{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 0,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 271.2847900390625,
      "learning_rate": 0.0,
      "loss": 15.6328,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 283.8895263671875,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 15.7266,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 239.6302490234375,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 14.4062,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 131.42355346679688,
      "learning_rate": 8.571428571428571e-06,
      "loss": 6.6289,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 26.378475189208984,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.9219,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 10.474356651306152,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.4797,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.809896469116211,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.1807,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.836686372756958,
      "learning_rate": 2e-05,
      "loss": 0.1663,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.031554937362671,
      "learning_rate": 1.998426815017817e-05,
      "loss": 0.1649,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.8881802558898926,
      "learning_rate": 1.9937122098932428e-05,
      "loss": 0.1857,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 2.4832403659820557,
      "learning_rate": 1.985871018518236e-05,
      "loss": 0.1583,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.085007429122925,
      "learning_rate": 1.9749279121818235e-05,
      "loss": 0.1541,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 2.2945327758789062,
      "learning_rate": 1.9609173219450998e-05,
      "loss": 0.1553,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.169069290161133,
      "learning_rate": 1.9438833303083677e-05,
      "loss": 0.1539,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.0928995609283447,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.1472,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.304161548614502,
      "learning_rate": 1.900968867902419e-05,
      "loss": 0.1589,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 1.644942283630371,
      "learning_rate": 1.8752234219087538e-05,
      "loss": 0.1449,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.959534764289856,
      "learning_rate": 1.8467241992282842e-05,
      "loss": 0.155,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 21.322084426879883,
      "learning_rate": 1.8155608689592604e-05,
      "loss": 0.2281,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.6131975650787354,
      "learning_rate": 1.78183148246803e-05,
      "loss": 0.1748,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9911768436431885,
      "learning_rate": 1.7456421648831658e-05,
      "loss": 0.1499,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.7157345414161682,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.1598,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 1.3037433624267578,
      "learning_rate": 1.6663465779520042e-05,
      "loss": 0.1428,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.650227427482605,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 0.1381,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.1550507545471191,
      "learning_rate": 1.578671296179806e-05,
      "loss": 0.126,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.8351575136184692,
      "learning_rate": 1.5320320765153367e-05,
      "loss": 0.1112,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.8693701028823853,
      "learning_rate": 1.4837188871052399e-05,
      "loss": 0.1158,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.883232593536377,
      "learning_rate": 1.4338837391175582e-05,
      "loss": 0.0951,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 2.0021462440490723,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.141,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.9316145181655884,
      "learning_rate": 1.3302790619551673e-05,
      "loss": 0.1143,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.6722294092178345,
      "learning_rate": 1.2768355114248493e-05,
      "loss": 0.0856,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 3.3709585666656494,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 0.1282,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 3.494358539581299,
      "learning_rate": 1.1675062233047365e-05,
      "loss": 0.1166,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 1.0232586860656738,
      "learning_rate": 1.1119644761033079e-05,
      "loss": 0.1171,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.7489449977874756,
      "learning_rate": 1.0560704472371919e-05,
      "loss": 0.0844,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.0576767921447754,
      "learning_rate": 1e-05,
      "loss": 0.1084,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 1.014384150505066,
      "learning_rate": 9.439295527628083e-06,
      "loss": 0.0855,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.956558108329773,
      "learning_rate": 8.880355238966923e-06,
      "loss": 0.0793,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.9556608200073242,
      "learning_rate": 8.324937766952638e-06,
      "loss": 0.0726,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 2.3250770568847656,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.0802,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 2.596691131591797,
      "learning_rate": 7.2316448857515076e-06,
      "loss": 0.1185,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.510233163833618,
      "learning_rate": 6.697209380448333e-06,
      "loss": 0.0885,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 1.380808711051941,
      "learning_rate": 6.173165676349103e-06,
      "loss": 0.0732,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 1.4121789932250977,
      "learning_rate": 5.66116260882442e-06,
      "loss": 0.0781,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 1.6490198373794556,
      "learning_rate": 5.1628111289476025e-06,
      "loss": 0.0627,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.9158168435096741,
      "learning_rate": 4.679679234846636e-06,
      "loss": 0.0486,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 1.6034945249557495,
      "learning_rate": 4.213287038201943e-06,
      "loss": 0.0543,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.2905007600784302,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.0587,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.971811830997467,
      "learning_rate": 3.3365342204799613e-06,
      "loss": 0.0772,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 1.3265019655227661,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.069,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 1.0910696983337402,
      "learning_rate": 2.5435783511683444e-06,
      "loss": 0.0531,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.5556491017341614,
      "learning_rate": 2.1816851753197023e-06,
      "loss": 0.0735,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.8411810398101807,
      "learning_rate": 1.8443913104073984e-06,
      "loss": 0.0399,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.5246292948722839,
      "learning_rate": 1.5327580077171589e-06,
      "loss": 0.0299,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.4854477643966675,
      "learning_rate": 1.2477657809124632e-06,
      "loss": 0.0348,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.8015491962432861,
      "learning_rate": 9.903113209758098e-07,
      "loss": 0.0342,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 1.3755743503570557,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.046,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.956333339214325,
      "learning_rate": 5.611666969163243e-07,
      "loss": 0.0662,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.7447959184646606,
      "learning_rate": 3.908267805490051e-07,
      "loss": 0.0401,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.1069077253341675,
      "learning_rate": 2.507208781817638e-07,
      "loss": 0.0717,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.6235014200210571,
      "learning_rate": 1.4128981481764115e-07,
      "loss": 0.0464,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.7081692218780518,
      "learning_rate": 6.287790106757396e-08,
      "loss": 0.0389,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5594448447227478,
      "learning_rate": 1.5731849821833955e-08,
      "loss": 0.0408,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.211049111532339e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}