{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019536019536019536,
  "eval_steps": 500,
  "global_step": 32,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 4.13485050201416,
      "epoch": 0.0006105006105006105,
      "grad_norm": 6.779195785522461,
      "learning_rate": 0.0003,
      "loss": 6.2653,
      "mean_token_accuracy": 0.16929133236408234,
      "num_tokens": 1024.0,
      "step": 1
    },
    {
      "entropy": 5.793717861175537,
      "epoch": 0.001221001221001221,
      "grad_norm": 16.547292709350586,
      "learning_rate": 0.00029927770900082954,
      "loss": 7.4425,
      "mean_token_accuracy": 0.07185039669275284,
      "num_tokens": 2048.0,
      "step": 2
    },
    {
      "entropy": 5.173164367675781,
      "epoch": 0.0018315018315018315,
      "grad_norm": 8.281397819519043,
      "learning_rate": 0.00029711779206048454,
      "loss": 7.0805,
      "mean_token_accuracy": 0.04595404490828514,
      "num_tokens": 3072.0,
      "step": 3
    },
    {
      "entropy": 5.790804862976074,
      "epoch": 0.002442002442002442,
      "grad_norm": 7.232938289642334,
      "learning_rate": 0.0002935410503598313,
      "loss": 5.9113,
      "mean_token_accuracy": 0.09690721333026886,
      "num_tokens": 4096.0,
      "step": 4
    },
    {
      "entropy": 5.514730453491211,
      "epoch": 0.0030525030525030525,
      "grad_norm": 5.750503063201904,
      "learning_rate": 0.000288581929876693,
      "loss": 5.9462,
      "mean_token_accuracy": 0.10728346556425095,
      "num_tokens": 5120.0,
      "step": 5
    },
    {
      "entropy": 4.5655198097229,
      "epoch": 0.003663003663003663,
      "grad_norm": 9.491901397705078,
      "learning_rate": 0.0002822881896522532,
      "loss": 5.7517,
      "mean_token_accuracy": 0.18307086825370789,
      "num_tokens": 6144.0,
      "step": 6
    },
    {
      "entropy": 4.92832088470459,
      "epoch": 0.004273504273504274,
      "grad_norm": 4.776255130767822,
      "learning_rate": 0.0002747204418453818,
      "loss": 5.6682,
      "mean_token_accuracy": 0.17814961075782776,
      "num_tokens": 7168.0,
      "step": 7
    },
    {
      "entropy": 6.124536991119385,
      "epoch": 0.004884004884004884,
      "grad_norm": 11.058452606201172,
      "learning_rate": 0.0002659515680044105,
      "loss": 4.9755,
      "mean_token_accuracy": 0.18397626280784607,
      "num_tokens": 8192.0,
      "step": 8
    },
    {
      "entropy": 4.757119655609131,
      "epoch": 0.005494505494505495,
      "grad_norm": 30.98914909362793,
      "learning_rate": 0.00025606601717798207,
      "loss": 5.5204,
      "mean_token_accuracy": 0.1530286967754364,
      "num_tokens": 9216.0,
      "step": 9
    },
    {
      "entropy": 3.9111785888671875,
      "epoch": 0.006105006105006105,
      "grad_norm": 6.036701202392578,
      "learning_rate": 0.0002451589926245468,
      "loss": 5.7534,
      "mean_token_accuracy": 0.15548455715179443,
      "num_tokens": 10240.0,
      "step": 10
    },
    {
      "entropy": 5.500742435455322,
      "epoch": 0.006715506715506716,
      "grad_norm": 3.4777474403381348,
      "learning_rate": 0.0002333355349529403,
      "loss": 5.7081,
      "mean_token_accuracy": 0.15589743852615356,
      "num_tokens": 11264.0,
      "step": 11
    },
    {
      "entropy": 5.70326566696167,
      "epoch": 0.007326007326007326,
      "grad_norm": 3.508657217025757,
      "learning_rate": 0.00022070951052389966,
      "loss": 5.0422,
      "mean_token_accuracy": 0.18095238506793976,
      "num_tokens": 12288.0,
      "step": 12
    },
    {
      "entropy": 4.923552513122559,
      "epoch": 0.007936507936507936,
      "grad_norm": 3.8143184185028076,
      "learning_rate": 0.00020740251485476345,
      "loss": 5.1931,
      "mean_token_accuracy": 0.169199600815773,
      "num_tokens": 13312.0,
      "step": 13
    },
    {
      "entropy": 4.681103706359863,
      "epoch": 0.008547008547008548,
      "grad_norm": 3.4933412075042725,
      "learning_rate": 0.0001935427015881693,
      "loss": 5.573,
      "mean_token_accuracy": 0.17606329917907715,
      "num_tokens": 14336.0,
      "step": 14
    },
    {
      "entropy": 5.161688327789307,
      "epoch": 0.009157509157509158,
      "grad_norm": 6.412088394165039,
      "learning_rate": 0.00017926354830241924,
      "loss": 5.2034,
      "mean_token_accuracy": 0.20263424515724182,
      "num_tokens": 15360.0,
      "step": 15
    },
    {
      "entropy": 5.262051582336426,
      "epoch": 0.009768009768009768,
      "grad_norm": 3.836217164993286,
      "learning_rate": 0.0001647025710494341,
      "loss": 4.6478,
      "mean_token_accuracy": 0.22834645211696625,
      "num_tokens": 16384.0,
      "step": 16
    },
    {
      "entropy": 5.14174747467041,
      "epoch": 0.010378510378510378,
      "grad_norm": 6.356348037719727,
      "learning_rate": 0.00015,
      "loss": 5.7193,
      "mean_token_accuracy": 0.174869105219841,
      "num_tokens": 17408.0,
      "step": 17
    },
    {
      "entropy": 4.554754734039307,
      "epoch": 0.01098901098901099,
      "grad_norm": 3.5281262397766113,
      "learning_rate": 0.0001352974289505659,
      "loss": 4.8491,
      "mean_token_accuracy": 0.22342519462108612,
      "num_tokens": 18432.0,
      "step": 18
    },
    {
      "entropy": 5.017117500305176,
      "epoch": 0.0115995115995116,
      "grad_norm": 3.1419517993927,
      "learning_rate": 0.00012073645169758076,
      "loss": 5.3589,
      "mean_token_accuracy": 0.20088790357112885,
      "num_tokens": 19456.0,
      "step": 19
    },
    {
      "entropy": 4.860474586486816,
      "epoch": 0.01221001221001221,
      "grad_norm": 3.614912986755371,
      "learning_rate": 0.00010645729841183066,
      "loss": 5.1,
      "mean_token_accuracy": 0.19789473712444305,
      "num_tokens": 20480.0,
      "step": 20
    },
    {
      "entropy": 5.405769348144531,
      "epoch": 0.01282051282051282,
      "grad_norm": 17.46617317199707,
      "learning_rate": 9.259748514523653e-05,
      "loss": 5.4736,
      "mean_token_accuracy": 0.17610710859298706,
      "num_tokens": 21504.0,
      "step": 21
    },
    {
      "entropy": 5.062948703765869,
      "epoch": 0.013431013431013432,
      "grad_norm": 3.2527050971984863,
      "learning_rate": 7.929048947610034e-05,
      "loss": 4.5604,
      "mean_token_accuracy": 0.21810699999332428,
      "num_tokens": 22528.0,
      "step": 22
    },
    {
      "entropy": 4.796494483947754,
      "epoch": 0.014041514041514042,
      "grad_norm": 3.152696132659912,
      "learning_rate": 6.66644650470597e-05,
      "loss": 4.1272,
      "mean_token_accuracy": 0.28236493468284607,
      "num_tokens": 23552.0,
      "step": 23
    },
    {
      "entropy": 4.756124496459961,
      "epoch": 0.014652014652014652,
      "grad_norm": 2.406891345977783,
      "learning_rate": 5.4841007375453186e-05,
      "loss": 4.5433,
      "mean_token_accuracy": 0.24015748500823975,
      "num_tokens": 24576.0,
      "step": 24
    },
    {
      "entropy": 4.696354389190674,
      "epoch": 0.015262515262515262,
      "grad_norm": 3.4845199584960938,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 4.6104,
      "mean_token_accuracy": 0.24015748500823975,
      "num_tokens": 25600.0,
      "step": 25
    },
    {
      "entropy": 4.748116493225098,
      "epoch": 0.015873015873015872,
      "grad_norm": 63.001136779785156,
      "learning_rate": 3.404843199558945e-05,
      "loss": 4.5619,
      "mean_token_accuracy": 0.24924011528491974,
      "num_tokens": 26624.0,
      "step": 26
    },
    {
      "entropy": 4.614930152893066,
      "epoch": 0.016483516483516484,
      "grad_norm": 2.197350025177002,
      "learning_rate": 2.5279558154618197e-05,
      "loss": 4.7666,
      "mean_token_accuracy": 0.24020101130008698,
      "num_tokens": 27648.0,
      "step": 27
    },
    {
      "entropy": 4.691383361816406,
      "epoch": 0.017094017094017096,
      "grad_norm": 2.5826752185821533,
      "learning_rate": 1.7711810347746757e-05,
      "loss": 4.6907,
      "mean_token_accuracy": 0.2278876155614853,
      "num_tokens": 28672.0,
      "step": 28
    },
    {
      "entropy": 4.772076606750488,
      "epoch": 0.017704517704517704,
      "grad_norm": 3.7122533321380615,
      "learning_rate": 1.1418070123306989e-05,
      "loss": 4.6573,
      "mean_token_accuracy": 0.20523138344287872,
      "num_tokens": 29696.0,
      "step": 29
    },
    {
      "entropy": 4.471816062927246,
      "epoch": 0.018315018315018316,
      "grad_norm": 2.352668285369873,
      "learning_rate": 6.458949640168675e-06,
      "loss": 4.3323,
      "mean_token_accuracy": 0.2381889820098877,
      "num_tokens": 30720.0,
      "step": 30
    },
    {
      "entropy": 4.810123443603516,
      "epoch": 0.018925518925518924,
      "grad_norm": 2.075646162033081,
      "learning_rate": 2.882207939515435e-06,
      "loss": 4.9162,
      "mean_token_accuracy": 0.2311507910490036,
      "num_tokens": 31744.0,
      "step": 31
    },
    {
      "entropy": 4.847671031951904,
      "epoch": 0.019536019536019536,
      "grad_norm": 2.874021291732788,
      "learning_rate": 7.222909991704773e-07,
      "loss": 4.9275,
      "mean_token_accuracy": 0.20472441613674164,
      "num_tokens": 32768.0,
      "step": 32
    }
  ],
  "logging_steps": 1,
  "max_steps": 32,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 137211949350912.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}