{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00832639467110741,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.326394671107411e-05,
      "grad_norm": 0.6528549790382385,
      "learning_rate": 1e-05,
      "loss": 1.1197,
      "step": 1
    },
    {
      "epoch": 8.326394671107411e-05,
      "eval_loss": 1.2025511264801025,
      "eval_runtime": 1852.7806,
      "eval_samples_per_second": 5.459,
      "eval_steps_per_second": 0.683,
      "step": 1
    },
    {
      "epoch": 0.00016652789342214822,
      "grad_norm": 0.5731087327003479,
      "learning_rate": 2e-05,
      "loss": 1.4157,
      "step": 2
    },
    {
      "epoch": 0.0002497918401332223,
      "grad_norm": 0.6199445724487305,
      "learning_rate": 3e-05,
      "loss": 1.0426,
      "step": 3
    },
    {
      "epoch": 0.00033305578684429644,
      "grad_norm": 0.7111283540725708,
      "learning_rate": 4e-05,
      "loss": 0.8851,
      "step": 4
    },
    {
      "epoch": 0.00041631973355537054,
      "grad_norm": 0.7614225745201111,
      "learning_rate": 5e-05,
      "loss": 1.133,
      "step": 5
    },
    {
      "epoch": 0.0004995836802664446,
      "grad_norm": 0.6754878759384155,
      "learning_rate": 6e-05,
      "loss": 1.1536,
      "step": 6
    },
    {
      "epoch": 0.0005828476269775188,
      "grad_norm": 0.7614368796348572,
      "learning_rate": 7e-05,
      "loss": 1.1377,
      "step": 7
    },
    {
      "epoch": 0.0006661115736885929,
      "grad_norm": 0.9258794188499451,
      "learning_rate": 8e-05,
      "loss": 1.2977,
      "step": 8
    },
    {
      "epoch": 0.000749375520399667,
      "grad_norm": 1.0688425302505493,
      "learning_rate": 9e-05,
      "loss": 1.148,
      "step": 9
    },
    {
      "epoch": 0.000749375520399667,
      "eval_loss": 1.0213708877563477,
      "eval_runtime": 1855.6342,
      "eval_samples_per_second": 5.45,
      "eval_steps_per_second": 0.682,
      "step": 9
    },
    {
      "epoch": 0.0008326394671107411,
      "grad_norm": 0.7153362035751343,
      "learning_rate": 0.0001,
      "loss": 0.8094,
      "step": 10
    },
    {
      "epoch": 0.0009159034138218152,
      "grad_norm": 0.5778496265411377,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8924,
      "step": 11
    },
    {
      "epoch": 0.0009991673605328892,
      "grad_norm": 0.6626104712486267,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.899,
      "step": 12
    },
    {
      "epoch": 0.0010824313072439634,
      "grad_norm": 0.503301739692688,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.7183,
      "step": 13
    },
    {
      "epoch": 0.0011656952539550376,
      "grad_norm": 0.7047042846679688,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8217,
      "step": 14
    },
    {
      "epoch": 0.0012489592006661116,
      "grad_norm": 0.6127983331680298,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.9597,
      "step": 15
    },
    {
      "epoch": 0.0013322231473771858,
      "grad_norm": 0.8989804983139038,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.7034,
      "step": 16
    },
    {
      "epoch": 0.0014154870940882597,
      "grad_norm": 0.6098889708518982,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6515,
      "step": 17
    },
    {
      "epoch": 0.001498751040799334,
      "grad_norm": 0.6165075302124023,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.8014,
      "step": 18
    },
    {
      "epoch": 0.001498751040799334,
      "eval_loss": 0.7662500143051147,
      "eval_runtime": 1854.9316,
      "eval_samples_per_second": 5.452,
      "eval_steps_per_second": 0.682,
      "step": 18
    },
    {
      "epoch": 0.001582014987510408,
      "grad_norm": 0.5860106348991394,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.84,
      "step": 19
    },
    {
      "epoch": 0.0016652789342214821,
      "grad_norm": 0.7958736419677734,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.7013,
      "step": 20
    },
    {
      "epoch": 0.0017485428809325561,
      "grad_norm": 0.7166709899902344,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.687,
      "step": 21
    },
    {
      "epoch": 0.0018318068276436303,
      "grad_norm": 0.6691816449165344,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7604,
      "step": 22
    },
    {
      "epoch": 0.0019150707743547043,
      "grad_norm": 0.6859657168388367,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.1768,
      "step": 23
    },
    {
      "epoch": 0.0019983347210657783,
      "grad_norm": 0.6140884757041931,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.787,
      "step": 24
    },
    {
      "epoch": 0.0020815986677768525,
      "grad_norm": 0.8285980224609375,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7319,
      "step": 25
    },
    {
      "epoch": 0.0021648626144879267,
      "grad_norm": 0.43060940504074097,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4609,
      "step": 26
    },
    {
      "epoch": 0.002248126561199001,
      "grad_norm": 0.6124065518379211,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7266,
      "step": 27
    },
    {
      "epoch": 0.002248126561199001,
      "eval_loss": 0.6869298219680786,
      "eval_runtime": 1854.5703,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 0.682,
      "step": 27
    },
    {
      "epoch": 0.002331390507910075,
      "grad_norm": 0.549606204032898,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8842,
      "step": 28
    },
    {
      "epoch": 0.002414654454621149,
      "grad_norm": 0.499147891998291,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.6108,
      "step": 29
    },
    {
      "epoch": 0.002497918401332223,
      "grad_norm": 0.4452704191207886,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.8397,
      "step": 30
    },
    {
      "epoch": 0.0025811823480432973,
      "grad_norm": 0.5132455825805664,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.5112,
      "step": 31
    },
    {
      "epoch": 0.0026644462947543715,
      "grad_norm": 0.6590349674224854,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7076,
      "step": 32
    },
    {
      "epoch": 0.0027477102414654453,
      "grad_norm": 0.47231316566467285,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7897,
      "step": 33
    },
    {
      "epoch": 0.0028309741881765195,
      "grad_norm": 0.44176238775253296,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.6479,
      "step": 34
    },
    {
      "epoch": 0.0029142381348875937,
      "grad_norm": 0.5545864105224609,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.4567,
      "step": 35
    },
    {
      "epoch": 0.002997502081598668,
      "grad_norm": 0.5183555483818054,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.4244,
      "step": 36
    },
    {
      "epoch": 0.002997502081598668,
      "eval_loss": 0.6542710661888123,
      "eval_runtime": 1854.5763,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 0.682,
      "step": 36
    },
    {
      "epoch": 0.0030807660283097417,
      "grad_norm": 0.9999545216560364,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3533,
      "step": 37
    },
    {
      "epoch": 0.003164029975020816,
      "grad_norm": 0.6992344856262207,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.659,
      "step": 38
    },
    {
      "epoch": 0.00324729392173189,
      "grad_norm": 0.5412084460258484,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.5872,
      "step": 39
    },
    {
      "epoch": 0.0033305578684429643,
      "grad_norm": 0.552274227142334,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6418,
      "step": 40
    },
    {
      "epoch": 0.0034138218151540385,
      "grad_norm": 0.5327650308609009,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.7878,
      "step": 41
    },
    {
      "epoch": 0.0034970857618651123,
      "grad_norm": 0.5023038387298584,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3751,
      "step": 42
    },
    {
      "epoch": 0.0035803497085761865,
      "grad_norm": 0.4928383529186249,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.8629,
      "step": 43
    },
    {
      "epoch": 0.0036636136552872607,
      "grad_norm": 0.7069478034973145,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6381,
      "step": 44
    },
    {
      "epoch": 0.003746877601998335,
      "grad_norm": 0.5697295665740967,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.959,
      "step": 45
    },
    {
      "epoch": 0.003746877601998335,
      "eval_loss": 0.6388195753097534,
      "eval_runtime": 1855.2358,
      "eval_samples_per_second": 5.452,
      "eval_steps_per_second": 0.682,
      "step": 45
    },
    {
      "epoch": 0.0038301415487094087,
      "grad_norm": 0.5294673442840576,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2692,
      "step": 46
    },
    {
      "epoch": 0.003913405495420483,
      "grad_norm": 0.5600007176399231,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.608,
      "step": 47
    },
    {
      "epoch": 0.003996669442131557,
      "grad_norm": 0.5166972279548645,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8449,
      "step": 48
    },
    {
      "epoch": 0.004079933388842631,
      "grad_norm": 0.6273412704467773,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.5955,
      "step": 49
    },
    {
      "epoch": 0.004163197335553705,
      "grad_norm": 0.6368096470832825,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7049,
      "step": 50
    },
    {
      "epoch": 0.004246461282264779,
      "grad_norm": 0.4962923228740692,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.6266,
      "step": 51
    },
    {
      "epoch": 0.0043297252289758534,
      "grad_norm": 0.7681780457496643,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6163,
      "step": 52
    },
    {
      "epoch": 0.004412989175686928,
      "grad_norm": 0.5388240814208984,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.9432,
      "step": 53
    },
    {
      "epoch": 0.004496253122398002,
      "grad_norm": 0.540766716003418,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5601,
      "step": 54
    },
    {
      "epoch": 0.004496253122398002,
      "eval_loss": 0.6262350678443909,
      "eval_runtime": 1854.3549,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 0.682,
      "step": 54
    },
    {
      "epoch": 0.004579517069109076,
      "grad_norm": 0.5966364741325378,
      "learning_rate": 5e-05,
      "loss": 0.5944,
      "step": 55
    },
    {
      "epoch": 0.00466278101582015,
      "grad_norm": 0.5495940446853638,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7748,
      "step": 56
    },
    {
      "epoch": 0.004746044962531224,
      "grad_norm": 0.5919543504714966,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.6178,
      "step": 57
    },
    {
      "epoch": 0.004829308909242298,
      "grad_norm": 0.4971623420715332,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.6822,
      "step": 58
    },
    {
      "epoch": 0.004912572855953372,
      "grad_norm": 0.48071619868278503,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.6229,
      "step": 59
    },
    {
      "epoch": 0.004995836802664446,
      "grad_norm": 0.6728600263595581,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7187,
      "step": 60
    },
    {
      "epoch": 0.00507910074937552,
      "grad_norm": 0.5078701376914978,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.807,
      "step": 61
    },
    {
      "epoch": 0.005162364696086595,
      "grad_norm": 0.6860705614089966,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5846,
      "step": 62
    },
    {
      "epoch": 0.005245628642797669,
      "grad_norm": 0.6484000086784363,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.5815,
      "step": 63
    },
    {
      "epoch": 0.005245628642797669,
      "eval_loss": 0.6161054968833923,
      "eval_runtime": 1860.8419,
      "eval_samples_per_second": 5.435,
      "eval_steps_per_second": 0.68,
      "step": 63
    },
    {
      "epoch": 0.005328892589508743,
      "grad_norm": 0.5421977639198303,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6864,
      "step": 64
    },
    {
      "epoch": 0.005412156536219817,
      "grad_norm": 0.4390830397605896,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.7059,
      "step": 65
    },
    {
      "epoch": 0.005495420482930891,
      "grad_norm": 0.6560856699943542,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.6547,
      "step": 66
    },
    {
      "epoch": 0.005578684429641965,
      "grad_norm": 0.5721938610076904,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4023,
      "step": 67
    },
    {
      "epoch": 0.005661948376353039,
      "grad_norm": 0.5835623741149902,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.6517,
      "step": 68
    },
    {
      "epoch": 0.005745212323064113,
      "grad_norm": 0.4951063096523285,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.7356,
      "step": 69
    },
    {
      "epoch": 0.005828476269775187,
      "grad_norm": 0.5354863405227661,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4917,
      "step": 70
    },
    {
      "epoch": 0.005911740216486262,
      "grad_norm": 0.6460197567939758,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5706,
      "step": 71
    },
    {
      "epoch": 0.005995004163197336,
      "grad_norm": 0.46462133526802063,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.8467,
      "step": 72
    },
    {
      "epoch": 0.005995004163197336,
      "eval_loss": 0.6105489730834961,
      "eval_runtime": 1856.1031,
      "eval_samples_per_second": 5.449,
      "eval_steps_per_second": 0.682,
      "step": 72
    },
    {
      "epoch": 0.00607826810990841,
      "grad_norm": 0.5325016975402832,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.775,
      "step": 73
    },
    {
      "epoch": 0.006161532056619483,
      "grad_norm": 0.5006434917449951,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.5357,
      "step": 74
    },
    {
      "epoch": 0.0062447960033305576,
      "grad_norm": 0.46966591477394104,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.908,
      "step": 75
    },
    {
      "epoch": 0.006328059950041632,
      "grad_norm": 0.5430799126625061,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7039,
      "step": 76
    },
    {
      "epoch": 0.006411323896752706,
      "grad_norm": 0.49497535824775696,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.71,
      "step": 77
    },
    {
      "epoch": 0.00649458784346378,
      "grad_norm": 0.8195580244064331,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.431,
      "step": 78
    },
    {
      "epoch": 0.006577851790174854,
      "grad_norm": 0.6235741376876831,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.5497,
      "step": 79
    },
    {
      "epoch": 0.006661115736885929,
      "grad_norm": 0.5306349992752075,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.548,
      "step": 80
    },
    {
      "epoch": 0.006744379683597003,
      "grad_norm": 0.43674591183662415,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6883,
      "step": 81
    },
    {
      "epoch": 0.006744379683597003,
      "eval_loss": 0.6068940758705139,
      "eval_runtime": 1854.7201,
      "eval_samples_per_second": 5.453,
      "eval_steps_per_second": 0.682,
      "step": 81
    },
    {
      "epoch": 0.006827643630308077,
      "grad_norm": 0.5326769948005676,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.717,
      "step": 82
    },
    {
      "epoch": 0.00691090757701915,
      "grad_norm": 0.5180171728134155,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.738,
      "step": 83
    },
    {
      "epoch": 0.0069941715237302245,
      "grad_norm": 0.34972211718559265,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.5106,
      "step": 84
    },
    {
      "epoch": 0.007077435470441299,
      "grad_norm": 0.5829041600227356,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6901,
      "step": 85
    },
    {
      "epoch": 0.007160699417152373,
      "grad_norm": 0.8260759711265564,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6048,
      "step": 86
    },
    {
      "epoch": 0.007243963363863447,
      "grad_norm": 0.843137800693512,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4245,
      "step": 87
    },
    {
      "epoch": 0.007327227310574521,
      "grad_norm": 0.6163090467453003,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6817,
      "step": 88
    },
    {
      "epoch": 0.0074104912572855956,
      "grad_norm": 0.6686189770698547,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.6306,
      "step": 89
    },
    {
      "epoch": 0.00749375520399667,
      "grad_norm": 0.4524418115615845,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4867,
      "step": 90
    },
    {
      "epoch": 0.00749375520399667,
      "eval_loss": 0.6050958037376404,
      "eval_runtime": 1857.1868,
      "eval_samples_per_second": 5.446,
      "eval_steps_per_second": 0.681,
      "step": 90
    },
    {
      "epoch": 0.007577019150707744,
      "grad_norm": 0.5021795630455017,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5776,
      "step": 91
    },
    {
      "epoch": 0.007660283097418817,
      "grad_norm": 0.7382466793060303,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.6027,
      "step": 92
    },
    {
      "epoch": 0.0077435470441298915,
      "grad_norm": 0.4903351366519928,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.4592,
      "step": 93
    },
    {
      "epoch": 0.007826810990840967,
      "grad_norm": 0.4780626595020294,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7751,
      "step": 94
    },
    {
      "epoch": 0.00791007493755204,
      "grad_norm": 0.5676589608192444,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.4189,
      "step": 95
    },
    {
      "epoch": 0.007993338884263113,
      "grad_norm": 0.5701627135276794,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.5224,
      "step": 96
    },
    {
      "epoch": 0.008076602830974187,
      "grad_norm": 0.5422607064247131,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.5171,
      "step": 97
    },
    {
      "epoch": 0.008159866777685262,
      "grad_norm": 0.714150071144104,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.719,
      "step": 98
    },
    {
      "epoch": 0.008243130724396336,
      "grad_norm": 0.5458808541297913,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8718,
      "step": 99
    },
    {
      "epoch": 0.008243130724396336,
      "eval_loss": 0.6047412157058716,
      "eval_runtime": 1857.5279,
      "eval_samples_per_second": 5.445,
      "eval_steps_per_second": 0.681,
      "step": 99
    },
    {
      "epoch": 0.00832639467110741,
      "grad_norm": 0.5551886558532715,
      "learning_rate": 0.0,
      "loss": 0.3388,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1602201751322624e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}