{
  "best_metric": 0.319932222366333,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.007874325760856726,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.937162880428363e-05,
      "grad_norm": 0.15041573345661163,
      "learning_rate": 1e-05,
      "loss": 0.4842,
      "step": 1
    },
    {
      "epoch": 3.937162880428363e-05,
      "eval_loss": 0.6386224031448364,
      "eval_runtime": 1977.8714,
      "eval_samples_per_second": 21.628,
      "eval_steps_per_second": 5.407,
      "step": 1
    },
    {
      "epoch": 7.874325760856726e-05,
      "grad_norm": 0.15318730473518372,
      "learning_rate": 2e-05,
      "loss": 0.4723,
      "step": 2
    },
    {
      "epoch": 0.0001181148864128509,
      "grad_norm": 0.155586376786232,
      "learning_rate": 3e-05,
      "loss": 0.4649,
      "step": 3
    },
    {
      "epoch": 0.00015748651521713453,
      "grad_norm": 0.15842971205711365,
      "learning_rate": 4e-05,
      "loss": 0.4612,
      "step": 4
    },
    {
      "epoch": 0.00019685814402141817,
      "grad_norm": 0.18087449669837952,
      "learning_rate": 5e-05,
      "loss": 0.4572,
      "step": 5
    },
    {
      "epoch": 0.0002362297728257018,
      "grad_norm": 0.1720651388168335,
      "learning_rate": 6e-05,
      "loss": 0.4519,
      "step": 6
    },
    {
      "epoch": 0.00027560140162998545,
      "grad_norm": 0.17728309333324432,
      "learning_rate": 7e-05,
      "loss": 0.4686,
      "step": 7
    },
    {
      "epoch": 0.00031497303043426906,
      "grad_norm": 0.19638827443122864,
      "learning_rate": 8e-05,
      "loss": 0.4867,
      "step": 8
    },
    {
      "epoch": 0.0003543446592385527,
      "grad_norm": 0.220866858959198,
      "learning_rate": 9e-05,
      "loss": 0.439,
      "step": 9
    },
    {
      "epoch": 0.00039371628804283634,
      "grad_norm": 0.20618507266044617,
      "learning_rate": 0.0001,
      "loss": 0.4673,
      "step": 10
    },
    {
      "epoch": 0.00043308791684711995,
      "grad_norm": 0.19284336268901825,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4405,
      "step": 11
    },
    {
      "epoch": 0.0004724595456514036,
      "grad_norm": 0.18760031461715698,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4306,
      "step": 12
    },
    {
      "epoch": 0.0005118311744556872,
      "grad_norm": 0.195184588432312,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4259,
      "step": 13
    },
    {
      "epoch": 0.0005512028032599709,
      "grad_norm": 0.18539170920848846,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.42,
      "step": 14
    },
    {
      "epoch": 0.0005905744320642545,
      "grad_norm": 0.17798694968223572,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4373,
      "step": 15
    },
    {
      "epoch": 0.0006299460608685381,
      "grad_norm": 0.17233476042747498,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4092,
      "step": 16
    },
    {
      "epoch": 0.0006693176896728218,
      "grad_norm": 0.1832939237356186,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.412,
      "step": 17
    },
    {
      "epoch": 0.0007086893184771055,
      "grad_norm": 0.19086192548274994,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.411,
      "step": 18
    },
    {
      "epoch": 0.000748060947281389,
      "grad_norm": 0.17972241342067719,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4002,
      "step": 19
    },
    {
      "epoch": 0.0007874325760856727,
      "grad_norm": 0.19496911764144897,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4031,
      "step": 20
    },
    {
      "epoch": 0.0008268042048899563,
      "grad_norm": 0.20632889866828918,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3987,
      "step": 21
    },
    {
      "epoch": 0.0008661758336942399,
      "grad_norm": 0.20927245914936066,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.413,
      "step": 22
    },
    {
      "epoch": 0.0009055474624985236,
      "grad_norm": 0.2088814377784729,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3929,
      "step": 23
    },
    {
      "epoch": 0.0009449190913028072,
      "grad_norm": 0.206711083650589,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.3946,
      "step": 24
    },
    {
      "epoch": 0.0009842907201070908,
      "grad_norm": 0.2751156687736511,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4084,
      "step": 25
    },
    {
      "epoch": 0.0010236623489113745,
      "grad_norm": 0.2105296105146408,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3774,
      "step": 26
    },
    {
      "epoch": 0.0010630339777156581,
      "grad_norm": 0.2260245382785797,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.3939,
      "step": 27
    },
    {
      "epoch": 0.0011024056065199418,
      "grad_norm": 0.21112877130508423,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.3626,
      "step": 28
    },
    {
      "epoch": 0.0011417772353242255,
      "grad_norm": 0.23001547157764435,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3737,
      "step": 29
    },
    {
      "epoch": 0.001181148864128509,
      "grad_norm": 0.2270578145980835,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3833,
      "step": 30
    },
    {
      "epoch": 0.0012205204929327926,
      "grad_norm": 0.23201963305473328,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.373,
      "step": 31
    },
    {
      "epoch": 0.0012598921217370762,
      "grad_norm": 0.23965425789356232,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3871,
      "step": 32
    },
    {
      "epoch": 0.00129926375054136,
      "grad_norm": 0.25030216574668884,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3794,
      "step": 33
    },
    {
      "epoch": 0.0013386353793456436,
      "grad_norm": 0.24742576479911804,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3673,
      "step": 34
    },
    {
      "epoch": 0.0013780070081499272,
      "grad_norm": 0.2736644744873047,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3855,
      "step": 35
    },
    {
      "epoch": 0.001417378636954211,
      "grad_norm": 0.29005998373031616,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3987,
      "step": 36
    },
    {
      "epoch": 0.0014567502657584943,
      "grad_norm": 0.3033083975315094,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4231,
      "step": 37
    },
    {
      "epoch": 0.001496121894562778,
      "grad_norm": 0.32821401953697205,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3914,
      "step": 38
    },
    {
      "epoch": 0.0015354935233670617,
      "grad_norm": 0.34220942854881287,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3872,
      "step": 39
    },
    {
      "epoch": 0.0015748651521713453,
      "grad_norm": 0.38347524404525757,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4096,
      "step": 40
    },
    {
      "epoch": 0.001614236780975629,
      "grad_norm": 0.3992728590965271,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4435,
      "step": 41
    },
    {
      "epoch": 0.0016536084097799127,
      "grad_norm": 0.4478294551372528,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4257,
      "step": 42
    },
    {
      "epoch": 0.0016929800385841961,
      "grad_norm": 0.4987800717353821,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4593,
      "step": 43
    },
    {
      "epoch": 0.0017323516673884798,
      "grad_norm": 0.48720991611480713,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4405,
      "step": 44
    },
    {
      "epoch": 0.0017717232961927635,
      "grad_norm": 0.5510795712471008,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5094,
      "step": 45
    },
    {
      "epoch": 0.0018110949249970471,
      "grad_norm": 0.643317461013794,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.4789,
      "step": 46
    },
    {
      "epoch": 0.0018504665538013308,
      "grad_norm": 0.7148213386535645,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.4995,
      "step": 47
    },
    {
      "epoch": 0.0018898381826056145,
      "grad_norm": 0.873295247554779,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4872,
      "step": 48
    },
    {
      "epoch": 0.0019292098114098981,
      "grad_norm": 0.9476174712181091,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.5099,
      "step": 49
    },
    {
      "epoch": 0.0019685814402141816,
      "grad_norm": 1.705020546913147,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7284,
      "step": 50
    },
    {
      "epoch": 0.0019685814402141816,
      "eval_loss": 0.48922795057296753,
      "eval_runtime": 1987.8865,
      "eval_samples_per_second": 21.519,
      "eval_steps_per_second": 5.38,
      "step": 50
    },
    {
      "epoch": 0.0020079530690184652,
      "grad_norm": 1.1396428346633911,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5298,
      "step": 51
    },
    {
      "epoch": 0.002047324697822749,
      "grad_norm": 0.575873613357544,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4576,
      "step": 52
    },
    {
      "epoch": 0.0020866963266270326,
      "grad_norm": 0.29430681467056274,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4226,
      "step": 53
    },
    {
      "epoch": 0.0021260679554313162,
      "grad_norm": 0.22301702201366425,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3945,
      "step": 54
    },
    {
      "epoch": 0.0021654395842356,
      "grad_norm": 0.19866794347763062,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3653,
      "step": 55
    },
    {
      "epoch": 0.0022048112130398836,
      "grad_norm": 0.22038273513317108,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.3928,
      "step": 56
    },
    {
      "epoch": 0.0022441828418441672,
      "grad_norm": 0.2194378525018692,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.384,
      "step": 57
    },
    {
      "epoch": 0.002283554470648451,
      "grad_norm": 0.22321100533008575,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3963,
      "step": 58
    },
    {
      "epoch": 0.0023229260994527346,
      "grad_norm": 0.20015667378902435,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3944,
      "step": 59
    },
    {
      "epoch": 0.002362297728257018,
      "grad_norm": 0.1830534040927887,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3929,
      "step": 60
    },
    {
      "epoch": 0.0024016693570613015,
      "grad_norm": 0.17937935888767242,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3737,
      "step": 61
    },
    {
      "epoch": 0.002441040985865585,
      "grad_norm": 0.17047609388828278,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3544,
      "step": 62
    },
    {
      "epoch": 0.002480412614669869,
      "grad_norm": 0.16016490757465363,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3535,
      "step": 63
    },
    {
      "epoch": 0.0025197842434741525,
      "grad_norm": 0.17423444986343384,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3662,
      "step": 64
    },
    {
      "epoch": 0.002559155872278436,
      "grad_norm": 0.16964031755924225,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3414,
      "step": 65
    },
    {
      "epoch": 0.00259852750108272,
      "grad_norm": 0.17602507770061493,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3599,
      "step": 66
    },
    {
      "epoch": 0.0026378991298870035,
      "grad_norm": 0.17280983924865723,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3634,
      "step": 67
    },
    {
      "epoch": 0.002677270758691287,
      "grad_norm": 0.17735128104686737,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3395,
      "step": 68
    },
    {
      "epoch": 0.002716642387495571,
      "grad_norm": 0.19342201948165894,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3339,
      "step": 69
    },
    {
      "epoch": 0.0027560140162998545,
      "grad_norm": 0.18403244018554688,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3639,
      "step": 70
    },
    {
      "epoch": 0.002795385645104138,
      "grad_norm": 0.1859416365623474,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3689,
      "step": 71
    },
    {
      "epoch": 0.002834757273908422,
      "grad_norm": 0.17948848009109497,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3145,
      "step": 72
    },
    {
      "epoch": 0.002874128902712705,
      "grad_norm": 0.19565199315547943,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3687,
      "step": 73
    },
    {
      "epoch": 0.0029135005315169887,
      "grad_norm": 0.17460434138774872,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3372,
      "step": 74
    },
    {
      "epoch": 0.0029528721603212724,
      "grad_norm": 0.1879396140575409,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3313,
      "step": 75
    },
    {
      "epoch": 0.002992243789125556,
      "grad_norm": 0.18079061806201935,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3339,
      "step": 76
    },
    {
      "epoch": 0.0030316154179298397,
      "grad_norm": 0.19918537139892578,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.3329,
      "step": 77
    },
    {
      "epoch": 0.0030709870467341234,
      "grad_norm": 0.19581687450408936,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3256,
      "step": 78
    },
    {
      "epoch": 0.003110358675538407,
      "grad_norm": 0.21447274088859558,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3618,
      "step": 79
    },
    {
      "epoch": 0.0031497303043426907,
      "grad_norm": 0.2164623737335205,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3543,
      "step": 80
    },
    {
      "epoch": 0.0031891019331469744,
      "grad_norm": 0.21725690364837646,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.325,
      "step": 81
    },
    {
      "epoch": 0.003228473561951258,
      "grad_norm": 0.23109690845012665,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3482,
      "step": 82
    },
    {
      "epoch": 0.0032678451907555417,
      "grad_norm": 0.2352961301803589,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3401,
      "step": 83
    },
    {
      "epoch": 0.0033072168195598254,
      "grad_norm": 0.26041918992996216,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3655,
      "step": 84
    },
    {
      "epoch": 0.003346588448364109,
      "grad_norm": 0.24683479964733124,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3365,
      "step": 85
    },
    {
      "epoch": 0.0033859600771683923,
      "grad_norm": 0.2742876708507538,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3544,
      "step": 86
    },
    {
      "epoch": 0.003425331705972676,
      "grad_norm": 0.3074694573879242,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3455,
      "step": 87
    },
    {
      "epoch": 0.0034647033347769596,
      "grad_norm": 0.28489139676094055,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3248,
      "step": 88
    },
    {
      "epoch": 0.0035040749635812433,
      "grad_norm": 0.32520392537117004,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.373,
      "step": 89
    },
    {
      "epoch": 0.003543446592385527,
      "grad_norm": 0.3589666783809662,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3843,
      "step": 90
    },
    {
      "epoch": 0.0035828182211898106,
      "grad_norm": 0.39428192377090454,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3816,
      "step": 91
    },
    {
      "epoch": 0.0036221898499940943,
      "grad_norm": 0.38958320021629333,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3553,
      "step": 92
    },
    {
      "epoch": 0.003661561478798378,
      "grad_norm": 0.44357359409332275,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.3812,
      "step": 93
    },
    {
      "epoch": 0.0037009331076026616,
      "grad_norm": 0.49647799134254456,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3667,
      "step": 94
    },
    {
      "epoch": 0.0037403047364069453,
      "grad_norm": 0.6239516139030457,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.438,
      "step": 95
    },
    {
      "epoch": 0.003779676365211229,
      "grad_norm": 0.5736242532730103,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3732,
      "step": 96
    },
    {
      "epoch": 0.0038190479940155126,
      "grad_norm": 0.8299224376678467,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4323,
      "step": 97
    },
    {
      "epoch": 0.0038584196228197963,
      "grad_norm": 1.0015686750411987,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5042,
      "step": 98
    },
    {
      "epoch": 0.0038977912516240795,
      "grad_norm": 0.9972793459892273,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.541,
      "step": 99
    },
    {
      "epoch": 0.003937162880428363,
      "grad_norm": 1.5904582738876343,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5061,
      "step": 100
    },
    {
      "epoch": 0.003937162880428363,
      "eval_loss": 0.36916714906692505,
      "eval_runtime": 1987.5486,
      "eval_samples_per_second": 21.523,
      "eval_steps_per_second": 5.381,
      "step": 100
    },
    {
      "epoch": 0.003976534509232647,
      "grad_norm": 0.2698248624801636,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3903,
      "step": 101
    },
    {
      "epoch": 0.0040159061380369305,
      "grad_norm": 0.25083526968955994,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.361,
      "step": 102
    },
    {
      "epoch": 0.004055277766841214,
      "grad_norm": 0.24954238533973694,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.3741,
      "step": 103
    },
    {
      "epoch": 0.004094649395645498,
      "grad_norm": 0.3203243613243103,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.354,
      "step": 104
    },
    {
      "epoch": 0.0041340210244497815,
      "grad_norm": 0.28686997294425964,
      "learning_rate": 5e-05,
      "loss": 0.3327,
      "step": 105
    },
    {
      "epoch": 0.004173392653254065,
      "grad_norm": 0.26731210947036743,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3667,
      "step": 106
    },
    {
      "epoch": 0.004212764282058349,
      "grad_norm": 0.21260957419872284,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3509,
      "step": 107
    },
    {
      "epoch": 0.0042521359108626325,
      "grad_norm": 0.19314557313919067,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3412,
      "step": 108
    },
    {
      "epoch": 0.004291507539666916,
      "grad_norm": 0.1857222020626068,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3341,
      "step": 109
    },
    {
      "epoch": 0.0043308791684712,
      "grad_norm": 0.1851547658443451,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3304,
      "step": 110
    },
    {
      "epoch": 0.0043702507972754835,
      "grad_norm": 0.17488974332809448,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3413,
      "step": 111
    },
    {
      "epoch": 0.004409622426079767,
      "grad_norm": 0.1782592386007309,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.327,
      "step": 112
    },
    {
      "epoch": 0.004448994054884051,
      "grad_norm": 0.18713821470737457,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.333,
      "step": 113
    },
    {
      "epoch": 0.0044883656836883345,
      "grad_norm": 0.18218685686588287,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.3255,
      "step": 114
    },
    {
      "epoch": 0.004527737312492618,
      "grad_norm": 0.17883919179439545,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3057,
      "step": 115
    },
    {
      "epoch": 0.004567108941296902,
      "grad_norm": 0.19183780252933502,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3426,
      "step": 116
    },
    {
      "epoch": 0.0046064805701011855,
      "grad_norm": 0.18949471414089203,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3071,
      "step": 117
    },
    {
      "epoch": 0.004645852198905469,
      "grad_norm": 0.2053540199995041,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3475,
      "step": 118
    },
    {
      "epoch": 0.004685223827709752,
      "grad_norm": 0.1862872689962387,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3215,
      "step": 119
    },
    {
      "epoch": 0.004724595456514036,
      "grad_norm": 0.1784752458333969,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3118,
      "step": 120
    },
    {
      "epoch": 0.004763967085318319,
      "grad_norm": 0.2016214281320572,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3161,
      "step": 121
    },
    {
      "epoch": 0.004803338714122603,
      "grad_norm": 0.19396907091140747,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3351,
      "step": 122
    },
    {
      "epoch": 0.004842710342926887,
      "grad_norm": 0.19207337498664856,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3283,
      "step": 123
    },
    {
      "epoch": 0.00488208197173117,
      "grad_norm": 0.19837477803230286,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3095,
      "step": 124
    },
    {
      "epoch": 0.004921453600535454,
      "grad_norm": 0.2044375091791153,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3175,
      "step": 125
    },
    {
      "epoch": 0.004960825229339738,
      "grad_norm": 0.19916394352912903,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3109,
      "step": 126
    },
    {
      "epoch": 0.005000196858144021,
      "grad_norm": 0.20544566214084625,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3271,
      "step": 127
    },
    {
      "epoch": 0.005039568486948305,
      "grad_norm": 0.20632264018058777,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2933,
      "step": 128
    },
    {
      "epoch": 0.005078940115752589,
      "grad_norm": 0.21720726788043976,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.2933,
      "step": 129
    },
    {
      "epoch": 0.005118311744556872,
      "grad_norm": 0.22517623007297516,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3044,
      "step": 130
    },
    {
      "epoch": 0.005157683373361156,
      "grad_norm": 0.2334209382534027,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3146,
      "step": 131
    },
    {
      "epoch": 0.00519705500216544,
      "grad_norm": 0.2260541021823883,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.298,
      "step": 132
    },
    {
      "epoch": 0.005236426630969723,
      "grad_norm": 0.25719016790390015,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.335,
      "step": 133
    },
    {
      "epoch": 0.005275798259774007,
      "grad_norm": 0.25886377692222595,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3031,
      "step": 134
    },
    {
      "epoch": 0.005315169888578291,
      "grad_norm": 0.2470293641090393,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3037,
      "step": 135
    },
    {
      "epoch": 0.005354541517382574,
      "grad_norm": 0.28103408217430115,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3125,
      "step": 136
    },
    {
      "epoch": 0.005393913146186858,
      "grad_norm": 0.28059205412864685,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2969,
      "step": 137
    },
    {
      "epoch": 0.005433284774991142,
      "grad_norm": 0.28502798080444336,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3268,
      "step": 138
    },
    {
      "epoch": 0.005472656403795425,
      "grad_norm": 0.31838536262512207,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3314,
      "step": 139
    },
    {
      "epoch": 0.005512028032599709,
      "grad_norm": 0.33839502930641174,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3107,
      "step": 140
    },
    {
      "epoch": 0.005551399661403993,
      "grad_norm": 0.3526189923286438,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3015,
      "step": 141
    },
    {
      "epoch": 0.005590771290208276,
      "grad_norm": 0.39796969294548035,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3616,
      "step": 142
    },
    {
      "epoch": 0.00563014291901256,
      "grad_norm": 0.46527615189552307,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3218,
      "step": 143
    },
    {
      "epoch": 0.005669514547816844,
      "grad_norm": 0.5111784338951111,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3397,
      "step": 144
    },
    {
      "epoch": 0.005708886176621126,
      "grad_norm": 0.5502793192863464,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3911,
      "step": 145
    },
    {
      "epoch": 0.00574825780542541,
      "grad_norm": 0.545826256275177,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3407,
      "step": 146
    },
    {
      "epoch": 0.005787629434229694,
      "grad_norm": 0.5801648497581482,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3376,
      "step": 147
    },
    {
      "epoch": 0.005827001063033977,
      "grad_norm": 0.7802667617797852,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4137,
      "step": 148
    },
    {
      "epoch": 0.005866372691838261,
      "grad_norm": 0.85842365026474,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4084,
      "step": 149
    },
    {
      "epoch": 0.005905744320642545,
      "grad_norm": 1.3954704999923706,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4737,
      "step": 150
    },
    {
      "epoch": 0.005905744320642545,
      "eval_loss": 0.3278917670249939,
      "eval_runtime": 1988.7296,
      "eval_samples_per_second": 21.51,
      "eval_steps_per_second": 5.378,
      "step": 150
    },
    {
      "epoch": 0.005945115949446828,
      "grad_norm": 0.1948564499616623,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3431,
      "step": 151
    },
    {
      "epoch": 0.005984487578251112,
      "grad_norm": 0.21047662198543549,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3306,
      "step": 152
    },
    {
      "epoch": 0.006023859207055396,
      "grad_norm": 0.18953219056129456,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.3527,
      "step": 153
    },
    {
      "epoch": 0.006063230835859679,
      "grad_norm": 0.1903805434703827,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3282,
      "step": 154
    },
    {
      "epoch": 0.006102602464663963,
      "grad_norm": 0.21121416985988617,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3155,
      "step": 155
    },
    {
      "epoch": 0.006141974093468247,
      "grad_norm": 0.18949289619922638,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3052,
      "step": 156
    },
    {
      "epoch": 0.00618134572227253,
      "grad_norm": 0.19921760261058807,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3165,
      "step": 157
    },
    {
      "epoch": 0.006220717351076814,
      "grad_norm": 0.17726148664951324,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2903,
      "step": 158
    },
    {
      "epoch": 0.006260088979881098,
      "grad_norm": 0.1820344179868698,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3057,
      "step": 159
    },
    {
      "epoch": 0.006299460608685381,
      "grad_norm": 0.19113346934318542,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3007,
      "step": 160
    },
    {
      "epoch": 0.006338832237489665,
      "grad_norm": 0.19020693004131317,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3009,
      "step": 161
    },
    {
      "epoch": 0.006378203866293949,
      "grad_norm": 0.1869511753320694,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3295,
      "step": 162
    },
    {
      "epoch": 0.006417575495098232,
      "grad_norm": 0.18837088346481323,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.295,
      "step": 163
    },
    {
      "epoch": 0.006456947123902516,
      "grad_norm": 0.18772277235984802,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3003,
      "step": 164
    },
    {
      "epoch": 0.0064963187527068,
      "grad_norm": 0.19596266746520996,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.3084,
      "step": 165
    },
    {
      "epoch": 0.006535690381511083,
      "grad_norm": 0.1919110268354416,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3051,
      "step": 166
    },
    {
      "epoch": 0.006575062010315367,
      "grad_norm": 0.1833999902009964,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2937,
      "step": 167
    },
    {
      "epoch": 0.006614433639119651,
      "grad_norm": 0.19418050348758698,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3011,
      "step": 168
    },
    {
      "epoch": 0.006653805267923934,
      "grad_norm": 0.19146481156349182,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2896,
      "step": 169
    },
    {
      "epoch": 0.006693176896728218,
      "grad_norm": 0.19181102514266968,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2856,
      "step": 170
    },
    {
      "epoch": 0.006732548525532501,
      "grad_norm": 0.20279942452907562,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3017,
      "step": 171
    },
    {
      "epoch": 0.0067719201543367845,
      "grad_norm": 0.19550299644470215,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2826,
      "step": 172
    },
    {
      "epoch": 0.006811291783141068,
      "grad_norm": 0.20785211026668549,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3052,
      "step": 173
    },
    {
      "epoch": 0.006850663411945352,
      "grad_norm": 0.21435591578483582,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.3091,
      "step": 174
    },
    {
      "epoch": 0.0068900350407496355,
      "grad_norm": 0.21510900557041168,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2927,
      "step": 175
    },
    {
      "epoch": 0.006929406669553919,
      "grad_norm": 0.21470153331756592,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3071,
      "step": 176
    },
    {
      "epoch": 0.006968778298358203,
      "grad_norm": 0.21582479774951935,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2964,
      "step": 177
    },
    {
      "epoch": 0.0070081499271624865,
      "grad_norm": 0.23161204159259796,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3158,
      "step": 178
    },
    {
      "epoch": 0.00704752155596677,
      "grad_norm": 0.22845427691936493,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3102,
      "step": 179
    },
    {
      "epoch": 0.007086893184771054,
      "grad_norm": 0.23113465309143066,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.2994,
      "step": 180
    },
    {
      "epoch": 0.0071262648135753375,
      "grad_norm": 0.2367093712091446,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3018,
      "step": 181
    },
    {
      "epoch": 0.007165636442379621,
      "grad_norm": 0.25694456696510315,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2869,
      "step": 182
    },
    {
      "epoch": 0.007205008071183905,
      "grad_norm": 0.24491827189922333,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3006,
      "step": 183
    },
    {
      "epoch": 0.0072443796999881885,
      "grad_norm": 0.26006895303726196,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.3207,
      "step": 184
    },
    {
      "epoch": 0.007283751328792472,
      "grad_norm": 0.27544456720352173,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3075,
      "step": 185
    },
    {
      "epoch": 0.007323122957596756,
      "grad_norm": 0.29050812125205994,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3211,
      "step": 186
    },
    {
      "epoch": 0.0073624945864010395,
      "grad_norm": 0.2896967828273773,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.311,
      "step": 187
    },
    {
      "epoch": 0.007401866215205323,
      "grad_norm": 0.30733922123908997,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3309,
      "step": 188
    },
    {
      "epoch": 0.007441237844009607,
      "grad_norm": 0.3271937668323517,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3068,
      "step": 189
    },
    {
      "epoch": 0.0074806094728138905,
      "grad_norm": 0.36184725165367126,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3326,
      "step": 190
    },
    {
      "epoch": 0.007519981101618174,
      "grad_norm": 0.37546616792678833,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.34,
      "step": 191
    },
    {
      "epoch": 0.007559352730422458,
      "grad_norm": 0.3785892128944397,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2993,
      "step": 192
    },
    {
      "epoch": 0.0075987243592267415,
      "grad_norm": 0.41964954137802124,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3444,
      "step": 193
    },
    {
      "epoch": 0.007638095988031025,
      "grad_norm": 0.45998209714889526,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3886,
      "step": 194
    },
    {
      "epoch": 0.007677467616835309,
      "grad_norm": 0.5077772736549377,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3589,
      "step": 195
    },
    {
      "epoch": 0.0077168392456395925,
      "grad_norm": 0.5247809886932373,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3507,
      "step": 196
    },
    {
      "epoch": 0.007756210874443875,
      "grad_norm": 0.6396381258964539,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3246,
      "step": 197
    },
    {
      "epoch": 0.007795582503248159,
      "grad_norm": 0.8766241073608398,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4458,
      "step": 198
    },
    {
      "epoch": 0.007834954132052444,
      "grad_norm": 1.0297117233276367,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4466,
      "step": 199
    },
    {
      "epoch": 0.007874325760856726,
      "grad_norm": 1.4922454357147217,
      "learning_rate": 0.0,
      "loss": 0.5555,
      "step": 200
    },
    {
      "epoch": 0.007874325760856726,
      "eval_loss": 0.319932222366333,
      "eval_runtime": 1988.5455,
      "eval_samples_per_second": 21.512,
      "eval_steps_per_second": 5.378,
      "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": 1.439681531609088e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}