": 144
    },
    {
      "epoch": 0.054976303317535544,
      "grad_norm": 0.8460737466812134,
      "learning_rate": 1.1573618619309965e-05,
      "loss": 0.323,
      "step": 145
    },
    {
      "epoch": 0.05535545023696682,
      "grad_norm": 0.7780117988586426,
      "learning_rate": 1.1184709245793889e-05,
      "loss": 0.2783,
      "step": 146
    },
    {
      "epoch": 0.05573459715639811,
      "grad_norm": 0.8993276357650757,
      "learning_rate": 1.0800943784900502e-05,
      "loss": 0.3748,
      "step": 147
    },
    {
      "epoch": 0.056113744075829385,
      "grad_norm": 0.8467982411384583,
      "learning_rate": 1.042242715427494e-05,
      "loss": 0.2837,
      "step": 148
    },
    {
      "epoch": 0.05649289099526066,
      "grad_norm": 0.8935648202896118,
      "learning_rate": 1.004926283658455e-05,
      "loss": 0.3136,
      "step": 149
    },
    {
      "epoch": 0.05687203791469194,
      "grad_norm": 0.9242781400680542,
      "learning_rate": 9.681552851227774e-06,
      "loss": 0.2324,
      "step": 150
    },
    {
      "epoch": 0.05687203791469194,
      "eval_loss": 0.5187870860099792,
      "eval_runtime": 345.6495,
      "eval_samples_per_second": 12.851,
      "eval_steps_per_second": 3.214,
      "step": 150
    },
    {
      "epoch": 0.057251184834123225,
      "grad_norm": 1.3798567056655884,
      "learning_rate": 9.319397726443026e-06,
      "loss": 1.0638,
      "step": 151
    },
    {
      "epoch": 0.0576303317535545,
      "grad_norm": 1.1334023475646973,
      "learning_rate": 8.962896471825342e-06,
      "loss": 0.6878,
      "step": 152
    },
    {
      "epoch": 0.05800947867298578,
      "grad_norm": 1.0488735437393188,
      "learning_rate": 8.61214655125809e-06,
      "loss": 0.7195,
      "step": 153
    },
    {
      "epoch": 0.05838862559241706,
      "grad_norm": 1.0702718496322632,
      "learning_rate": 8.267243856267331e-06,
      "loss": 0.5706,
      "step": 154
    },
    {
      "epoch": 0.058767772511848344,
      "grad_norm": 0.9154753088951111,
      "learning_rate": 7.928282679806052e-06,
      "loss": 0.5379,
      "step": 155
    },
    {
      "epoch": 0.05914691943127962,
      "grad_norm": 1.022912859916687,
      "learning_rate": 7.595355690475393e-06,
      "loss": 0.6094,
      "step": 156
    },
    {
      "epoch": 0.0595260663507109,
      "grad_norm": 1.1987192630767822,
      "learning_rate": 7.268553907189964e-06,
      "loss": 0.6575,
      "step": 157
    },
    {
      "epoch": 0.05990521327014218,
      "grad_norm": 1.0124115943908691,
      "learning_rate": 6.947966674294236e-06,
      "loss": 0.6735,
      "step": 158
    },
    {
      "epoch": 0.060284360189573456,
      "grad_norm": 1.0271550416946411,
      "learning_rate": 6.6336816371366305e-06,
      "loss": 0.5953,
      "step": 159
    },
    {
      "epoch": 0.06066350710900474,
      "grad_norm": 1.0127638578414917,
      "learning_rate": 6.325784718108196e-06,
      "loss": 0.6548,
      "step": 160
    },
    {
      "epoch": 0.06104265402843602,
      "grad_norm": 0.8849831223487854,
      "learning_rate": 6.0243600931522595e-06,
      "loss": 0.6348,
      "step": 161
    },
    {
      "epoch": 0.0614218009478673,
      "grad_norm": 0.9687224626541138,
      "learning_rate": 5.72949016875158e-06,
      "loss": 0.5602,
      "step": 162
    },
    {
      "epoch": 0.061800947867298575,
      "grad_norm": 0.9322991371154785,
      "learning_rate": 5.44125555939923e-06,
      "loss": 0.6793,
      "step": 163
    },
    {
      "epoch": 0.06218009478672986,
      "grad_norm": 0.8064345717430115,
      "learning_rate": 5.159735065559399e-06,
      "loss": 0.4625,
      "step": 164
    },
    {
      "epoch": 0.06255924170616113,
      "grad_norm": 0.9643939137458801,
      "learning_rate": 4.885005652124144e-06,
      "loss": 0.6543,
      "step": 165
    },
    {
      "epoch": 0.06293838862559242,
      "grad_norm": 0.9320531487464905,
      "learning_rate": 4.617142427371934e-06,
      "loss": 0.5322,
      "step": 166
    },
    {
      "epoch": 0.0633175355450237,
      "grad_norm": 0.7888116240501404,
      "learning_rate": 4.3562186224338265e-06,
      "loss": 0.4682,
      "step": 167
    },
    {
      "epoch": 0.06369668246445498,
      "grad_norm": 0.9415287375450134,
      "learning_rate": 4.102305571272783e-06,
      "loss": 0.6159,
      "step": 168
    },
    {
      "epoch": 0.06407582938388626,
      "grad_norm": 0.8795173168182373,
      "learning_rate": 3.855472691181678e-06,
      "loss": 0.5751,
      "step": 169
    },
    {
      "epoch": 0.06445497630331753,
      "grad_norm": 0.9194141030311584,
      "learning_rate": 3.615787463805331e-06,
      "loss": 0.5376,
      "step": 170
    },
    {
      "epoch": 0.06483412322274881,
      "grad_norm": 0.9153357744216919,
      "learning_rate": 3.383315416691646e-06,
      "loss": 0.5864,
      "step": 171
    },
    {
      "epoch": 0.06521327014218009,
      "grad_norm": 0.8993094563484192,
      "learning_rate": 3.158120105377096e-06,
      "loss": 0.5267,
      "step": 172
    },
    {
      "epoch": 0.06559241706161137,
      "grad_norm": 0.8435608744621277,
      "learning_rate": 2.940263096011233e-06,
      "loss": 0.5413,
      "step": 173
    },
    {
      "epoch": 0.06597156398104266,
      "grad_norm": 0.9139825105667114,
      "learning_rate": 2.729803948525125e-06,
      "loss": 0.4994,
      "step": 174
    },
    {
      "epoch": 0.06635071090047394,
      "grad_norm": 0.8998444080352783,
      "learning_rate": 2.526800200348275e-06,
      "loss": 0.5262,
      "step": 175
    },
    {
      "epoch": 0.06672985781990522,
      "grad_norm": 0.8086129426956177,
      "learning_rate": 2.3313073506784575e-06,
      "loss": 0.4989,
      "step": 176
    },
    {
      "epoch": 0.0671090047393365,
      "grad_norm": 0.805290937423706,
      "learning_rate": 2.143378845308791e-06,
      "loss": 0.4473,
      "step": 177
    },
    {
      "epoch": 0.06748815165876777,
      "grad_norm": 0.8601678609848022,
      "learning_rate": 1.9630660620161777e-06,
      "loss": 0.4955,
      "step": 178
    },
    {
      "epoch": 0.06786729857819905,
      "grad_norm": 0.875322699546814,
      "learning_rate": 1.790418296515165e-06,
      "loss": 0.5145,
      "step": 179
    },
    {
      "epoch": 0.06824644549763033,
      "grad_norm": 0.8989061117172241,
      "learning_rate": 1.625482748980961e-06,
      "loss": 0.5265,
      "step": 180
    },
    {
      "epoch": 0.0686255924170616,
      "grad_norm": 0.8949686884880066,
      "learning_rate": 1.4683045111453942e-06,
      "loss": 0.4835,
      "step": 181
    },
    {
      "epoch": 0.06900473933649288,
      "grad_norm": 0.9829505681991577,
      "learning_rate": 1.3189265539692707e-06,
      "loss": 0.4863,
      "step": 182
    },
    {
      "epoch": 0.06938388625592418,
      "grad_norm": 0.9040274024009705,
      "learning_rate": 1.1773897158945557e-06,
      "loss": 0.4871,
      "step": 183
    },
    {
      "epoch": 0.06976303317535545,
      "grad_norm": 0.8389787077903748,
      "learning_rate": 1.0437326916795432e-06,
      "loss": 0.4487,
      "step": 184
    },
    {
      "epoch": 0.07014218009478673,
      "grad_norm": 0.8816047310829163,
      "learning_rate": 9.179920218200888e-07,
      "loss": 0.4567,
      "step": 185
    },
    {
      "epoch": 0.07052132701421801,
      "grad_norm": 0.951728343963623,
      "learning_rate": 8.002020825598277e-07,
      "loss": 0.4308,
      "step": 186
    },
    {
      "epoch": 0.07090047393364929,
      "grad_norm": 0.9444287419319153,
      "learning_rate": 6.90395076492022e-07,
      "loss": 0.4475,
      "step": 187
    },
    {
      "epoch": 0.07127962085308057,
      "grad_norm": 0.7584393620491028,
      "learning_rate": 5.886010237557194e-07,
      "loss": 0.3609,
      "step": 188
    },
    {
      "epoch": 0.07165876777251184,
      "grad_norm": 0.8242846727371216,
      "learning_rate": 4.94847753828529e-07,
      "loss": 0.3971,
      "step": 189
    },
    {
      "epoch": 0.07203791469194312,
      "grad_norm": 0.8676409125328064,
      "learning_rate": 4.091608979183303e-07,
      "loss": 0.3851,
      "step": 190
    },
    {
      "epoch": 0.07241706161137441,
      "grad_norm": 0.8776127696037292,
      "learning_rate": 3.315638819559452e-07,
      "loss": 0.3837,
      "step": 191
    },
    {
      "epoch": 0.07279620853080569,
      "grad_norm": 0.9045898914337158,
      "learning_rate": 2.6207792019074414e-07,
      "loss": 0.4312,
      "step": 192
    },
    {
      "epoch": 0.07317535545023697,
      "grad_norm": 0.9427354335784912,
      "learning_rate": 2.0072200939085573e-07,
      "loss": 0.4484,
      "step": 193
    },
    {
      "epoch": 0.07355450236966825,
      "grad_norm": 0.8181795477867126,
      "learning_rate": 1.475129236496575e-07,
      "loss": 0.3509,
      "step": 194
    },
    {
      "epoch": 0.07393364928909953,
      "grad_norm": 0.7674962878227234,
      "learning_rate": 1.0246520979990459e-07,
      "loss": 0.3238,
      "step": 195
    },
    {
      "epoch": 0.0743127962085308,
      "grad_norm": 0.8669456839561462,
      "learning_rate": 6.559118343676396e-08,
      "loss": 0.3703,
      "step": 196
    },
    {
      "epoch": 0.07469194312796208,
      "grad_norm": 0.8156073093414307,
      "learning_rate": 3.690092555085789e-08,
      "loss": 0.2708,
      "step": 197
    },
    {
      "epoch": 0.07507109004739336,
      "grad_norm": 0.8143777847290039,
      "learning_rate": 1.640227977221853e-08,
      "loss": 0.269,
      "step": 198
    },
    {
      "epoch": 0.07545023696682464,
      "grad_norm": 0.8005136847496033,
      "learning_rate": 4.1008502259298755e-09,
      "loss": 0.2552,
      "step": 199
    },
    {
      "epoch": 0.07582938388625593,
      "grad_norm": 0.886074423789978,
      "learning_rate": 0.0,
      "loss": 0.2134,
      "step": 200
    },
    {
      "epoch": 0.07582938388625593,
      "eval_loss": 0.5063894391059875,
      "eval_runtime": 344.7064,
      "eval_samples_per_second": 12.886,
      "eval_steps_per_second": 3.223,
      "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": 3.092452836429005e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}