{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.5130800098180771,
      "epoch": 0.025,
      "grad_norm": 0.130859375,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8656,
      "mean_token_accuracy": 0.802799665927887,
      "num_tokens": 1952251.0,
      "step": 10
    },
    {
      "entropy": 0.5367302268743515,
      "epoch": 0.05,
      "grad_norm": 0.06494140625,
      "learning_rate": 0.00019639175257731958,
      "loss": 0.511,
      "mean_token_accuracy": 0.8456412851810455,
      "num_tokens": 3913906.0,
      "step": 20
    },
    {
      "entropy": 0.45613302290439606,
      "epoch": 0.075,
      "grad_norm": 0.0281982421875,
      "learning_rate": 0.00019123711340206188,
      "loss": 0.4604,
      "mean_token_accuracy": 0.8565289735794067,
      "num_tokens": 5864430.0,
      "step": 30
    },
    {
      "entropy": 0.4395095020532608,
      "epoch": 0.1,
      "grad_norm": 0.0255126953125,
      "learning_rate": 0.00018608247422680413,
      "loss": 0.4418,
      "mean_token_accuracy": 0.8613654911518097,
      "num_tokens": 7824557.0,
      "step": 40
    },
    {
      "entropy": 0.4373431891202927,
      "epoch": 0.125,
      "grad_norm": 0.021728515625,
      "learning_rate": 0.0001809278350515464,
      "loss": 0.4392,
      "mean_token_accuracy": 0.8622795283794403,
      "num_tokens": 9780531.0,
      "step": 50
    },
    {
      "entropy": 0.44023202657699584,
      "epoch": 0.15,
      "grad_norm": 0.02294921875,
      "learning_rate": 0.00017577319587628866,
      "loss": 0.4401,
      "mean_token_accuracy": 0.8610924303531646,
      "num_tokens": 11737624.0,
      "step": 60
    },
    {
      "entropy": 0.428512442111969,
      "epoch": 0.175,
      "grad_norm": 0.022705078125,
      "learning_rate": 0.00017061855670103093,
      "loss": 0.4313,
      "mean_token_accuracy": 0.8635753691196442,
      "num_tokens": 13697322.0,
      "step": 70
    },
    {
      "entropy": 0.43105508685112,
      "epoch": 0.2,
      "grad_norm": 0.0228271484375,
      "learning_rate": 0.00016546391752577318,
      "loss": 0.4318,
      "mean_token_accuracy": 0.863618916273117,
      "num_tokens": 15649945.0,
      "step": 80
    },
    {
      "entropy": 0.424772709608078,
      "epoch": 0.225,
      "grad_norm": 0.0255126953125,
      "learning_rate": 0.0001603092783505155,
      "loss": 0.4253,
      "mean_token_accuracy": 0.8657742798328399,
      "num_tokens": 17593762.0,
      "step": 90
    },
    {
      "entropy": 0.4235113948583603,
      "epoch": 0.25,
      "grad_norm": 0.024658203125,
      "learning_rate": 0.00015515463917525774,
      "loss": 0.4243,
      "mean_token_accuracy": 0.8653883039951324,
      "num_tokens": 19542045.0,
      "step": 100
    },
    {
      "entropy": 0.41819455325603483,
      "epoch": 0.275,
      "grad_norm": 0.0244140625,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4193,
      "mean_token_accuracy": 0.8669234216213226,
      "num_tokens": 21495444.0,
      "step": 110
    },
    {
      "entropy": 0.41760264337062836,
      "epoch": 0.3,
      "grad_norm": 0.024169921875,
      "learning_rate": 0.00014484536082474226,
      "loss": 0.4192,
      "mean_token_accuracy": 0.8668062031269074,
      "num_tokens": 23454845.0,
      "step": 120
    },
    {
      "entropy": 0.4235453844070435,
      "epoch": 0.325,
      "grad_norm": 0.0247802734375,
      "learning_rate": 0.00013969072164948454,
      "loss": 0.4255,
      "mean_token_accuracy": 0.8658895254135132,
      "num_tokens": 25407964.0,
      "step": 130
    },
    {
      "entropy": 0.41925162076950073,
      "epoch": 0.35,
      "grad_norm": 0.0252685546875,
      "learning_rate": 0.00013453608247422682,
      "loss": 0.4194,
      "mean_token_accuracy": 0.8667669773101807,
      "num_tokens": 27366353.0,
      "step": 140
    },
    {
      "entropy": 0.4193441987037659,
      "epoch": 0.375,
      "grad_norm": 0.024658203125,
      "learning_rate": 0.0001293814432989691,
      "loss": 0.4219,
      "mean_token_accuracy": 0.8661471247673035,
      "num_tokens": 29324217.0,
      "step": 150
    },
    {
      "entropy": 0.41715689599514005,
      "epoch": 0.4,
      "grad_norm": 0.0255126953125,
      "learning_rate": 0.00012422680412371134,
      "loss": 0.417,
      "mean_token_accuracy": 0.8673597633838653,
      "num_tokens": 31274352.0,
      "step": 160
    },
    {
      "entropy": 0.41513965725898744,
      "epoch": 0.425,
      "grad_norm": 0.02490234375,
      "learning_rate": 0.00011907216494845362,
      "loss": 0.4144,
      "mean_token_accuracy": 0.8679460406303405,
      "num_tokens": 33232032.0,
      "step": 170
    },
    {
      "entropy": 0.41377590596675873,
      "epoch": 0.45,
      "grad_norm": 0.02587890625,
      "learning_rate": 0.00011391752577319588,
      "loss": 0.4151,
      "mean_token_accuracy": 0.8679844081401825,
      "num_tokens": 35185807.0,
      "step": 180
    },
    {
      "entropy": 0.41528587639331815,
      "epoch": 0.475,
      "grad_norm": 0.0262451171875,
      "learning_rate": 0.00010876288659793815,
      "loss": 0.4163,
      "mean_token_accuracy": 0.8680092096328735,
      "num_tokens": 37142040.0,
      "step": 190
    },
    {
      "entropy": 0.4145059704780579,
      "epoch": 0.5,
      "grad_norm": 0.025390625,
      "learning_rate": 0.00010360824742268042,
      "loss": 0.4155,
      "mean_token_accuracy": 0.868000590801239,
      "num_tokens": 39089347.0,
      "step": 200
    },
    {
      "entropy": 0.4087012320756912,
      "epoch": 0.525,
      "grad_norm": 0.0260009765625,
      "learning_rate": 9.845360824742269e-05,
      "loss": 0.4089,
      "mean_token_accuracy": 0.8693469941616059,
      "num_tokens": 41036290.0,
      "step": 210
    },
    {
      "entropy": 0.40894885659217833,
      "epoch": 0.55,
      "grad_norm": 0.0257568359375,
      "learning_rate": 9.329896907216495e-05,
      "loss": 0.411,
      "mean_token_accuracy": 0.8692088723182678,
      "num_tokens": 42977921.0,
      "step": 220
    },
    {
      "entropy": 0.4120857834815979,
      "epoch": 0.575,
      "grad_norm": 0.0257568359375,
      "learning_rate": 8.814432989690722e-05,
      "loss": 0.4121,
      "mean_token_accuracy": 0.868464720249176,
      "num_tokens": 44926629.0,
      "step": 230
    },
    {
      "entropy": 0.4110714465379715,
      "epoch": 0.6,
      "grad_norm": 0.025634765625,
      "learning_rate": 8.298969072164949e-05,
      "loss": 0.4118,
      "mean_token_accuracy": 0.8687853872776031,
      "num_tokens": 46881619.0,
      "step": 240
    },
    {
      "entropy": 0.4152237057685852,
      "epoch": 0.625,
      "grad_norm": 0.026123046875,
      "learning_rate": 7.783505154639175e-05,
      "loss": 0.4164,
      "mean_token_accuracy": 0.867627602815628,
      "num_tokens": 48844100.0,
      "step": 250
    },
    {
      "entropy": 0.40879290401935575,
      "epoch": 0.65,
      "grad_norm": 0.0267333984375,
      "learning_rate": 7.268041237113403e-05,
      "loss": 0.4087,
      "mean_token_accuracy": 0.869741427898407,
      "num_tokens": 50790693.0,
      "step": 260
    },
    {
      "entropy": 0.4091353178024292,
      "epoch": 0.675,
      "grad_norm": 0.0257568359375,
      "learning_rate": 6.752577319587629e-05,
      "loss": 0.4103,
      "mean_token_accuracy": 0.8694662570953369,
      "num_tokens": 52742161.0,
      "step": 270
    },
    {
      "entropy": 0.4107410669326782,
      "epoch": 0.7,
      "grad_norm": 0.0269775390625,
      "learning_rate": 6.237113402061855e-05,
      "loss": 0.4111,
      "mean_token_accuracy": 0.8692059934139251,
      "num_tokens": 54692664.0,
      "step": 280
    },
    {
      "entropy": 0.4057494968175888,
      "epoch": 0.725,
      "grad_norm": 0.0263671875,
      "learning_rate": 5.721649484536082e-05,
      "loss": 0.407,
      "mean_token_accuracy": 0.8700494408607483,
      "num_tokens": 56654881.0,
      "step": 290
    },
    {
      "entropy": 0.40529186129570005,
      "epoch": 0.75,
      "grad_norm": 0.0263671875,
      "learning_rate": 5.20618556701031e-05,
      "loss": 0.4057,
      "mean_token_accuracy": 0.8709144175052643,
      "num_tokens": 58612358.0,
      "step": 300
    },
    {
      "entropy": 0.4049283146858215,
      "epoch": 0.775,
      "grad_norm": 0.0264892578125,
      "learning_rate": 4.690721649484536e-05,
      "loss": 0.4059,
      "mean_token_accuracy": 0.8705782651901245,
      "num_tokens": 60570532.0,
      "step": 310
    },
    {
      "entropy": 0.41278861463069916,
      "epoch": 0.8,
      "grad_norm": 0.0264892578125,
      "learning_rate": 4.175257731958763e-05,
      "loss": 0.4129,
      "mean_token_accuracy": 0.8685104608535766,
      "num_tokens": 62523745.0,
      "step": 320
    },
    {
      "entropy": 0.4059197723865509,
      "epoch": 0.825,
      "grad_norm": 0.0262451171875,
      "learning_rate": 3.6597938144329896e-05,
      "loss": 0.4061,
      "mean_token_accuracy": 0.8701611340045929,
      "num_tokens": 64468966.0,
      "step": 330
    },
    {
      "entropy": 0.4075415819883347,
      "epoch": 0.85,
      "grad_norm": 0.026611328125,
      "learning_rate": 3.1443298969072166e-05,
      "loss": 0.4084,
      "mean_token_accuracy": 0.8696109414100647,
      "num_tokens": 66421242.0,
      "step": 340
    },
    {
      "entropy": 0.4091123640537262,
      "epoch": 0.875,
      "grad_norm": 0.0269775390625,
      "learning_rate": 2.6288659793814435e-05,
      "loss": 0.4095,
      "mean_token_accuracy": 0.8693838775157928,
      "num_tokens": 68383604.0,
      "step": 350
    },
    {
      "entropy": 0.4036696970462799,
      "epoch": 0.9,
      "grad_norm": 0.026611328125,
      "learning_rate": 2.1134020618556702e-05,
      "loss": 0.4036,
      "mean_token_accuracy": 0.8708941996097564,
      "num_tokens": 70340165.0,
      "step": 360
    },
    {
      "entropy": 0.4065678924322128,
      "epoch": 0.925,
      "grad_norm": 0.0260009765625,
      "learning_rate": 1.5979381443298968e-05,
      "loss": 0.4081,
      "mean_token_accuracy": 0.8699499130249023,
      "num_tokens": 72299574.0,
      "step": 370
    },
    {
      "entropy": 0.40871464014053344,
      "epoch": 0.95,
      "grad_norm": 0.0263671875,
      "learning_rate": 1.0824742268041238e-05,
      "loss": 0.4097,
      "mean_token_accuracy": 0.8694815635681152,
      "num_tokens": 74258475.0,
      "step": 380
    },
    {
      "entropy": 0.4087704449892044,
      "epoch": 0.975,
      "grad_norm": 0.026123046875,
      "learning_rate": 5.670103092783505e-06,
      "loss": 0.409,
      "mean_token_accuracy": 0.8698881447315217,
      "num_tokens": 76213204.0,
      "step": 390
    },
    {
      "entropy": 0.4095977067947388,
      "epoch": 1.0,
      "grad_norm": 0.02587890625,
      "learning_rate": 5.154639175257732e-07,
      "loss": 0.4106,
      "mean_token_accuracy": 0.8693839371204376,
      "num_tokens": 78069199.0,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5378917481854796e+19,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}