{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025214321734745335,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033619095646327115,
      "grad_norm": 0.10730858892202377,
      "learning_rate": 1e-05,
      "loss": 1.2476,
      "step": 1
    },
    {
      "epoch": 0.00033619095646327115,
      "eval_loss": 0.4694666266441345,
      "eval_runtime": 519.4413,
      "eval_samples_per_second": 4.822,
      "eval_steps_per_second": 0.604,
      "step": 1
    },
    {
      "epoch": 0.0006723819129265423,
      "grad_norm": 0.1259564310312271,
      "learning_rate": 2e-05,
      "loss": 1.1416,
      "step": 2
    },
    {
      "epoch": 0.0010085728693898135,
      "grad_norm": 0.14729371666908264,
      "learning_rate": 3e-05,
      "loss": 0.8194,
      "step": 3
    },
    {
      "epoch": 0.0013447638258530846,
      "grad_norm": 0.12723466753959656,
      "learning_rate": 4e-05,
      "loss": 0.7933,
      "step": 4
    },
    {
      "epoch": 0.0016809547823163557,
      "grad_norm": 0.09622741490602493,
      "learning_rate": 5e-05,
      "loss": 0.8939,
      "step": 5
    },
    {
      "epoch": 0.002017145738779627,
      "grad_norm": 0.12448238581418991,
      "learning_rate": 6e-05,
      "loss": 1.1703,
      "step": 6
    },
    {
      "epoch": 0.002353336695242898,
      "grad_norm": 0.12984026968479156,
      "learning_rate": 7e-05,
      "loss": 1.0056,
      "step": 7
    },
    {
      "epoch": 0.002689527651706169,
      "grad_norm": 0.10037598758935928,
      "learning_rate": 8e-05,
      "loss": 1.0172,
      "step": 8
    },
    {
      "epoch": 0.0030257186081694403,
      "grad_norm": 0.16960003972053528,
      "learning_rate": 9e-05,
      "loss": 0.9901,
      "step": 9
    },
    {
      "epoch": 0.0030257186081694403,
      "eval_loss": 0.45871731638908386,
      "eval_runtime": 520.5305,
      "eval_samples_per_second": 4.812,
      "eval_steps_per_second": 0.603,
      "step": 9
    },
    {
      "epoch": 0.0033619095646327114,
      "grad_norm": 0.11391803622245789,
      "learning_rate": 0.0001,
      "loss": 0.747,
      "step": 10
    },
    {
      "epoch": 0.0036981005210959825,
      "grad_norm": 0.12835194170475006,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8036,
      "step": 11
    },
    {
      "epoch": 0.004034291477559254,
      "grad_norm": 0.15800194442272186,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.821,
      "step": 12
    },
    {
      "epoch": 0.004370482434022525,
      "grad_norm": 0.1520373374223709,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1576,
      "step": 13
    },
    {
      "epoch": 0.004706673390485796,
      "grad_norm": 0.11342062056064606,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8558,
      "step": 14
    },
    {
      "epoch": 0.005042864346949067,
      "grad_norm": 0.1125694215297699,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.809,
      "step": 15
    },
    {
      "epoch": 0.005379055303412338,
      "grad_norm": 0.09935540705919266,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.8306,
      "step": 16
    },
    {
      "epoch": 0.005715246259875609,
      "grad_norm": 0.10935939103364944,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.9415,
      "step": 17
    },
    {
      "epoch": 0.006051437216338881,
      "grad_norm": 0.1281980276107788,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.0971,
      "step": 18
    },
    {
      "epoch": 0.006051437216338881,
      "eval_loss": 0.4295453429222107,
      "eval_runtime": 520.1874,
      "eval_samples_per_second": 4.816,
      "eval_steps_per_second": 0.604,
      "step": 18
    },
    {
      "epoch": 0.006387628172802151,
      "grad_norm": 0.14010263979434967,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8776,
      "step": 19
    },
    {
      "epoch": 0.006723819129265423,
      "grad_norm": 0.13674810528755188,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.9476,
      "step": 20
    },
    {
      "epoch": 0.0070600100857286935,
      "grad_norm": 0.1213589459657669,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.8023,
      "step": 21
    },
    {
      "epoch": 0.007396201042191965,
      "grad_norm": 0.11117886006832123,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8448,
      "step": 22
    },
    {
      "epoch": 0.0077323919986552365,
      "grad_norm": 0.17285647988319397,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.9852,
      "step": 23
    },
    {
      "epoch": 0.008068582955118508,
      "grad_norm": 0.14396902918815613,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.837,
      "step": 24
    },
    {
      "epoch": 0.008404773911581778,
      "grad_norm": 0.17633315920829773,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9313,
      "step": 25
    },
    {
      "epoch": 0.00874096486804505,
      "grad_norm": 0.14555157721042633,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.0778,
      "step": 26
    },
    {
      "epoch": 0.009077155824508321,
      "grad_norm": 0.213585764169693,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.0392,
      "step": 27
    },
    {
      "epoch": 0.009077155824508321,
      "eval_loss": 0.4172186851501465,
      "eval_runtime": 520.3435,
      "eval_samples_per_second": 4.814,
      "eval_steps_per_second": 0.603,
      "step": 27
    },
    {
      "epoch": 0.009413346780971592,
      "grad_norm": 0.13581795990467072,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9057,
      "step": 28
    },
    {
      "epoch": 0.009749537737434862,
      "grad_norm": 0.13606233894824982,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.834,
      "step": 29
    },
    {
      "epoch": 0.010085728693898134,
      "grad_norm": 0.10573849827051163,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7095,
      "step": 30
    },
    {
      "epoch": 0.010421919650361405,
      "grad_norm": 0.1352711021900177,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8305,
      "step": 31
    },
    {
      "epoch": 0.010758110606824677,
      "grad_norm": 0.1466984897851944,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1909,
      "step": 32
    },
    {
      "epoch": 0.011094301563287948,
      "grad_norm": 0.1325143724679947,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9531,
      "step": 33
    },
    {
      "epoch": 0.011430492519751218,
      "grad_norm": 0.12995202839374542,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7252,
      "step": 34
    },
    {
      "epoch": 0.01176668347621449,
      "grad_norm": 0.14775383472442627,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.9489,
      "step": 35
    },
    {
      "epoch": 0.012102874432677761,
      "grad_norm": 0.12643499672412872,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.8091,
      "step": 36
    },
    {
      "epoch": 0.012102874432677761,
      "eval_loss": 0.4073251187801361,
      "eval_runtime": 520.2573,
      "eval_samples_per_second": 4.815,
      "eval_steps_per_second": 0.604,
      "step": 36
    },
    {
      "epoch": 0.012439065389141033,
      "grad_norm": 0.14514999091625214,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8325,
      "step": 37
    },
    {
      "epoch": 0.012775256345604303,
      "grad_norm": 0.1432967633008957,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.8276,
      "step": 38
    },
    {
      "epoch": 0.013111447302067574,
      "grad_norm": 0.1540251523256302,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.877,
      "step": 39
    },
    {
      "epoch": 0.013447638258530846,
      "grad_norm": 0.15357555449008942,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.803,
      "step": 40
    },
    {
      "epoch": 0.013783829214994117,
      "grad_norm": 0.1181618869304657,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8035,
      "step": 41
    },
    {
      "epoch": 0.014120020171457387,
      "grad_norm": 0.14073234796524048,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7444,
      "step": 42
    },
    {
      "epoch": 0.014456211127920659,
      "grad_norm": 0.13493859767913818,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.9286,
      "step": 43
    },
    {
      "epoch": 0.01479240208438393,
      "grad_norm": 0.12726479768753052,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.733,
      "step": 44
    },
    {
      "epoch": 0.015128593040847202,
      "grad_norm": 0.1429787576198578,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.686,
      "step": 45
    },
    {
      "epoch": 0.015128593040847202,
      "eval_loss": 0.39961525797843933,
      "eval_runtime": 520.1231,
      "eval_samples_per_second": 4.816,
      "eval_steps_per_second": 0.604,
      "step": 45
    },
    {
      "epoch": 0.015464783997310473,
      "grad_norm": 0.1767192929983139,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.79,
      "step": 46
    },
    {
      "epoch": 0.015800974953773743,
      "grad_norm": 0.1457664966583252,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.082,
      "step": 47
    },
    {
      "epoch": 0.016137165910237016,
      "grad_norm": 0.15917548537254333,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8385,
      "step": 48
    },
    {
      "epoch": 0.016473356866700286,
      "grad_norm": 0.15853087604045868,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.9264,
      "step": 49
    },
    {
      "epoch": 0.016809547823163556,
      "grad_norm": 0.15454040467739105,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.9211,
      "step": 50
    },
    {
      "epoch": 0.01714573877962683,
      "grad_norm": 0.15525253117084503,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.0932,
      "step": 51
    },
    {
      "epoch": 0.0174819297360901,
      "grad_norm": 0.16235189139842987,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8784,
      "step": 52
    },
    {
      "epoch": 0.01781812069255337,
      "grad_norm": 0.15708541870117188,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8008,
      "step": 53
    },
    {
      "epoch": 0.018154311649016642,
      "grad_norm": 0.14517341554164886,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8614,
      "step": 54
    },
    {
      "epoch": 0.018154311649016642,
      "eval_loss": 0.3940263092517853,
      "eval_runtime": 520.2854,
      "eval_samples_per_second": 4.815,
      "eval_steps_per_second": 0.604,
      "step": 54
    },
    {
      "epoch": 0.01849050260547991,
      "grad_norm": 0.14681681990623474,
      "learning_rate": 5e-05,
      "loss": 0.7681,
      "step": 55
    },
    {
      "epoch": 0.018826693561943185,
      "grad_norm": 0.16690337657928467,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8776,
      "step": 56
    },
    {
      "epoch": 0.019162884518406455,
      "grad_norm": 0.1465039998292923,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.8363,
      "step": 57
    },
    {
      "epoch": 0.019499075474869725,
      "grad_norm": 0.14444556832313538,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7682,
      "step": 58
    },
    {
      "epoch": 0.019835266431332998,
      "grad_norm": 0.15662549436092377,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.8127,
      "step": 59
    },
    {
      "epoch": 0.020171457387796268,
      "grad_norm": 0.20951992273330688,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.8957,
      "step": 60
    },
    {
      "epoch": 0.02050764834425954,
      "grad_norm": 0.14374086260795593,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.5995,
      "step": 61
    },
    {
      "epoch": 0.02084383930072281,
      "grad_norm": 0.16216455399990082,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.8144,
      "step": 62
    },
    {
      "epoch": 0.02118003025718608,
      "grad_norm": 0.19871731102466583,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9087,
      "step": 63
    },
    {
      "epoch": 0.02118003025718608,
      "eval_loss": 0.38950610160827637,
      "eval_runtime": 520.3691,
      "eval_samples_per_second": 4.814,
      "eval_steps_per_second": 0.603,
      "step": 63
    },
    {
      "epoch": 0.021516221213649354,
      "grad_norm": 0.17969125509262085,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8345,
      "step": 64
    },
    {
      "epoch": 0.021852412170112624,
      "grad_norm": 0.1704406887292862,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0127,
      "step": 65
    },
    {
      "epoch": 0.022188603126575897,
      "grad_norm": 0.1846325546503067,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.6452,
      "step": 66
    },
    {
      "epoch": 0.022524794083039167,
      "grad_norm": 0.17157776653766632,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8627,
      "step": 67
    },
    {
      "epoch": 0.022860985039502436,
      "grad_norm": 0.16123242676258087,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0274,
      "step": 68
    },
    {
      "epoch": 0.02319717599596571,
      "grad_norm": 0.1710616648197174,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.85,
      "step": 69
    },
    {
      "epoch": 0.02353336695242898,
      "grad_norm": 0.1854245364665985,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6882,
      "step": 70
    },
    {
      "epoch": 0.02386955790889225,
      "grad_norm": 0.17862558364868164,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.0612,
      "step": 71
    },
    {
      "epoch": 0.024205748865355523,
      "grad_norm": 0.15848234295845032,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.6429,
      "step": 72
    },
    {
      "epoch": 0.024205748865355523,
      "eval_loss": 0.3867124319076538,
      "eval_runtime": 520.5242,
      "eval_samples_per_second": 4.812,
      "eval_steps_per_second": 0.603,
      "step": 72
    },
    {
      "epoch": 0.024541939821818792,
      "grad_norm": 0.24715834856033325,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0981,
      "step": 73
    },
    {
      "epoch": 0.024878130778282066,
      "grad_norm": 0.17577554285526276,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8896,
      "step": 74
    },
    {
      "epoch": 0.025214321734745335,
      "grad_norm": 0.1859356015920639,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.6978,
      "step": 75
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.5217449435136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}