{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15723270440251572,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007861635220125786,
      "grad_norm": 3.0213987827301025,
      "learning_rate": 6.492727272727273e-06,
      "loss": 1.167,
      "mean_token_accuracy": 0.8948278307914734,
      "num_tokens": 243748.0,
      "step": 5
    },
    {
      "epoch": 0.015723270440251572,
      "grad_norm": 0.11831969767808914,
      "learning_rate": 1.4608636363636365e-05,
      "loss": 0.2505,
      "mean_token_accuracy": 0.9432892441749573,
      "num_tokens": 478484.0,
      "step": 10
    },
    {
      "epoch": 0.02358490566037736,
      "grad_norm": 0.576977550983429,
      "learning_rate": 2.2724545454545454e-05,
      "loss": 0.4225,
      "mean_token_accuracy": 0.9014830231666565,
      "num_tokens": 714755.0,
      "step": 15
    },
    {
      "epoch": 0.031446540880503145,
      "grad_norm": 0.5038472414016724,
      "learning_rate": 3.084045454545455e-05,
      "loss": 0.2062,
      "mean_token_accuracy": 0.9511839628219605,
      "num_tokens": 938861.0,
      "step": 20
    },
    {
      "epoch": 0.03930817610062893,
      "grad_norm": 0.10820402950048447,
      "learning_rate": 3.570983082744108e-05,
      "loss": 0.2658,
      "mean_token_accuracy": 0.9272931456565857,
      "num_tokens": 1184972.0,
      "step": 25
    },
    {
      "epoch": 0.04716981132075472,
      "grad_norm": 0.10856287181377411,
      "learning_rate": 3.5707927685240945e-05,
      "loss": 0.3296,
      "mean_token_accuracy": 0.9227312803268433,
      "num_tokens": 1439601.0,
      "step": 30
    },
    {
      "epoch": 0.055031446540880505,
      "grad_norm": 0.13562311232089996,
      "learning_rate": 3.570391023667205e-05,
      "loss": 0.1222,
      "mean_token_accuracy": 0.9637470602989197,
      "num_tokens": 1686577.0,
      "step": 35
    },
    {
      "epoch": 0.06289308176100629,
      "grad_norm": 0.1110280305147171,
      "learning_rate": 3.569777911613607e-05,
      "loss": 0.1717,
      "mean_token_accuracy": 0.950537359714508,
      "num_tokens": 1931742.0,
      "step": 40
    },
    {
      "epoch": 0.07075471698113207,
      "grad_norm": 0.3167303800582886,
      "learning_rate": 3.568953529180803e-05,
      "loss": 0.3037,
      "mean_token_accuracy": 0.9172726392745971,
      "num_tokens": 2174477.0,
      "step": 45
    },
    {
      "epoch": 0.07861635220125786,
      "grad_norm": 0.33226126432418823,
      "learning_rate": 3.567918006548335e-05,
      "loss": 0.2245,
      "mean_token_accuracy": 0.9457881450653076,
      "num_tokens": 2413863.0,
      "step": 50
    },
    {
      "epoch": 0.08647798742138364,
      "grad_norm": 0.13773199915885925,
      "learning_rate": 3.566671507237232e-05,
      "loss": 0.216,
      "mean_token_accuracy": 0.9455354571342468,
      "num_tokens": 2659910.0,
      "step": 55
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 0.07179869711399078,
      "learning_rate": 3.565214228084184e-05,
      "loss": 0.1916,
      "mean_token_accuracy": 0.9463666200637817,
      "num_tokens": 2899168.0,
      "step": 60
    },
    {
      "epoch": 0.10220125786163523,
      "grad_norm": 0.10081195086240768,
      "learning_rate": 3.563546399210463e-05,
      "loss": 0.2032,
      "mean_token_accuracy": 0.9378719687461853,
      "num_tokens": 3144079.0,
      "step": 65
    },
    {
      "epoch": 0.11006289308176101,
      "grad_norm": 0.11605896055698395,
      "learning_rate": 3.561668283985582e-05,
      "loss": 0.2079,
      "mean_token_accuracy": 0.9464151382446289,
      "num_tokens": 3386245.0,
      "step": 70
    },
    {
      "epoch": 0.1179245283018868,
      "grad_norm": 0.37404799461364746,
      "learning_rate": 3.559580178985706e-05,
      "loss": 0.1553,
      "mean_token_accuracy": 0.9538340926170349,
      "num_tokens": 3633576.0,
      "step": 75
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": 0.10142400115728378,
      "learning_rate": 3.557282413946822e-05,
      "loss": 0.2372,
      "mean_token_accuracy": 0.9347850561141968,
      "num_tokens": 3883799.0,
      "step": 80
    },
    {
      "epoch": 0.13364779874213836,
      "grad_norm": 0.09328413009643555,
      "learning_rate": 3.5547753517126655e-05,
      "loss": 0.2395,
      "mean_token_accuracy": 0.9314639449119568,
      "num_tokens": 4125110.0,
      "step": 85
    },
    {
      "epoch": 0.14150943396226415,
      "grad_norm": 0.573935866355896,
      "learning_rate": 3.552059388177427e-05,
      "loss": 0.2638,
      "mean_token_accuracy": 0.932257080078125,
      "num_tokens": 4370521.0,
      "step": 90
    },
    {
      "epoch": 0.14937106918238993,
      "grad_norm": 0.13649845123291016,
      "learning_rate": 3.549134952223232e-05,
      "loss": 0.149,
      "mean_token_accuracy": 0.9563753366470337,
      "num_tokens": 4616430.0,
      "step": 95
    },
    {
      "epoch": 0.15723270440251572,
      "grad_norm": 0.12769070267677307,
      "learning_rate": 3.546002505652419e-05,
      "loss": 0.1694,
      "mean_token_accuracy": 0.9526991248130798,
      "num_tokens": 4859373.0,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 1272,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0786560826304102e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}