{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009488116134541487,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.488116134541487e-05,
      "grad_norm": 1.1179174184799194,
      "learning_rate": 1e-05,
      "loss": 2.0136,
      "step": 1
    },
    {
      "epoch": 9.488116134541487e-05,
      "eval_loss": 2.044814109802246,
      "eval_runtime": 1082.9405,
      "eval_samples_per_second": 8.196,
      "eval_steps_per_second": 1.025,
      "step": 1
    },
    {
      "epoch": 0.00018976232269082974,
      "grad_norm": 1.2873406410217285,
      "learning_rate": 2e-05,
      "loss": 2.2054,
      "step": 2
    },
    {
      "epoch": 0.00028464348403624463,
      "grad_norm": 1.4217164516448975,
      "learning_rate": 3e-05,
      "loss": 2.2993,
      "step": 3
    },
    {
      "epoch": 0.00037952464538165947,
      "grad_norm": 1.0913364887237549,
      "learning_rate": 4e-05,
      "loss": 1.9095,
      "step": 4
    },
    {
      "epoch": 0.00047440580672707437,
      "grad_norm": 1.1571333408355713,
      "learning_rate": 5e-05,
      "loss": 1.8157,
      "step": 5
    },
    {
      "epoch": 0.0005692869680724893,
      "grad_norm": 1.1290559768676758,
      "learning_rate": 6e-05,
      "loss": 1.6643,
      "step": 6
    },
    {
      "epoch": 0.000664168129417904,
      "grad_norm": 1.201819896697998,
      "learning_rate": 7e-05,
      "loss": 1.9168,
      "step": 7
    },
    {
      "epoch": 0.0007590492907633189,
      "grad_norm": 1.501457929611206,
      "learning_rate": 8e-05,
      "loss": 2.1298,
      "step": 8
    },
    {
      "epoch": 0.0008539304521087338,
      "grad_norm": 1.226552963256836,
      "learning_rate": 9e-05,
      "loss": 1.9444,
      "step": 9
    },
    {
      "epoch": 0.0008539304521087338,
      "eval_loss": 1.828656792640686,
      "eval_runtime": 1085.5057,
      "eval_samples_per_second": 8.177,
      "eval_steps_per_second": 1.023,
      "step": 9
    },
    {
      "epoch": 0.0009488116134541487,
      "grad_norm": 1.08986496925354,
      "learning_rate": 0.0001,
      "loss": 2.0429,
      "step": 10
    },
    {
      "epoch": 0.0010436927747995636,
      "grad_norm": 1.1125391721725464,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.8817,
      "step": 11
    },
    {
      "epoch": 0.0011385739361449785,
      "grad_norm": 1.5336627960205078,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.8072,
      "step": 12
    },
    {
      "epoch": 0.0012334550974903932,
      "grad_norm": 1.4077439308166504,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8512,
      "step": 13
    },
    {
      "epoch": 0.001328336258835808,
      "grad_norm": 1.3526650667190552,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.7567,
      "step": 14
    },
    {
      "epoch": 0.001423217420181223,
      "grad_norm": 1.23054039478302,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.782,
      "step": 15
    },
    {
      "epoch": 0.0015180985815266379,
      "grad_norm": 1.219004511833191,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7007,
      "step": 16
    },
    {
      "epoch": 0.0016129797428720528,
      "grad_norm": 0.9380444288253784,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7286,
      "step": 17
    },
    {
      "epoch": 0.0017078609042174677,
      "grad_norm": 1.0295952558517456,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7644,
      "step": 18
    },
    {
      "epoch": 0.0017078609042174677,
      "eval_loss": 1.6711846590042114,
      "eval_runtime": 1084.8063,
      "eval_samples_per_second": 8.182,
      "eval_steps_per_second": 1.023,
      "step": 18
    },
    {
      "epoch": 0.0018027420655628826,
      "grad_norm": 1.3452121019363403,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9288,
      "step": 19
    },
    {
      "epoch": 0.0018976232269082975,
      "grad_norm": 0.9437580108642578,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5166,
      "step": 20
    },
    {
      "epoch": 0.001992504388253712,
      "grad_norm": 0.9429516792297363,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.4955,
      "step": 21
    },
    {
      "epoch": 0.0020873855495991273,
      "grad_norm": 0.8644145727157593,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.4253,
      "step": 22
    },
    {
      "epoch": 0.002182266710944542,
      "grad_norm": 0.940532922744751,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6322,
      "step": 23
    },
    {
      "epoch": 0.002277147872289957,
      "grad_norm": 0.9520596265792847,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4608,
      "step": 24
    },
    {
      "epoch": 0.0023720290336353717,
      "grad_norm": 1.16845703125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5855,
      "step": 25
    },
    {
      "epoch": 0.0024669101949807864,
      "grad_norm": 0.8661882877349854,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5336,
      "step": 26
    },
    {
      "epoch": 0.0025617913563262015,
      "grad_norm": 0.9252780675888062,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.6042,
      "step": 27
    },
    {
      "epoch": 0.0025617913563262015,
      "eval_loss": 1.634818196296692,
      "eval_runtime": 1085.0329,
      "eval_samples_per_second": 8.18,
      "eval_steps_per_second": 1.023,
      "step": 27
    },
    {
      "epoch": 0.002656672517671616,
      "grad_norm": 1.040569543838501,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6379,
      "step": 28
    },
    {
      "epoch": 0.0027515536790170313,
      "grad_norm": 0.934683084487915,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.5159,
      "step": 29
    },
    {
      "epoch": 0.002846434840362446,
      "grad_norm": 0.908628523349762,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5628,
      "step": 30
    },
    {
      "epoch": 0.002941316001707861,
      "grad_norm": 0.8518630862236023,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.5605,
      "step": 31
    },
    {
      "epoch": 0.0030361971630532758,
      "grad_norm": 0.9292842149734497,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.6211,
      "step": 32
    },
    {
      "epoch": 0.0031310783243986904,
      "grad_norm": 0.9021596312522888,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.6151,
      "step": 33
    },
    {
      "epoch": 0.0032259594857441056,
      "grad_norm": 0.8258885741233826,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.6105,
      "step": 34
    },
    {
      "epoch": 0.0033208406470895202,
      "grad_norm": 0.8333180546760559,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4312,
      "step": 35
    },
    {
      "epoch": 0.0034157218084349353,
      "grad_norm": 0.9054083824157715,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.6345,
      "step": 36
    },
    {
      "epoch": 0.0034157218084349353,
      "eval_loss": 1.6105045080184937,
      "eval_runtime": 1084.7416,
      "eval_samples_per_second": 8.183,
      "eval_steps_per_second": 1.023,
      "step": 36
    },
    {
      "epoch": 0.00351060296978035,
      "grad_norm": 0.9723847508430481,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5801,
      "step": 37
    },
    {
      "epoch": 0.003605484131125765,
      "grad_norm": 0.9598375558853149,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.7289,
      "step": 38
    },
    {
      "epoch": 0.00370036529247118,
      "grad_norm": 0.7757585644721985,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.3911,
      "step": 39
    },
    {
      "epoch": 0.003795246453816595,
      "grad_norm": 0.9091125726699829,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6503,
      "step": 40
    },
    {
      "epoch": 0.0038901276151620096,
      "grad_norm": 0.82570880651474,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.5909,
      "step": 41
    },
    {
      "epoch": 0.003985008776507424,
      "grad_norm": 0.892005205154419,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.5125,
      "step": 42
    },
    {
      "epoch": 0.004079889937852839,
      "grad_norm": 0.9276201128959656,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.554,
      "step": 43
    },
    {
      "epoch": 0.0041747710991982545,
      "grad_norm": 0.9247840642929077,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.5783,
      "step": 44
    },
    {
      "epoch": 0.004269652260543669,
      "grad_norm": 0.7888846397399902,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.6686,
      "step": 45
    },
    {
      "epoch": 0.004269652260543669,
      "eval_loss": 1.599737524986267,
      "eval_runtime": 1084.3859,
      "eval_samples_per_second": 8.185,
      "eval_steps_per_second": 1.024,
      "step": 45
    },
    {
      "epoch": 0.004364533421889084,
      "grad_norm": 0.8548523187637329,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7366,
      "step": 46
    },
    {
      "epoch": 0.004459414583234499,
      "grad_norm": 0.9126039147377014,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.7126,
      "step": 47
    },
    {
      "epoch": 0.004554295744579914,
      "grad_norm": 0.8707435727119446,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.595,
      "step": 48
    },
    {
      "epoch": 0.004649176905925328,
      "grad_norm": 0.9774793386459351,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.6117,
      "step": 49
    },
    {
      "epoch": 0.0047440580672707434,
      "grad_norm": 0.96619713306427,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.7324,
      "step": 50
    },
    {
      "epoch": 0.0048389392286161586,
      "grad_norm": 1.023463487625122,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.7059,
      "step": 51
    },
    {
      "epoch": 0.004933820389961573,
      "grad_norm": 0.8547558784484863,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5016,
      "step": 52
    },
    {
      "epoch": 0.005028701551306988,
      "grad_norm": 1.066588282585144,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.6275,
      "step": 53
    },
    {
      "epoch": 0.005123582712652403,
      "grad_norm": 0.9226563572883606,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.5763,
      "step": 54
    },
    {
      "epoch": 0.005123582712652403,
      "eval_loss": 1.5895732641220093,
      "eval_runtime": 1085.9797,
      "eval_samples_per_second": 8.173,
      "eval_steps_per_second": 1.022,
      "step": 54
    },
    {
      "epoch": 0.005218463873997818,
      "grad_norm": 0.9529568552970886,
      "learning_rate": 5e-05,
      "loss": 1.4746,
      "step": 55
    },
    {
      "epoch": 0.005313345035343232,
      "grad_norm": 0.9537659883499146,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.5252,
      "step": 56
    },
    {
      "epoch": 0.0054082261966886475,
      "grad_norm": 0.938528299331665,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.6918,
      "step": 57
    },
    {
      "epoch": 0.005503107358034063,
      "grad_norm": 0.8640182614326477,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4192,
      "step": 58
    },
    {
      "epoch": 0.005597988519379477,
      "grad_norm": 0.9006210565567017,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.6865,
      "step": 59
    },
    {
      "epoch": 0.005692869680724892,
      "grad_norm": 0.9384432435035706,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5462,
      "step": 60
    },
    {
      "epoch": 0.005787750842070307,
      "grad_norm": 0.7974855899810791,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.4804,
      "step": 61
    },
    {
      "epoch": 0.005882632003415722,
      "grad_norm": 0.8848018050193787,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.6823,
      "step": 62
    },
    {
      "epoch": 0.005977513164761136,
      "grad_norm": 0.915611743927002,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.6606,
      "step": 63
    },
    {
      "epoch": 0.005977513164761136,
      "eval_loss": 1.5825635194778442,
      "eval_runtime": 1086.2989,
      "eval_samples_per_second": 8.171,
      "eval_steps_per_second": 1.022,
      "step": 63
    },
    {
      "epoch": 0.0060723943261065515,
      "grad_norm": 0.8883166313171387,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.51,
      "step": 64
    },
    {
      "epoch": 0.006167275487451967,
      "grad_norm": 0.9482608437538147,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6562,
      "step": 65
    },
    {
      "epoch": 0.006262156648797381,
      "grad_norm": 0.9113356471061707,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4691,
      "step": 66
    },
    {
      "epoch": 0.006357037810142796,
      "grad_norm": 0.863713264465332,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4748,
      "step": 67
    },
    {
      "epoch": 0.006451918971488211,
      "grad_norm": 0.7576276659965515,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.6295,
      "step": 68
    },
    {
      "epoch": 0.006546800132833626,
      "grad_norm": 1.0895142555236816,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8405,
      "step": 69
    },
    {
      "epoch": 0.0066416812941790405,
      "grad_norm": 0.8840911388397217,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.666,
      "step": 70
    },
    {
      "epoch": 0.006736562455524456,
      "grad_norm": 0.8552221059799194,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.4645,
      "step": 71
    },
    {
      "epoch": 0.006831443616869871,
      "grad_norm": 0.9999718070030212,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9506,
      "step": 72
    },
    {
      "epoch": 0.006831443616869871,
      "eval_loss": 1.575843334197998,
      "eval_runtime": 1085.8118,
      "eval_samples_per_second": 8.175,
      "eval_steps_per_second": 1.022,
      "step": 72
    },
    {
      "epoch": 0.006926324778215285,
      "grad_norm": 0.9333106875419617,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.6179,
      "step": 73
    },
    {
      "epoch": 0.0070212059395607,
      "grad_norm": 0.8568230867385864,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.4738,
      "step": 74
    },
    {
      "epoch": 0.007116087100906115,
      "grad_norm": 0.8466446399688721,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.4126,
      "step": 75
    },
    {
      "epoch": 0.00721096826225153,
      "grad_norm": 0.9957802891731262,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.7137,
      "step": 76
    },
    {
      "epoch": 0.0073058494235969445,
      "grad_norm": 0.8167088031768799,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.5226,
      "step": 77
    },
    {
      "epoch": 0.00740073058494236,
      "grad_norm": 0.8567049503326416,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5889,
      "step": 78
    },
    {
      "epoch": 0.007495611746287775,
      "grad_norm": 0.8254848718643188,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.5097,
      "step": 79
    },
    {
      "epoch": 0.00759049290763319,
      "grad_norm": 1.0071043968200684,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7966,
      "step": 80
    },
    {
      "epoch": 0.007685374068978604,
      "grad_norm": 0.8706706166267395,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6111,
      "step": 81
    },
    {
      "epoch": 0.007685374068978604,
      "eval_loss": 1.5721654891967773,
      "eval_runtime": 1086.0032,
      "eval_samples_per_second": 8.173,
      "eval_steps_per_second": 1.022,
      "step": 81
    },
    {
      "epoch": 0.007780255230324019,
      "grad_norm": 0.9305638074874878,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6522,
      "step": 82
    },
    {
      "epoch": 0.007875136391669434,
      "grad_norm": 0.7519930601119995,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.4109,
      "step": 83
    },
    {
      "epoch": 0.007970017553014849,
      "grad_norm": 0.8699010610580444,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7363,
      "step": 84
    },
    {
      "epoch": 0.008064898714360265,
      "grad_norm": 0.8968572020530701,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.6637,
      "step": 85
    },
    {
      "epoch": 0.008159779875705679,
      "grad_norm": 0.8648973703384399,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.5079,
      "step": 86
    },
    {
      "epoch": 0.008254661037051093,
      "grad_norm": 0.8895729780197144,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5252,
      "step": 87
    },
    {
      "epoch": 0.008349542198396509,
      "grad_norm": 0.8378965854644775,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.7974,
      "step": 88
    },
    {
      "epoch": 0.008444423359741923,
      "grad_norm": 0.8197259306907654,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.7134,
      "step": 89
    },
    {
      "epoch": 0.008539304521087338,
      "grad_norm": 0.8713379502296448,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.457,
      "step": 90
    },
    {
      "epoch": 0.008539304521087338,
      "eval_loss": 1.570660948753357,
      "eval_runtime": 1085.8766,
      "eval_samples_per_second": 8.174,
      "eval_steps_per_second": 1.022,
      "step": 90
    },
    {
      "epoch": 0.008634185682432753,
      "grad_norm": 0.8578446507453918,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.4388,
      "step": 91
    },
    {
      "epoch": 0.008729066843778168,
      "grad_norm": 0.9030793309211731,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.5076,
      "step": 92
    },
    {
      "epoch": 0.008823948005123582,
      "grad_norm": 0.898984432220459,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.3373,
      "step": 93
    },
    {
      "epoch": 0.008918829166468998,
      "grad_norm": 0.8677286505699158,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.4457,
      "step": 94
    },
    {
      "epoch": 0.009013710327814412,
      "grad_norm": 0.8072497844696045,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.2907,
      "step": 95
    },
    {
      "epoch": 0.009108591489159828,
      "grad_norm": 0.9417414665222168,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.5188,
      "step": 96
    },
    {
      "epoch": 0.009203472650505242,
      "grad_norm": 0.8864390254020691,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.6006,
      "step": 97
    },
    {
      "epoch": 0.009298353811850657,
      "grad_norm": 0.8669371604919434,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.5055,
      "step": 98
    },
    {
      "epoch": 0.009393234973196073,
      "grad_norm": 0.8430877327919006,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.352,
      "step": 99
    },
    {
      "epoch": 0.009393234973196073,
      "eval_loss": 1.5703389644622803,
      "eval_runtime": 1085.4904,
      "eval_samples_per_second": 8.177,
      "eval_steps_per_second": 1.023,
      "step": 99
    },
    {
      "epoch": 0.009488116134541487,
      "grad_norm": 0.8918697834014893,
      "learning_rate": 0.0,
      "loss": 1.4941,
      "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": 7.41887686213632e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}