{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.5236270803213119,
      "epoch": 0.05561735261401557,
      "grad_norm": 0.055419921875,
      "learning_rate": 0.00019974051702905277,
      "loss": 1.5805291748046875,
      "mean_token_accuracy": 0.647714718580246,
      "num_tokens": 143908.0,
      "step": 25
    },
    {
      "entropy": 1.3212773679941892,
      "epoch": 0.11123470522803114,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00019683677672505253,
      "loss": 1.2404356384277344,
      "mean_token_accuracy": 0.7040169030427933,
      "num_tokens": 286606.0,
      "step": 50
    },
    {
      "entropy": 1.1558487902022898,
      "epoch": 0.1668520578420467,
      "grad_norm": 0.08984375,
      "learning_rate": 0.0001907992282510675,
      "loss": 1.0775267791748047,
      "mean_token_accuracy": 0.7465412376821041,
      "num_tokens": 420820.0,
      "step": 75
    },
    {
      "entropy": 1.0273668716661633,
      "epoch": 0.22246941045606228,
      "grad_norm": 0.08642578125,
      "learning_rate": 0.00018182325727950777,
      "loss": 0.9585573577880859,
      "mean_token_accuracy": 0.7694233341515064,
      "num_tokens": 556416.0,
      "step": 100
    },
    {
      "entropy": 0.8720588740799576,
      "epoch": 0.27808676307007785,
      "grad_norm": 0.09033203125,
      "learning_rate": 0.00017019934199557867,
      "loss": 0.7967613983154297,
      "mean_token_accuracy": 0.8086028082668781,
      "num_tokens": 693255.0,
      "step": 125
    },
    {
      "entropy": 0.7958288640156388,
      "epoch": 0.3337041156840934,
      "grad_norm": 0.08642578125,
      "learning_rate": 0.00015630365271303827,
      "loss": 0.6878538513183594,
      "mean_token_accuracy": 0.8273787525296211,
      "num_tokens": 830019.0,
      "step": 150
    },
    {
      "entropy": 0.7475133097125217,
      "epoch": 0.389321468298109,
      "grad_norm": 0.0791015625,
      "learning_rate": 0.00014058587834217355,
      "loss": 0.6619260406494141,
      "mean_token_accuracy": 0.8369621601700783,
      "num_tokens": 970194.0,
      "step": 175
    },
    {
      "entropy": 0.6880824944004417,
      "epoch": 0.44493882091212456,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.00012355467366687156,
      "loss": 0.6069028854370118,
      "mean_token_accuracy": 0.8497222004830838,
      "num_tokens": 1106500.0,
      "step": 200
    },
    {
      "entropy": 0.6797102421335875,
      "epoch": 0.5005561735261401,
      "grad_norm": 0.08935546875,
      "learning_rate": 0.00010576119838245844,
      "loss": 0.6194157028198242,
      "mean_token_accuracy": 0.851585813164711,
      "num_tokens": 1248886.0,
      "step": 225
    },
    {
      "entropy": 0.6410426250938326,
      "epoch": 0.5561735261401557,
      "grad_norm": 0.0576171875,
      "learning_rate": 8.778128059995269e-05,
      "loss": 0.5677408218383789,
      "mean_token_accuracy": 0.8584357848763466,
      "num_tokens": 1393484.0,
      "step": 250
    },
    {
      "entropy": 0.49390312943141906,
      "epoch": 0.6117908787541713,
      "grad_norm": 0.03466796875,
      "learning_rate": 7.019678203706163e-05,
      "loss": 0.4471506881713867,
      "mean_token_accuracy": 0.890991186350584,
      "num_tokens": 1537897.0,
      "step": 275
    },
    {
      "entropy": 0.6916981361201033,
      "epoch": 0.6674082313681868,
      "grad_norm": 0.12353515625,
      "learning_rate": 5.357676795106799e-05,
      "loss": 0.6350007247924805,
      "mean_token_accuracy": 0.8496893347799778,
      "num_tokens": 1675749.0,
      "step": 300
    },
    {
      "entropy": 0.6515753491269425,
      "epoch": 0.7230255839822024,
      "grad_norm": 0.0751953125,
      "learning_rate": 3.845909118765073e-05,
      "loss": 0.6029189682006836,
      "mean_token_accuracy": 0.8555391871929169,
      "num_tokens": 1815517.0,
      "step": 325
    },
    {
      "entropy": 0.6985861426126212,
      "epoch": 0.778642936596218,
      "grad_norm": 0.0390625,
      "learning_rate": 2.5332986318163886e-05,
      "loss": 0.6293030548095703,
      "mean_token_accuracy": 0.8477095763385296,
      "num_tokens": 1955691.0,
      "step": 350
    },
    {
      "entropy": 0.6039358280133456,
      "epoch": 0.8342602892102335,
      "grad_norm": 0.06494140625,
      "learning_rate": 1.462323714966114e-05,
      "loss": 0.5598350524902344,
      "mean_token_accuracy": 0.8694348326325416,
      "num_tokens": 2096304.0,
      "step": 375
    },
    {
      "entropy": 0.6356105864001438,
      "epoch": 0.8898776418242491,
      "grad_norm": 0.049560546875,
      "learning_rate": 6.676429974848563e-06,
      "loss": 0.6045819091796875,
      "mean_token_accuracy": 0.8612590564787388,
      "num_tokens": 2230962.0,
      "step": 400
    },
    {
      "entropy": 0.6548895966866985,
      "epoch": 0.9454949944382648,
      "grad_norm": 0.07861328125,
      "learning_rate": 1.7497374309405346e-06,
      "loss": 0.5994021224975586,
      "mean_token_accuracy": 0.8573913918435574,
      "num_tokens": 2364095.0,
      "step": 425
    },
    {
      "entropy": 0.6505621709737318,
      "epoch": 1.0,
      "grad_norm": 0.08837890625,
      "learning_rate": 2.5959414452270124e-09,
      "loss": 0.6095585632324219,
      "mean_token_accuracy": 0.8590780609116262,
      "num_tokens": 2497006.0,
      "step": 450
    }
  ],
  "logging_steps": 25,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.0653709786799923e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}