{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.888888888888889,
  "eval_steps": 500,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 6.797902417315128,
      "learning_rate": 1e-07,
      "loss": 0.9441,
      "step": 1
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 7.317497008148059,
      "learning_rate": 2e-07,
      "loss": 0.953,
      "step": 2
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 8.84997688747691,
      "learning_rate": 1.9987954562051723e-07,
      "loss": 1.0895,
      "step": 3
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 6.835460415178357,
      "learning_rate": 1.9951847266721968e-07,
      "loss": 0.9701,
      "step": 4
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 6.676973263423372,
      "learning_rate": 1.989176509964781e-07,
      "loss": 0.9841,
      "step": 5
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 8.496174663508192,
      "learning_rate": 1.9807852804032302e-07,
      "loss": 1.2296,
      "step": 6
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 7.680554628706011,
      "learning_rate": 1.970031253194544e-07,
      "loss": 1.0875,
      "step": 7
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 5.801217073567055,
      "learning_rate": 1.9569403357322088e-07,
      "loss": 0.7655,
      "step": 8
    },
    {
      "epoch": 0.4,
      "grad_norm": 8.13494114077952,
      "learning_rate": 1.9415440651830205e-07,
      "loss": 0.9572,
      "step": 9
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 7.362762295757269,
      "learning_rate": 1.9238795325112868e-07,
      "loss": 1.0439,
      "step": 10
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 5.212536078393568,
      "learning_rate": 1.9039892931234434e-07,
      "loss": 0.8029,
      "step": 11
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 16.43591823675137,
      "learning_rate": 1.8819212643483548e-07,
      "loss": 1.1343,
      "step": 12
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 8.173432004465319,
      "learning_rate": 1.8577286100002721e-07,
      "loss": 1.1107,
      "step": 13
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 5.675717610095781,
      "learning_rate": 1.8314696123025453e-07,
      "loss": 0.7825,
      "step": 14
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 6.959693318774922,
      "learning_rate": 1.8032075314806448e-07,
      "loss": 1.0535,
      "step": 15
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 12.458896566613497,
      "learning_rate": 1.7730104533627368e-07,
      "loss": 1.0818,
      "step": 16
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 7.51563574554633,
      "learning_rate": 1.740951125354959e-07,
      "loss": 1.0944,
      "step": 17
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.864529971037087,
      "learning_rate": 1.7071067811865473e-07,
      "loss": 0.7612,
      "step": 18
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 5.294393611658585,
      "learning_rate": 1.6715589548470183e-07,
      "loss": 0.7545,
      "step": 19
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 5.706241552655717,
      "learning_rate": 1.6343932841636453e-07,
      "loss": 0.7645,
      "step": 20
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 8.162680497729468,
      "learning_rate": 1.5956993044924333e-07,
      "loss": 1.0373,
      "step": 21
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 6.589458525146248,
      "learning_rate": 1.555570233019602e-07,
      "loss": 0.9356,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.589458525146248,
      "learning_rate": 1.5141027441932214e-07,
      "loss": 0.3931,
      "step": 23
    },
    {
      "epoch": 1.0444444444444445,
      "grad_norm": 7.5673766425728894,
      "learning_rate": 1.4713967368259978e-07,
      "loss": 0.7689,
      "step": 24
    },
    {
      "epoch": 1.0888888888888888,
      "grad_norm": 4.535866779916758,
      "learning_rate": 1.427555093430282e-07,
      "loss": 0.7715,
      "step": 25
    },
    {
      "epoch": 1.1333333333333333,
      "grad_norm": 10.236141110920356,
      "learning_rate": 1.3826834323650897e-07,
      "loss": 1.2028,
      "step": 26
    },
    {
      "epoch": 1.1777777777777778,
      "grad_norm": 10.607887336341987,
      "learning_rate": 1.33688985339222e-07,
      "loss": 0.9263,
      "step": 27
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 4.031737656519255,
      "learning_rate": 1.2902846772544622e-07,
      "loss": 0.7387,
      "step": 28
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 7.0329979315278255,
      "learning_rate": 1.2429801799032639e-07,
      "loss": 0.9234,
      "step": 29
    },
    {
      "epoch": 1.3111111111111111,
      "grad_norm": 5.547532142709396,
      "learning_rate": 1.1950903220161285e-07,
      "loss": 0.9003,
      "step": 30
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 4.273553268294401,
      "learning_rate": 1.1467304744553616e-07,
      "loss": 0.7408,
      "step": 31
    },
    {
      "epoch": 1.4,
      "grad_norm": 5.086045947842683,
      "learning_rate": 1.0980171403295608e-07,
      "loss": 1.2078,
      "step": 32
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 8.571669975116441,
      "learning_rate": 1.049067674327418e-07,
      "loss": 1.0827,
      "step": 33
    },
    {
      "epoch": 1.488888888888889,
      "grad_norm": 5.45172009606907,
      "learning_rate": 1e-07,
      "loss": 0.7224,
      "step": 34
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 6.031359968900742,
      "learning_rate": 9.50932325672582e-08,
      "loss": 0.9339,
      "step": 35
    },
    {
      "epoch": 1.5777777777777777,
      "grad_norm": 6.591510026067283,
      "learning_rate": 9.019828596704394e-08,
      "loss": 0.897,
      "step": 36
    },
    {
      "epoch": 1.6222222222222222,
      "grad_norm": 4.544983876264793,
      "learning_rate": 8.532695255446383e-08,
      "loss": 0.7406,
      "step": 37
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 4.073713187648033,
      "learning_rate": 8.049096779838717e-08,
      "loss": 0.7707,
      "step": 38
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 4.9974512325292455,
      "learning_rate": 7.570198200967362e-08,
      "loss": 1.0792,
      "step": 39
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 5.533485984999249,
      "learning_rate": 7.097153227455378e-08,
      "loss": 0.963,
      "step": 40
    },
    {
      "epoch": 1.8,
      "grad_norm": 10.19605878289518,
      "learning_rate": 6.6311014660778e-08,
      "loss": 0.7446,
      "step": 41
    },
    {
      "epoch": 1.8444444444444446,
      "grad_norm": 7.048961200332261,
      "learning_rate": 6.173165676349102e-08,
      "loss": 1.0592,
      "step": 42
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 6.093522827406117,
      "learning_rate": 5.7244490656971814e-08,
      "loss": 0.7403,
      "step": 43
    },
    {
      "epoch": 1.9333333333333333,
      "grad_norm": 5.213484794244025,
      "learning_rate": 5.286032631740023e-08,
      "loss": 1.0942,
      "step": 44
    },
    {
      "epoch": 1.9777777777777779,
      "grad_norm": 7.698604540853907,
      "learning_rate": 4.8589725580677834e-08,
      "loss": 1.0798,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.33633734624949,
      "learning_rate": 4.44429766980398e-08,
      "loss": 0.5624,
      "step": 46
    },
    {
      "epoch": 2.0444444444444443,
      "grad_norm": 5.709043294257629,
      "learning_rate": 4.043006955075666e-08,
      "loss": 0.9354,
      "step": 47
    },
    {
      "epoch": 2.088888888888889,
      "grad_norm": 4.14210763973087,
      "learning_rate": 3.656067158363546e-08,
      "loss": 0.7606,
      "step": 48
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 4.94132722485472,
      "learning_rate": 3.284410451529816e-08,
      "loss": 0.8826,
      "step": 49
    },
    {
      "epoch": 2.1777777777777776,
      "grad_norm": 7.777154196014082,
      "learning_rate": 2.928932188134525e-08,
      "loss": 1.1904,
      "step": 50
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 4.245492909879899,
      "learning_rate": 2.590488746450411e-08,
      "loss": 0.7593,
      "step": 51
    },
    {
      "epoch": 2.2666666666666666,
      "grad_norm": 6.145727347455345,
      "learning_rate": 2.26989546637263e-08,
      "loss": 0.9285,
      "step": 52
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 5.473956690076734,
      "learning_rate": 1.9679246851935517e-08,
      "loss": 0.9378,
      "step": 53
    },
    {
      "epoch": 2.3555555555555556,
      "grad_norm": 7.4602800223042545,
      "learning_rate": 1.6853038769745463e-08,
      "loss": 1.1818,
      "step": 54
    },
    {
      "epoch": 2.4,
      "grad_norm": 8.1186620326781,
      "learning_rate": 1.42271389999728e-08,
      "loss": 1.1918,
      "step": 55
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 5.25818516018029,
      "learning_rate": 1.1807873565164506e-08,
      "loss": 0.9272,
      "step": 56
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 3.7198017971600605,
      "learning_rate": 9.601070687655667e-09,
      "loss": 0.7377,
      "step": 57
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 7.35339519570955,
      "learning_rate": 7.612046748871325e-09,
      "loss": 0.9325,
      "step": 58
    },
    {
      "epoch": 2.5777777777777775,
      "grad_norm": 7.316116487266664,
      "learning_rate": 5.84559348169793e-09,
      "loss": 1.2113,
      "step": 59
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 6.3513168304636745,
      "learning_rate": 4.305966426779118e-09,
      "loss": 0.9665,
      "step": 60
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 97.26441187163927,
      "learning_rate": 2.9968746805456025e-09,
      "loss": 1.0286,
      "step": 61
    },
    {
      "epoch": 2.7111111111111112,
      "grad_norm": 5.386926886239872,
      "learning_rate": 1.921471959676957e-09,
      "loss": 0.9448,
      "step": 62
    },
    {
      "epoch": 2.7555555555555555,
      "grad_norm": 4.05757891272107,
      "learning_rate": 1.0823490035218985e-09,
      "loss": 0.7462,
      "step": 63
    },
    {
      "epoch": 2.8,
      "grad_norm": 4.523004487871204,
      "learning_rate": 4.815273327803182e-10,
      "loss": 0.7498,
      "step": 64
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 5.296397747329322,
      "learning_rate": 1.204543794827595e-10,
      "loss": 0.8899,
      "step": 65
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 5.53542694737542,
      "learning_rate": 0.0,
      "loss": 0.741,
      "step": 66
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 33,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 28826886029312.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}