{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04032258064516129,
      "grad_norm": 5.529094696044922,
      "learning_rate": 1.967741935483871e-05,
      "loss": 2.1468,
      "num_tokens": 569626.0,
      "step": 5
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 1.6760125160217285,
      "learning_rate": 1.9274193548387097e-05,
      "loss": 1.6179,
      "num_tokens": 1139325.0,
      "step": 10
    },
    {
      "epoch": 0.12096774193548387,
      "grad_norm": 1.4216994047164917,
      "learning_rate": 1.8870967741935487e-05,
      "loss": 1.597,
      "num_tokens": 1725544.0,
      "step": 15
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 1.5306953191757202,
      "learning_rate": 1.8467741935483873e-05,
      "loss": 1.5814,
      "num_tokens": 2307690.0,
      "step": 20
    },
    {
      "epoch": 0.20161290322580644,
      "grad_norm": 1.4263639450073242,
      "learning_rate": 1.806451612903226e-05,
      "loss": 1.539,
      "num_tokens": 2873351.0,
      "step": 25
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 1.4706966876983643,
      "learning_rate": 1.7661290322580645e-05,
      "loss": 1.5043,
      "num_tokens": 3458554.0,
      "step": 30
    },
    {
      "epoch": 0.28225806451612906,
      "grad_norm": 1.4188745021820068,
      "learning_rate": 1.7258064516129035e-05,
      "loss": 1.4626,
      "num_tokens": 4014867.0,
      "step": 35
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 1.3688955307006836,
      "learning_rate": 1.685483870967742e-05,
      "loss": 1.5154,
      "num_tokens": 4608605.0,
      "step": 40
    },
    {
      "epoch": 0.3629032258064516,
      "grad_norm": 1.4123735427856445,
      "learning_rate": 1.6451612903225807e-05,
      "loss": 1.4998,
      "num_tokens": 5185008.0,
      "step": 45
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 1.4094408750534058,
      "learning_rate": 1.6048387096774193e-05,
      "loss": 1.4426,
      "num_tokens": 5752110.0,
      "step": 50
    },
    {
      "epoch": 0.4435483870967742,
      "grad_norm": 1.337942361831665,
      "learning_rate": 1.5645161290322583e-05,
      "loss": 1.447,
      "num_tokens": 6312558.0,
      "step": 55
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 1.4133641719818115,
      "learning_rate": 1.5241935483870969e-05,
      "loss": 1.4254,
      "num_tokens": 6855383.0,
      "step": 60
    },
    {
      "epoch": 0.5241935483870968,
      "grad_norm": 1.4047032594680786,
      "learning_rate": 1.4838709677419357e-05,
      "loss": 1.3951,
      "num_tokens": 7450882.0,
      "step": 65
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 1.5289469957351685,
      "learning_rate": 1.4435483870967743e-05,
      "loss": 1.4078,
      "num_tokens": 8011410.0,
      "step": 70
    },
    {
      "epoch": 0.6048387096774194,
      "grad_norm": 1.3724051713943481,
      "learning_rate": 1.4032258064516131e-05,
      "loss": 1.3861,
      "num_tokens": 8604324.0,
      "step": 75
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 1.3465704917907715,
      "learning_rate": 1.3629032258064517e-05,
      "loss": 1.4134,
      "num_tokens": 9199811.0,
      "step": 80
    },
    {
      "epoch": 0.6854838709677419,
      "grad_norm": 1.4271504878997803,
      "learning_rate": 1.3225806451612903e-05,
      "loss": 1.3761,
      "num_tokens": 9779542.0,
      "step": 85
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 1.3447699546813965,
      "learning_rate": 1.2822580645161291e-05,
      "loss": 1.3681,
      "num_tokens": 10353120.0,
      "step": 90
    },
    {
      "epoch": 0.7661290322580645,
      "grad_norm": 1.4184237718582153,
      "learning_rate": 1.2419354838709679e-05,
      "loss": 1.3597,
      "num_tokens": 10939848.0,
      "step": 95
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 1.4755223989486694,
      "learning_rate": 1.2016129032258067e-05,
      "loss": 1.3648,
      "step": 100
    },
    {
      "epoch": 0.8064516129032258,
      "eval_loss": 1.3336517810821533,
      "eval_num_tokens": 11517816.0,
      "eval_runtime": 0.836,
      "eval_samples_per_second": 239.241,
      "eval_steps_per_second": 4.785,
      "step": 100
    },
    {
      "epoch": 0.8467741935483871,
      "grad_norm": 1.3846817016601562,
      "learning_rate": 1.1612903225806453e-05,
      "loss": 1.3236,
      "num_tokens": 12098001.0,
      "step": 105
    },
    {
      "epoch": 0.8870967741935484,
      "grad_norm": 1.3982224464416504,
      "learning_rate": 1.1209677419354839e-05,
      "loss": 1.3749,
      "num_tokens": 12664773.0,
      "step": 110
    },
    {
      "epoch": 0.9274193548387096,
      "grad_norm": 1.394708275794983,
      "learning_rate": 1.0806451612903225e-05,
      "loss": 1.3616,
      "num_tokens": 13239769.0,
      "step": 115
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 1.4701589345932007,
      "learning_rate": 1.0403225806451613e-05,
      "loss": 1.3239,
      "num_tokens": 13815380.0,
      "step": 120
    },
    {
      "epoch": 1.0080645161290323,
      "grad_norm": 1.8194153308868408,
      "learning_rate": 1e-05,
      "loss": 1.2917,
      "num_tokens": 14410457.0,
      "step": 125
    },
    {
      "epoch": 1.0483870967741935,
      "grad_norm": 1.5739810466766357,
      "learning_rate": 9.596774193548389e-06,
      "loss": 1.1886,
      "num_tokens": 14970862.0,
      "step": 130
    },
    {
      "epoch": 1.0887096774193548,
      "grad_norm": 1.4429163932800293,
      "learning_rate": 9.193548387096775e-06,
      "loss": 1.1446,
      "num_tokens": 15543251.0,
      "step": 135
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 1.4568403959274292,
      "learning_rate": 8.790322580645163e-06,
      "loss": 1.1923,
      "num_tokens": 16116595.0,
      "step": 140
    },
    {
      "epoch": 1.1693548387096775,
      "grad_norm": 1.2344177961349487,
      "learning_rate": 8.387096774193549e-06,
      "loss": 1.117,
      "num_tokens": 16692148.0,
      "step": 145
    },
    {
      "epoch": 1.2096774193548387,
      "grad_norm": 1.3003144264221191,
      "learning_rate": 7.983870967741935e-06,
      "loss": 1.1455,
      "num_tokens": 17259266.0,
      "step": 150
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.2739754915237427,
      "learning_rate": 7.580645161290323e-06,
      "loss": 1.1384,
      "num_tokens": 17850398.0,
      "step": 155
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 1.2682229280471802,
      "learning_rate": 7.177419354838711e-06,
      "loss": 1.1224,
      "num_tokens": 18427597.0,
      "step": 160
    },
    {
      "epoch": 1.3306451612903225,
      "grad_norm": 1.3172603845596313,
      "learning_rate": 6.774193548387097e-06,
      "loss": 1.1621,
      "num_tokens": 18995627.0,
      "step": 165
    },
    {
      "epoch": 1.370967741935484,
      "grad_norm": 1.3776545524597168,
      "learning_rate": 6.370967741935485e-06,
      "loss": 1.1768,
      "num_tokens": 19577403.0,
      "step": 170
    },
    {
      "epoch": 1.4112903225806452,
      "grad_norm": 1.5168935060501099,
      "learning_rate": 5.967741935483872e-06,
      "loss": 1.1654,
      "num_tokens": 20139809.0,
      "step": 175
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 1.3282400369644165,
      "learning_rate": 5.564516129032258e-06,
      "loss": 1.1845,
      "num_tokens": 20704956.0,
      "step": 180
    },
    {
      "epoch": 1.4919354838709677,
      "grad_norm": 1.2337759733200073,
      "learning_rate": 5.161290322580646e-06,
      "loss": 1.1292,
      "num_tokens": 21299733.0,
      "step": 185
    },
    {
      "epoch": 1.532258064516129,
      "grad_norm": 1.2648212909698486,
      "learning_rate": 4.758064516129033e-06,
      "loss": 1.1169,
      "num_tokens": 21844009.0,
      "step": 190
    },
    {
      "epoch": 1.5725806451612905,
      "grad_norm": 1.2721643447875977,
      "learning_rate": 4.35483870967742e-06,
      "loss": 1.1603,
      "num_tokens": 22428460.0,
      "step": 195
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 1.3038477897644043,
      "learning_rate": 3.951612903225807e-06,
      "loss": 1.145,
      "step": 200
    },
    {
      "epoch": 1.6129032258064515,
      "eval_loss": 1.2858035564422607,
      "eval_num_tokens": 22975636.0,
      "eval_runtime": 0.657,
      "eval_samples_per_second": 304.413,
      "eval_steps_per_second": 6.088,
      "step": 200
    },
    {
      "epoch": 1.653225806451613,
      "grad_norm": 1.148224949836731,
      "learning_rate": 3.548387096774194e-06,
      "loss": 1.1595,
      "num_tokens": 23542739.0,
      "step": 205
    },
    {
      "epoch": 1.6935483870967742,
      "grad_norm": 1.2188303470611572,
      "learning_rate": 3.145161290322581e-06,
      "loss": 1.1825,
      "num_tokens": 24136046.0,
      "step": 210
    },
    {
      "epoch": 1.7338709677419355,
      "grad_norm": 1.1819931268692017,
      "learning_rate": 2.7419354838709676e-06,
      "loss": 1.1742,
      "num_tokens": 24729797.0,
      "step": 215
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 1.1400372982025146,
      "learning_rate": 2.338709677419355e-06,
      "loss": 1.1038,
      "num_tokens": 25346765.0,
      "step": 220
    },
    {
      "epoch": 1.814516129032258,
      "grad_norm": 1.1438357830047607,
      "learning_rate": 1.935483870967742e-06,
      "loss": 1.1393,
      "num_tokens": 25941886.0,
      "step": 225
    },
    {
      "epoch": 1.8548387096774195,
      "grad_norm": 1.2471617460250854,
      "learning_rate": 1.5322580645161292e-06,
      "loss": 1.1393,
      "num_tokens": 26500890.0,
      "step": 230
    },
    {
      "epoch": 1.8951612903225805,
      "grad_norm": 1.1599065065383911,
      "learning_rate": 1.1290322580645162e-06,
      "loss": 1.1702,
      "num_tokens": 27078001.0,
      "step": 235
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 1.1888681650161743,
      "learning_rate": 7.258064516129033e-07,
      "loss": 1.127,
      "num_tokens": 27661921.0,
      "step": 240
    },
    {
      "epoch": 1.9758064516129032,
      "grad_norm": 1.153752326965332,
      "learning_rate": 3.2258064516129035e-07,
      "loss": 1.1062,
      "num_tokens": 28242974.0,
      "step": 245
    },
    {
      "epoch": 2.0,
      "num_tokens": 28583989.0,
      "step": 248,
      "total_flos": 3.601528462235402e+17,
      "train_loss": 1.304817815942149,
      "train_runtime": 294.8766,
      "train_samples_per_second": 107.204,
      "train_steps_per_second": 0.841
    }
  ],
  "logging_steps": 5,
  "max_steps": 248,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.601528462235402e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}