{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1511144692104269,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007555723460521345,
      "eval_loss": 12.450613975524902,
      "eval_runtime": 61.6454,
      "eval_samples_per_second": 36.175,
      "eval_steps_per_second": 4.526,
      "step": 1
    },
    {
      "epoch": 0.0022667170381564035,
      "grad_norm": 0.009174207225441933,
      "learning_rate": 3e-05,
      "loss": 12.453,
      "step": 3
    },
    {
      "epoch": 0.004533434076312807,
      "grad_norm": 0.009654853492975235,
      "learning_rate": 6e-05,
      "loss": 12.4526,
      "step": 6
    },
    {
      "epoch": 0.00680015111446921,
      "grad_norm": 0.008986242115497589,
      "learning_rate": 9e-05,
      "loss": 12.4507,
      "step": 9
    },
    {
      "epoch": 0.009066868152625614,
      "grad_norm": 0.009755842387676239,
      "learning_rate": 9.997266286704631e-05,
      "loss": 12.4496,
      "step": 12
    },
    {
      "epoch": 0.011333585190782017,
      "grad_norm": 0.011493120342493057,
      "learning_rate": 9.98292246503335e-05,
      "loss": 12.4487,
      "step": 15
    },
    {
      "epoch": 0.012844729882886286,
      "eval_loss": 12.450437545776367,
      "eval_runtime": 61.7871,
      "eval_samples_per_second": 36.092,
      "eval_steps_per_second": 4.516,
      "step": 17
    },
    {
      "epoch": 0.01360030222893842,
      "grad_norm": 0.009524165652692318,
      "learning_rate": 9.956320346634876e-05,
      "loss": 12.454,
      "step": 18
    },
    {
      "epoch": 0.015867019267094825,
      "grad_norm": 0.012806428596377373,
      "learning_rate": 9.917525374361912e-05,
      "loss": 12.4518,
      "step": 21
    },
    {
      "epoch": 0.018133736305251228,
      "grad_norm": 0.011713715270161629,
      "learning_rate": 9.86663298624003e-05,
      "loss": 12.4506,
      "step": 24
    },
    {
      "epoch": 0.02040045334340763,
      "grad_norm": 0.010967453010380268,
      "learning_rate": 9.803768380684242e-05,
      "loss": 12.4491,
      "step": 27
    },
    {
      "epoch": 0.022667170381564034,
      "grad_norm": 0.0131283700466156,
      "learning_rate": 9.729086208503174e-05,
      "loss": 12.4512,
      "step": 30
    },
    {
      "epoch": 0.024933887419720437,
      "grad_norm": 0.012522528879344463,
      "learning_rate": 9.642770192448536e-05,
      "loss": 12.4509,
      "step": 33
    },
    {
      "epoch": 0.02568945976577257,
      "eval_loss": 12.45008373260498,
      "eval_runtime": 61.8082,
      "eval_samples_per_second": 36.079,
      "eval_steps_per_second": 4.514,
      "step": 34
    },
    {
      "epoch": 0.02720060445787684,
      "grad_norm": 0.013970930129289627,
      "learning_rate": 9.545032675245813e-05,
      "loss": 12.4541,
      "step": 36
    },
    {
      "epoch": 0.029467321496033247,
      "grad_norm": 0.014797762967646122,
      "learning_rate": 9.43611409721806e-05,
      "loss": 12.4476,
      "step": 39
    },
    {
      "epoch": 0.03173403853418965,
      "grad_norm": 0.01638209819793701,
      "learning_rate": 9.316282404787871e-05,
      "loss": 12.4498,
      "step": 42
    },
    {
      "epoch": 0.03400075557234605,
      "grad_norm": 0.017414981499314308,
      "learning_rate": 9.185832391312644e-05,
      "loss": 12.4489,
      "step": 45
    },
    {
      "epoch": 0.036267472610502456,
      "grad_norm": 0.01976948417723179,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4498,
      "step": 48
    },
    {
      "epoch": 0.03853418964865886,
      "grad_norm": 0.017705973237752914,
      "learning_rate": 8.894386393810563e-05,
      "loss": 12.4478,
      "step": 51
    },
    {
      "epoch": 0.03853418964865886,
      "eval_loss": 12.449511528015137,
      "eval_runtime": 61.8317,
      "eval_samples_per_second": 36.066,
      "eval_steps_per_second": 4.512,
      "step": 51
    },
    {
      "epoch": 0.04080090668681526,
      "grad_norm": 0.018775586038827896,
      "learning_rate": 8.73410738492077e-05,
      "loss": 12.4476,
      "step": 54
    },
    {
      "epoch": 0.043067623724971665,
      "grad_norm": 0.020082606002688408,
      "learning_rate": 8.564642241456986e-05,
      "loss": 12.4519,
      "step": 57
    },
    {
      "epoch": 0.04533434076312807,
      "grad_norm": 0.01945601962506771,
      "learning_rate": 8.386407858128706e-05,
      "loss": 12.4513,
      "step": 60
    },
    {
      "epoch": 0.04760105780128447,
      "grad_norm": 0.02504323236644268,
      "learning_rate": 8.199842702516583e-05,
      "loss": 12.451,
      "step": 63
    },
    {
      "epoch": 0.049867774839440875,
      "grad_norm": 0.02477116324007511,
      "learning_rate": 8.005405736415126e-05,
      "loss": 12.4508,
      "step": 66
    },
    {
      "epoch": 0.05137891953154514,
      "eval_loss": 12.448628425598145,
      "eval_runtime": 61.7963,
      "eval_samples_per_second": 36.086,
      "eval_steps_per_second": 4.515,
      "step": 68
    },
    {
      "epoch": 0.05213449187759728,
      "grad_norm": 0.02452562004327774,
      "learning_rate": 7.803575286758364e-05,
      "loss": 12.4501,
      "step": 69
    },
    {
      "epoch": 0.05440120891575368,
      "grad_norm": 0.024608276784420013,
      "learning_rate": 7.594847868906076e-05,
      "loss": 12.449,
      "step": 72
    },
    {
      "epoch": 0.056667925953910084,
      "grad_norm": 0.025729818269610405,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.4491,
      "step": 75
    },
    {
      "epoch": 0.058934642992066494,
      "grad_norm": 0.026810096576809883,
      "learning_rate": 7.158771761692464e-05,
      "loss": 12.4492,
      "step": 78
    },
    {
      "epoch": 0.0612013600302229,
      "grad_norm": 0.030193008482456207,
      "learning_rate": 6.932495846462261e-05,
      "loss": 12.4488,
      "step": 81
    },
    {
      "epoch": 0.0634680770683793,
      "grad_norm": 0.0322081558406353,
      "learning_rate": 6.701465872208216e-05,
      "loss": 12.4457,
      "step": 84
    },
    {
      "epoch": 0.06422364941443143,
      "eval_loss": 12.447479248046875,
      "eval_runtime": 61.6601,
      "eval_samples_per_second": 36.166,
      "eval_steps_per_second": 4.525,
      "step": 85
    },
    {
      "epoch": 0.0657347941065357,
      "grad_norm": 0.03805829957127571,
      "learning_rate": 6.466250186922325e-05,
      "loss": 12.4443,
      "step": 87
    },
    {
      "epoch": 0.0680015111446921,
      "grad_norm": 0.03595505282282829,
      "learning_rate": 6.227427435703997e-05,
      "loss": 12.4494,
      "step": 90
    },
    {
      "epoch": 0.0702682281828485,
      "grad_norm": 0.03157583624124527,
      "learning_rate": 5.985585137257401e-05,
      "loss": 12.446,
      "step": 93
    },
    {
      "epoch": 0.07253494522100491,
      "grad_norm": 0.03606283292174339,
      "learning_rate": 5.74131823855921e-05,
      "loss": 12.4462,
      "step": 96
    },
    {
      "epoch": 0.07480166225916131,
      "grad_norm": 0.03671179711818695,
      "learning_rate": 5.495227651252315e-05,
      "loss": 12.4473,
      "step": 99
    },
    {
      "epoch": 0.07706837929731772,
      "grad_norm": 0.042302753776311874,
      "learning_rate": 5.247918773366112e-05,
      "loss": 12.4479,
      "step": 102
    },
    {
      "epoch": 0.07706837929731772,
      "eval_loss": 12.446091651916504,
      "eval_runtime": 61.8106,
      "eval_samples_per_second": 36.078,
      "eval_steps_per_second": 4.514,
      "step": 102
    },
    {
      "epoch": 0.07933509633547413,
      "grad_norm": 0.04813135042786598,
      "learning_rate": 5e-05,
      "loss": 12.4455,
      "step": 105
    },
    {
      "epoch": 0.08160181337363052,
      "grad_norm": 0.046277038753032684,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 12.4466,
      "step": 108
    },
    {
      "epoch": 0.08386853041178693,
      "grad_norm": 0.046285875141620636,
      "learning_rate": 4.504772348747687e-05,
      "loss": 12.4448,
      "step": 111
    },
    {
      "epoch": 0.08613524744994333,
      "grad_norm": 0.051637545228004456,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 12.4436,
      "step": 114
    },
    {
      "epoch": 0.08840196448809974,
      "grad_norm": 0.04436314478516579,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 12.4446,
      "step": 117
    },
    {
      "epoch": 0.08991310918020401,
      "eval_loss": 12.444755554199219,
      "eval_runtime": 61.8074,
      "eval_samples_per_second": 36.08,
      "eval_steps_per_second": 4.514,
      "step": 119
    },
    {
      "epoch": 0.09066868152625614,
      "grad_norm": 0.05455072224140167,
      "learning_rate": 3.772572564296005e-05,
      "loss": 12.4468,
      "step": 120
    },
    {
      "epoch": 0.09293539856441255,
      "grad_norm": 0.05117850750684738,
      "learning_rate": 3.533749813077677e-05,
      "loss": 12.4441,
      "step": 123
    },
    {
      "epoch": 0.09520211560256894,
      "grad_norm": 0.0508827343583107,
      "learning_rate": 3.298534127791785e-05,
      "loss": 12.4432,
      "step": 126
    },
    {
      "epoch": 0.09746883264072535,
      "grad_norm": 0.05112558230757713,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 12.444,
      "step": 129
    },
    {
      "epoch": 0.09973554967888175,
      "grad_norm": 0.05653185769915581,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 12.4435,
      "step": 132
    },
    {
      "epoch": 0.10200226671703816,
      "grad_norm": 0.050629470497369766,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 12.4432,
      "step": 135
    },
    {
      "epoch": 0.10275783906309029,
      "eval_loss": 12.443622589111328,
      "eval_runtime": 61.7899,
      "eval_samples_per_second": 36.09,
      "eval_steps_per_second": 4.515,
      "step": 136
    },
    {
      "epoch": 0.10426898375519456,
      "grad_norm": 0.05781077593564987,
      "learning_rate": 2.405152131093926e-05,
      "loss": 12.4441,
      "step": 138
    },
    {
      "epoch": 0.10653570079335097,
      "grad_norm": 0.05344181880354881,
      "learning_rate": 2.196424713241637e-05,
      "loss": 12.4449,
      "step": 141
    },
    {
      "epoch": 0.10880241783150736,
      "grad_norm": 0.05852736532688141,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 12.4415,
      "step": 144
    },
    {
      "epoch": 0.11106913486966377,
      "grad_norm": 0.05481090024113655,
      "learning_rate": 1.800157297483417e-05,
      "loss": 12.4416,
      "step": 147
    },
    {
      "epoch": 0.11333585190782017,
      "grad_norm": 0.05853069946169853,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 12.4436,
      "step": 150
    },
    {
      "epoch": 0.11560256894597658,
      "grad_norm": 0.05612453445792198,
      "learning_rate": 1.435357758543015e-05,
      "loss": 12.4425,
      "step": 153
    },
    {
      "epoch": 0.11560256894597658,
      "eval_loss": 12.44286060333252,
      "eval_runtime": 61.813,
      "eval_samples_per_second": 36.077,
      "eval_steps_per_second": 4.514,
      "step": 153
    },
    {
      "epoch": 0.11786928598413299,
      "grad_norm": 0.05935904011130333,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 12.4428,
      "step": 156
    },
    {
      "epoch": 0.12013600302228938,
      "grad_norm": 0.06513120234012604,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 12.4436,
      "step": 159
    },
    {
      "epoch": 0.1224027200604458,
      "grad_norm": 0.060658689588308334,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.4426,
      "step": 162
    },
    {
      "epoch": 0.12466943709860219,
      "grad_norm": 0.06469012796878815,
      "learning_rate": 8.141676086873572e-06,
      "loss": 12.4421,
      "step": 165
    },
    {
      "epoch": 0.1269361541367586,
      "grad_norm": 0.05972781777381897,
      "learning_rate": 6.837175952121306e-06,
      "loss": 12.4421,
      "step": 168
    },
    {
      "epoch": 0.12844729882886285,
      "eval_loss": 12.442495346069336,
      "eval_runtime": 61.8344,
      "eval_samples_per_second": 36.064,
      "eval_steps_per_second": 4.512,
      "step": 170
    },
    {
      "epoch": 0.129202871174915,
      "grad_norm": 0.06537988781929016,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 12.4418,
      "step": 171
    },
    {
      "epoch": 0.1314695882130714,
      "grad_norm": 0.052994538098573685,
      "learning_rate": 4.549673247541875e-06,
      "loss": 12.4399,
      "step": 174
    },
    {
      "epoch": 0.13373630525122782,
      "grad_norm": 0.061471715569496155,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 12.4436,
      "step": 177
    },
    {
      "epoch": 0.1360030222893842,
      "grad_norm": 0.057937003672122955,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 12.4452,
      "step": 180
    },
    {
      "epoch": 0.1382697393275406,
      "grad_norm": 0.06667575240135193,
      "learning_rate": 1.962316193157593e-06,
      "loss": 12.439,
      "step": 183
    },
    {
      "epoch": 0.140536456365697,
      "grad_norm": 0.05928559973835945,
      "learning_rate": 1.333670137599713e-06,
      "loss": 12.4442,
      "step": 186
    },
    {
      "epoch": 0.14129202871174915,
      "eval_loss": 12.44235610961914,
      "eval_runtime": 61.7029,
      "eval_samples_per_second": 36.141,
      "eval_steps_per_second": 4.522,
      "step": 187
    },
    {
      "epoch": 0.14280317340385343,
      "grad_norm": 0.0606582872569561,
      "learning_rate": 8.247462563808817e-07,
      "loss": 12.4418,
      "step": 189
    },
    {
      "epoch": 0.14506989044200982,
      "grad_norm": 0.06177810579538345,
      "learning_rate": 4.367965336512403e-07,
      "loss": 12.4451,
      "step": 192
    },
    {
      "epoch": 0.14733660748016622,
      "grad_norm": 0.05963071435689926,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 12.4409,
      "step": 195
    },
    {
      "epoch": 0.14960332451832262,
      "grad_norm": 0.06588052958250046,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 12.4448,
      "step": 198
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 442692009984.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}