{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05684240443370755,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001136848088674151,
      "grad_norm": 1.4815157651901245,
      "learning_rate": 0.0001,
      "loss": 2.1248,
      "step": 1
    },
    {
      "epoch": 0.002273696177348302,
      "grad_norm": 1.8329018354415894,
      "learning_rate": 0.0002,
      "loss": 2.6443,
      "step": 2
    },
    {
      "epoch": 0.003410544266022453,
      "grad_norm": 1.605793833732605,
      "learning_rate": 0.00019978589232386035,
      "loss": 2.2647,
      "step": 3
    },
    {
      "epoch": 0.004547392354696604,
      "grad_norm": 1.5724087953567505,
      "learning_rate": 0.00019914448613738106,
      "loss": 2.1454,
      "step": 4
    },
    {
      "epoch": 0.005684240443370754,
      "grad_norm": 1.348822832107544,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.2881,
      "step": 5
    },
    {
      "epoch": 0.006821088532044906,
      "grad_norm": 1.3859797716140747,
      "learning_rate": 0.00019659258262890683,
      "loss": 2.1213,
      "step": 6
    },
    {
      "epoch": 0.007957936620719057,
      "grad_norm": 1.4515624046325684,
      "learning_rate": 0.0001946930129495106,
      "loss": 2.1561,
      "step": 7
    },
    {
      "epoch": 0.009094784709393207,
      "grad_norm": 1.3554356098175049,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.8992,
      "step": 8
    },
    {
      "epoch": 0.010231632798067358,
      "grad_norm": 1.0971583127975464,
      "learning_rate": 0.00018968727415326884,
      "loss": 1.8558,
      "step": 9
    },
    {
      "epoch": 0.011368480886741509,
      "grad_norm": 0.9929386377334595,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.7249,
      "step": 10
    },
    {
      "epoch": 0.01250532897541566,
      "grad_norm": 1.1700142621994019,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.9864,
      "step": 11
    },
    {
      "epoch": 0.013642177064089812,
      "grad_norm": 1.3076943159103394,
      "learning_rate": 0.00017933533402912354,
      "loss": 1.5089,
      "step": 12
    },
    {
      "epoch": 0.014779025152763962,
      "grad_norm": 1.39998459815979,
      "learning_rate": 0.00017518398074789775,
      "loss": 1.6929,
      "step": 13
    },
    {
      "epoch": 0.015915873241438113,
      "grad_norm": 1.1641753911972046,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.6188,
      "step": 14
    },
    {
      "epoch": 0.017052721330112264,
      "grad_norm": 1.0474761724472046,
      "learning_rate": 0.00016593458151000688,
      "loss": 1.8896,
      "step": 15
    },
    {
      "epoch": 0.018189569418786414,
      "grad_norm": 0.8149166703224182,
      "learning_rate": 0.00016087614290087208,
      "loss": 1.6699,
      "step": 16
    },
    {
      "epoch": 0.019326417507460565,
      "grad_norm": 1.3811651468276978,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.9316,
      "step": 17
    },
    {
      "epoch": 0.020463265596134716,
      "grad_norm": 1.001374363899231,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.8242,
      "step": 18
    },
    {
      "epoch": 0.021600113684808867,
      "grad_norm": 0.9255009889602661,
      "learning_rate": 0.00014422886902190014,
      "loss": 1.7512,
      "step": 19
    },
    {
      "epoch": 0.022736961773483017,
      "grad_norm": 0.8966016173362732,
      "learning_rate": 0.000138268343236509,
      "loss": 1.6891,
      "step": 20
    },
    {
      "epoch": 0.023873809862157168,
      "grad_norm": 0.9224222302436829,
      "learning_rate": 0.00013214394653031616,
      "loss": 1.7677,
      "step": 21
    },
    {
      "epoch": 0.02501065795083132,
      "grad_norm": 1.3027838468551636,
      "learning_rate": 0.00012588190451025207,
      "loss": 1.7951,
      "step": 22
    },
    {
      "epoch": 0.026147506039505473,
      "grad_norm": 0.9471145272254944,
      "learning_rate": 0.00011950903220161285,
      "loss": 1.701,
      "step": 23
    },
    {
      "epoch": 0.027284354128179623,
      "grad_norm": 0.9963980913162231,
      "learning_rate": 0.00011305261922200519,
      "loss": 1.5028,
      "step": 24
    },
    {
      "epoch": 0.028421202216853774,
      "grad_norm": 1.285988211631775,
      "learning_rate": 0.00010654031292301432,
      "loss": 1.9019,
      "step": 25
    },
    {
      "epoch": 0.029558050305527925,
      "grad_norm": 0.9514207243919373,
      "learning_rate": 0.0001,
      "loss": 1.9525,
      "step": 26
    },
    {
      "epoch": 0.030694898394202075,
      "grad_norm": 0.8910967111587524,
      "learning_rate": 9.345968707698569e-05,
      "loss": 1.7485,
      "step": 27
    },
    {
      "epoch": 0.031831746482876226,
      "grad_norm": 1.0070226192474365,
      "learning_rate": 8.694738077799488e-05,
      "loss": 2.0128,
      "step": 28
    },
    {
      "epoch": 0.03296859457155037,
      "grad_norm": 0.8559178709983826,
      "learning_rate": 8.049096779838719e-05,
      "loss": 1.5326,
      "step": 29
    },
    {
      "epoch": 0.03410544266022453,
      "grad_norm": 0.8095901012420654,
      "learning_rate": 7.411809548974792e-05,
      "loss": 1.6773,
      "step": 30
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 1.0621888637542725,
      "learning_rate": 6.785605346968386e-05,
      "loss": 1.6565,
      "step": 31
    },
    {
      "epoch": 0.03637913883757283,
      "grad_norm": 1.2069458961486816,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.6746,
      "step": 32
    },
    {
      "epoch": 0.03751598692624698,
      "grad_norm": 1.1669138669967651,
      "learning_rate": 5.577113097809989e-05,
      "loss": 1.9012,
      "step": 33
    },
    {
      "epoch": 0.03865283501492113,
      "grad_norm": 0.8983680605888367,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.9007,
      "step": 34
    },
    {
      "epoch": 0.039789683103595284,
      "grad_norm": 1.0233827829360962,
      "learning_rate": 4.444297669803981e-05,
      "loss": 1.4926,
      "step": 35
    },
    {
      "epoch": 0.04092653119226943,
      "grad_norm": 0.7972369194030762,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 1.6314,
      "step": 36
    },
    {
      "epoch": 0.042063379280943586,
      "grad_norm": 1.2082093954086304,
      "learning_rate": 3.406541848999312e-05,
      "loss": 1.5206,
      "step": 37
    },
    {
      "epoch": 0.04320022736961773,
      "grad_norm": 1.1588741540908813,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.7528,
      "step": 38
    },
    {
      "epoch": 0.04433707545829189,
      "grad_norm": 1.1021286249160767,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 1.8891,
      "step": 39
    },
    {
      "epoch": 0.045473923546966034,
      "grad_norm": 0.8373359441757202,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 1.7719,
      "step": 40
    },
    {
      "epoch": 0.04661077163564019,
      "grad_norm": 1.1442703008651733,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 1.8333,
      "step": 41
    },
    {
      "epoch": 0.047747619724314336,
      "grad_norm": 0.8961570858955383,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.7535,
      "step": 42
    },
    {
      "epoch": 0.04888446781298849,
      "grad_norm": 0.8508850932121277,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 1.667,
      "step": 43
    },
    {
      "epoch": 0.05002131590166264,
      "grad_norm": 1.1900713443756104,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.8957,
      "step": 44
    },
    {
      "epoch": 0.05115816399033679,
      "grad_norm": 0.7741867899894714,
      "learning_rate": 5.306987050489442e-06,
      "loss": 1.9832,
      "step": 45
    },
    {
      "epoch": 0.052295012079010945,
      "grad_norm": 0.8075515031814575,
      "learning_rate": 3.40741737109318e-06,
      "loss": 1.8664,
      "step": 46
    },
    {
      "epoch": 0.05343186016768509,
      "grad_norm": 0.9421095252037048,
      "learning_rate": 1.921471959676957e-06,
      "loss": 1.6778,
      "step": 47
    },
    {
      "epoch": 0.05456870825635925,
      "grad_norm": 0.6307845115661621,
      "learning_rate": 8.555138626189618e-07,
      "loss": 1.8083,
      "step": 48
    },
    {
      "epoch": 0.055705556345033394,
      "grad_norm": 1.0674786567687988,
      "learning_rate": 2.141076761396521e-07,
      "loss": 1.5506,
      "step": 49
    },
    {
      "epoch": 0.05684240443370755,
      "grad_norm": 1.3023602962493896,
      "learning_rate": 0.0,
      "loss": 1.6605,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 7.455971246447002e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}