{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021669254938784355,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002889233991837914,
      "grad_norm": 66.85765075683594,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 26.6527,
      "step": 1
    },
    {
      "epoch": 0.0002889233991837914,
      "eval_loss": 4.310550689697266,
      "eval_runtime": 990.545,
      "eval_samples_per_second": 2.943,
      "eval_steps_per_second": 1.472,
      "step": 1
    },
    {
      "epoch": 0.0005778467983675828,
      "grad_norm": 73.37711334228516,
      "learning_rate": 6.666666666666667e-05,
      "loss": 43.7611,
      "step": 2
    },
    {
      "epoch": 0.0008667701975513742,
      "grad_norm": 65.6069107055664,
      "learning_rate": 0.0001,
      "loss": 26.0857,
      "step": 3
    },
    {
      "epoch": 0.0011556935967351656,
      "grad_norm": 59.228843688964844,
      "learning_rate": 9.99524110790929e-05,
      "loss": 28.3396,
      "step": 4
    },
    {
      "epoch": 0.001444616995918957,
      "grad_norm": 24.407468795776367,
      "learning_rate": 9.980973490458728e-05,
      "loss": 22.8091,
      "step": 5
    },
    {
      "epoch": 0.0017335403951027485,
      "grad_norm": 19.40464973449707,
      "learning_rate": 9.957224306869053e-05,
      "loss": 21.675,
      "step": 6
    },
    {
      "epoch": 0.0020224637942865397,
      "grad_norm": 21.251638412475586,
      "learning_rate": 9.924038765061042e-05,
      "loss": 17.9579,
      "step": 7
    },
    {
      "epoch": 0.002311387193470331,
      "grad_norm": 41.2540168762207,
      "learning_rate": 9.881480035599667e-05,
      "loss": 16.5047,
      "step": 8
    },
    {
      "epoch": 0.0026003105926541226,
      "grad_norm": 22.907991409301758,
      "learning_rate": 9.829629131445342e-05,
      "loss": 15.6627,
      "step": 9
    },
    {
      "epoch": 0.002889233991837914,
      "grad_norm": 37.04414367675781,
      "learning_rate": 9.768584753741134e-05,
      "loss": 17.3563,
      "step": 10
    },
    {
      "epoch": 0.0031781573910217055,
      "grad_norm": 21.000375747680664,
      "learning_rate": 9.698463103929542e-05,
      "loss": 14.7146,
      "step": 11
    },
    {
      "epoch": 0.003467080790205497,
      "grad_norm": 18.32266616821289,
      "learning_rate": 9.619397662556435e-05,
      "loss": 12.4842,
      "step": 12
    },
    {
      "epoch": 0.003756004189389288,
      "grad_norm": 27.443967819213867,
      "learning_rate": 9.53153893518325e-05,
      "loss": 10.4003,
      "step": 13
    },
    {
      "epoch": 0.004044927588573079,
      "grad_norm": 42.203514099121094,
      "learning_rate": 9.435054165891109e-05,
      "loss": 8.0634,
      "step": 14
    },
    {
      "epoch": 0.004333850987756871,
      "grad_norm": 162.54161071777344,
      "learning_rate": 9.330127018922194e-05,
      "loss": 12.063,
      "step": 15
    },
    {
      "epoch": 0.004622774386940662,
      "grad_norm": 36.060081481933594,
      "learning_rate": 9.21695722906443e-05,
      "loss": 8.8787,
      "step": 16
    },
    {
      "epoch": 0.004911697786124454,
      "grad_norm": 52.42499923706055,
      "learning_rate": 9.09576022144496e-05,
      "loss": 8.1511,
      "step": 17
    },
    {
      "epoch": 0.005200621185308245,
      "grad_norm": 49.18842697143555,
      "learning_rate": 8.966766701456177e-05,
      "loss": 6.8164,
      "step": 18
    },
    {
      "epoch": 0.005489544584492036,
      "grad_norm": 28.918075561523438,
      "learning_rate": 8.83022221559489e-05,
      "loss": 7.1671,
      "step": 19
    },
    {
      "epoch": 0.005778467983675828,
      "grad_norm": 18.048503875732422,
      "learning_rate": 8.68638668405062e-05,
      "loss": 8.5257,
      "step": 20
    },
    {
      "epoch": 0.006067391382859619,
      "grad_norm": 18.87720489501953,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.431,
      "step": 21
    },
    {
      "epoch": 0.006356314782043411,
      "grad_norm": 19.41789436340332,
      "learning_rate": 8.377951038078302e-05,
      "loss": 7.1162,
      "step": 22
    },
    {
      "epoch": 0.006645238181227202,
      "grad_norm": 19.061424255371094,
      "learning_rate": 8.213938048432697e-05,
      "loss": 7.5901,
      "step": 23
    },
    {
      "epoch": 0.006934161580410994,
      "grad_norm": 16.62812614440918,
      "learning_rate": 8.043807145043604e-05,
      "loss": 5.7933,
      "step": 24
    },
    {
      "epoch": 0.007223084979594785,
      "grad_norm": 28.045270919799805,
      "learning_rate": 7.86788218175523e-05,
      "loss": 6.6255,
      "step": 25
    },
    {
      "epoch": 0.007223084979594785,
      "eval_loss": 1.1299744844436646,
      "eval_runtime": 994.88,
      "eval_samples_per_second": 2.93,
      "eval_steps_per_second": 1.466,
      "step": 25
    },
    {
      "epoch": 0.007512008378778576,
      "grad_norm": 18.70418357849121,
      "learning_rate": 7.68649804173412e-05,
      "loss": 8.0266,
      "step": 26
    },
    {
      "epoch": 0.007800931777962368,
      "grad_norm": 29.825096130371094,
      "learning_rate": 7.500000000000001e-05,
      "loss": 9.148,
      "step": 27
    },
    {
      "epoch": 0.008089855177146159,
      "grad_norm": 52.200557708740234,
      "learning_rate": 7.308743066175172e-05,
      "loss": 7.8062,
      "step": 28
    },
    {
      "epoch": 0.00837877857632995,
      "grad_norm": 35.42280197143555,
      "learning_rate": 7.113091308703498e-05,
      "loss": 7.3871,
      "step": 29
    },
    {
      "epoch": 0.008667701975513743,
      "grad_norm": 41.86412048339844,
      "learning_rate": 6.91341716182545e-05,
      "loss": 7.6188,
      "step": 30
    },
    {
      "epoch": 0.008956625374697533,
      "grad_norm": 27.898130416870117,
      "learning_rate": 6.710100716628344e-05,
      "loss": 8.1271,
      "step": 31
    },
    {
      "epoch": 0.009245548773881325,
      "grad_norm": 21.139310836791992,
      "learning_rate": 6.503528997521366e-05,
      "loss": 5.1898,
      "step": 32
    },
    {
      "epoch": 0.009534472173065116,
      "grad_norm": 24.908050537109375,
      "learning_rate": 6.294095225512603e-05,
      "loss": 6.0579,
      "step": 33
    },
    {
      "epoch": 0.009823395572248908,
      "grad_norm": 46.74921798706055,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 7.2563,
      "step": 34
    },
    {
      "epoch": 0.010112318971432699,
      "grad_norm": 156.18777465820312,
      "learning_rate": 5.868240888334653e-05,
      "loss": 11.1945,
      "step": 35
    },
    {
      "epoch": 0.01040124237061649,
      "grad_norm": 38.862464904785156,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 7.6352,
      "step": 36
    },
    {
      "epoch": 0.010690165769800282,
      "grad_norm": 47.18630599975586,
      "learning_rate": 5.435778713738292e-05,
      "loss": 6.7799,
      "step": 37
    },
    {
      "epoch": 0.010979089168984072,
      "grad_norm": 24.2867431640625,
      "learning_rate": 5.218096936826681e-05,
      "loss": 5.5195,
      "step": 38
    },
    {
      "epoch": 0.011268012568167864,
      "grad_norm": 30.565311431884766,
      "learning_rate": 5e-05,
      "loss": 6.0461,
      "step": 39
    },
    {
      "epoch": 0.011556935967351656,
      "grad_norm": 28.035436630249023,
      "learning_rate": 4.781903063173321e-05,
      "loss": 6.4751,
      "step": 40
    },
    {
      "epoch": 0.011845859366535448,
      "grad_norm": 31.523160934448242,
      "learning_rate": 4.564221286261709e-05,
      "loss": 7.083,
      "step": 41
    },
    {
      "epoch": 0.012134782765719238,
      "grad_norm": 33.626914978027344,
      "learning_rate": 4.347369038899744e-05,
      "loss": 6.0292,
      "step": 42
    },
    {
      "epoch": 0.01242370616490303,
      "grad_norm": 46.72255325317383,
      "learning_rate": 4.131759111665349e-05,
      "loss": 7.6237,
      "step": 43
    },
    {
      "epoch": 0.012712629564086822,
      "grad_norm": 33.627716064453125,
      "learning_rate": 3.917801930309486e-05,
      "loss": 7.184,
      "step": 44
    },
    {
      "epoch": 0.013001552963270612,
      "grad_norm": 27.371572494506836,
      "learning_rate": 3.705904774487396e-05,
      "loss": 6.2984,
      "step": 45
    },
    {
      "epoch": 0.013290476362454404,
      "grad_norm": 37.012481689453125,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 5.5282,
      "step": 46
    },
    {
      "epoch": 0.013579399761638196,
      "grad_norm": 25.040252685546875,
      "learning_rate": 3.289899283371657e-05,
      "loss": 5.8425,
      "step": 47
    },
    {
      "epoch": 0.013868323160821988,
      "grad_norm": 53.89478302001953,
      "learning_rate": 3.086582838174551e-05,
      "loss": 9.8582,
      "step": 48
    },
    {
      "epoch": 0.014157246560005778,
      "grad_norm": 74.33063507080078,
      "learning_rate": 2.886908691296504e-05,
      "loss": 10.6698,
      "step": 49
    },
    {
      "epoch": 0.01444616995918957,
      "grad_norm": 55.97947311401367,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 6.7913,
      "step": 50
    },
    {
      "epoch": 0.01444616995918957,
      "eval_loss": 0.7597658038139343,
      "eval_runtime": 996.114,
      "eval_samples_per_second": 2.926,
      "eval_steps_per_second": 1.464,
      "step": 50
    },
    {
      "epoch": 0.014735093358373362,
      "grad_norm": 26.76323699951172,
      "learning_rate": 2.500000000000001e-05,
      "loss": 5.3221,
      "step": 51
    },
    {
      "epoch": 0.015024016757557152,
      "grad_norm": 40.71314239501953,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 7.0028,
      "step": 52
    },
    {
      "epoch": 0.015312940156740944,
      "grad_norm": 18.181428909301758,
      "learning_rate": 2.132117818244771e-05,
      "loss": 5.6947,
      "step": 53
    },
    {
      "epoch": 0.015601863555924736,
      "grad_norm": 23.002670288085938,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 6.155,
      "step": 54
    },
    {
      "epoch": 0.015890786955108527,
      "grad_norm": 18.26033592224121,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 5.6797,
      "step": 55
    },
    {
      "epoch": 0.016179710354292318,
      "grad_norm": 14.501717567443848,
      "learning_rate": 1.622048961921699e-05,
      "loss": 4.742,
      "step": 56
    },
    {
      "epoch": 0.01646863375347611,
      "grad_norm": 17.230289459228516,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 6.2838,
      "step": 57
    },
    {
      "epoch": 0.0167575571526599,
      "grad_norm": 14.124578475952148,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 5.8269,
      "step": 58
    },
    {
      "epoch": 0.01704648055184369,
      "grad_norm": 20.78701400756836,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 6.3414,
      "step": 59
    },
    {
      "epoch": 0.017335403951027485,
      "grad_norm": 13.879270553588867,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 4.1704,
      "step": 60
    },
    {
      "epoch": 0.017624327350211275,
      "grad_norm": 13.16641902923584,
      "learning_rate": 9.042397785550405e-06,
      "loss": 4.4702,
      "step": 61
    },
    {
      "epoch": 0.017913250749395065,
      "grad_norm": 12.741442680358887,
      "learning_rate": 7.830427709355725e-06,
      "loss": 4.0511,
      "step": 62
    },
    {
      "epoch": 0.01820217414857886,
      "grad_norm": 12.697881698608398,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.0318,
      "step": 63
    },
    {
      "epoch": 0.01849109754776265,
      "grad_norm": 19.755266189575195,
      "learning_rate": 5.649458341088915e-06,
      "loss": 3.4955,
      "step": 64
    },
    {
      "epoch": 0.01878002094694644,
      "grad_norm": 17.082738876342773,
      "learning_rate": 4.684610648167503e-06,
      "loss": 5.3582,
      "step": 65
    },
    {
      "epoch": 0.019068944346130233,
      "grad_norm": 15.043936729431152,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.0782,
      "step": 66
    },
    {
      "epoch": 0.019357867745314023,
      "grad_norm": 24.604942321777344,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.5255,
      "step": 67
    },
    {
      "epoch": 0.019646791144497817,
      "grad_norm": 13.922004699707031,
      "learning_rate": 2.314152462588659e-06,
      "loss": 4.1978,
      "step": 68
    },
    {
      "epoch": 0.019935714543681607,
      "grad_norm": 13.740044593811035,
      "learning_rate": 1.70370868554659e-06,
      "loss": 4.8924,
      "step": 69
    },
    {
      "epoch": 0.020224637942865397,
      "grad_norm": 12.760802268981934,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 4.1786,
      "step": 70
    },
    {
      "epoch": 0.02051356134204919,
      "grad_norm": 13.630950927734375,
      "learning_rate": 7.596123493895991e-07,
      "loss": 4.6798,
      "step": 71
    },
    {
      "epoch": 0.02080248474123298,
      "grad_norm": 15.914883613586426,
      "learning_rate": 4.277569313094809e-07,
      "loss": 6.1266,
      "step": 72
    },
    {
      "epoch": 0.02109140814041677,
      "grad_norm": 21.27867889404297,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 3.6778,
      "step": 73
    },
    {
      "epoch": 0.021380331539600565,
      "grad_norm": 16.753841400146484,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 5.9576,
      "step": 74
    },
    {
      "epoch": 0.021669254938784355,
      "grad_norm": 15.862313270568848,
      "learning_rate": 0.0,
      "loss": 3.6563,
      "step": 75
    },
    {
      "epoch": 0.021669254938784355,
      "eval_loss": 0.6312903761863708,
      "eval_runtime": 995.9618,
      "eval_samples_per_second": 2.927,
      "eval_steps_per_second": 1.464,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 9.86091809144832e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}