{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 83.33333333333333,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.9060055136680603,
      "epoch": 3.3333333333333335,
      "grad_norm": 1.0164649486541748,
      "learning_rate": 1.5e-05,
      "loss": 4.1011,
      "mean_token_accuracy": 0.4009168431162834,
      "num_tokens": 5512.0,
      "step": 10
    },
    {
      "entropy": 1.9487085342407227,
      "epoch": 6.666666666666667,
      "grad_norm": 0.9628961682319641,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 4.1923,
      "mean_token_accuracy": 0.39442635476589205,
      "num_tokens": 10326.0,
      "step": 20
    },
    {
      "entropy": 1.8993895709514619,
      "epoch": 10.0,
      "grad_norm": 1.177027702331543,
      "learning_rate": 4.8333333333333334e-05,
      "loss": 4.0334,
      "mean_token_accuracy": 0.40877673774957657,
      "num_tokens": 15462.0,
      "step": 30
    },
    {
      "entropy": 1.9950154840946197,
      "epoch": 13.333333333333334,
      "grad_norm": 1.436251163482666,
      "learning_rate": 4.9863047384206835e-05,
      "loss": 3.9342,
      "mean_token_accuracy": 0.40931957215070724,
      "num_tokens": 20681.0,
      "step": 40
    },
    {
      "entropy": 2.067208158969879,
      "epoch": 16.666666666666668,
      "grad_norm": 1.078131079673767,
      "learning_rate": 4.939155700460536e-05,
      "loss": 3.7698,
      "mean_token_accuracy": 0.42098456621170044,
      "num_tokens": 26109.0,
      "step": 50
    },
    {
      "entropy": 2.193948692083359,
      "epoch": 20.0,
      "grad_norm": 1.1934932470321655,
      "learning_rate": 4.859021265983959e-05,
      "loss": 3.6115,
      "mean_token_accuracy": 0.43236732184886933,
      "num_tokens": 31244.0,
      "step": 60
    },
    {
      "entropy": 2.4151065587997436,
      "epoch": 23.333333333333332,
      "grad_norm": 0.8595532774925232,
      "learning_rate": 4.7469851157479177e-05,
      "loss": 3.5401,
      "mean_token_accuracy": 0.42654525190591813,
      "num_tokens": 36738.0,
      "step": 70
    },
    {
      "entropy": 2.4695091366767885,
      "epoch": 26.666666666666668,
      "grad_norm": 0.9981549978256226,
      "learning_rate": 4.604562346488144e-05,
      "loss": 3.3173,
      "mean_token_accuracy": 0.4566218167543411,
      "num_tokens": 41886.0,
      "step": 80
    },
    {
      "entropy": 2.4938253283500673,
      "epoch": 30.0,
      "grad_norm": 0.5646995902061462,
      "learning_rate": 4.43367898183491e-05,
      "loss": 3.1822,
      "mean_token_accuracy": 0.4696041285991669,
      "num_tokens": 46983.0,
      "step": 90
    },
    {
      "entropy": 2.564500260353088,
      "epoch": 33.333333333333336,
      "grad_norm": 0.8602616786956787,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 3.1409,
      "mean_token_accuracy": 0.47821263819932935,
      "num_tokens": 52150.0,
      "step": 100
    },
    {
      "entropy": 2.5386017203330993,
      "epoch": 36.666666666666664,
      "grad_norm": 0.7394922971725464,
      "learning_rate": 4.0161277134970345e-05,
      "loss": 2.9888,
      "mean_token_accuracy": 0.49289675503969194,
      "num_tokens": 57240.0,
      "step": 110
    },
    {
      "entropy": 2.5600393176078797,
      "epoch": 40.0,
      "grad_norm": 0.6606329083442688,
      "learning_rate": 3.775106474414188e-05,
      "loss": 2.9445,
      "mean_token_accuracy": 0.5016584262251854,
      "num_tokens": 62806.0,
      "step": 120
    },
    {
      "entropy": 2.547697913646698,
      "epoch": 43.333333333333336,
      "grad_norm": 0.8845142126083374,
      "learning_rate": 3.516841607689501e-05,
      "loss": 2.9015,
      "mean_token_accuracy": 0.5097966089844703,
      "num_tokens": 67877.0,
      "step": 130
    },
    {
      "entropy": 2.5584489583969114,
      "epoch": 46.666666666666664,
      "grad_norm": 0.8559042811393738,
      "learning_rate": 3.244825702596205e-05,
      "loss": 2.9204,
      "mean_token_accuracy": 0.503237409889698,
      "num_tokens": 73030.0,
      "step": 140
    },
    {
      "entropy": 2.479199802875519,
      "epoch": 50.0,
      "grad_norm": 0.9662401080131531,
      "learning_rate": 2.9627373076117863e-05,
      "loss": 2.7848,
      "mean_token_accuracy": 0.5199230208992958,
      "num_tokens": 78133.0,
      "step": 150
    },
    {
      "entropy": 2.451095724105835,
      "epoch": 53.333333333333336,
      "grad_norm": 0.7248209714889526,
      "learning_rate": 2.674391184360313e-05,
      "loss": 2.72,
      "mean_token_accuracy": 0.530137126147747,
      "num_tokens": 83587.0,
      "step": 160
    },
    {
      "entropy": 2.4100263833999636,
      "epoch": 56.666666666666664,
      "grad_norm": 0.8213902115821838,
      "learning_rate": 2.3836867195056335e-05,
      "loss": 2.6899,
      "mean_token_accuracy": 0.5364036962389946,
      "num_tokens": 88745.0,
      "step": 170
    },
    {
      "entropy": 2.3743161976337435,
      "epoch": 60.0,
      "grad_norm": 0.9216499924659729,
      "learning_rate": 2.0945551922360818e-05,
      "loss": 2.6164,
      "mean_token_accuracy": 0.5464533418416977,
      "num_tokens": 93971.0,
      "step": 180
    },
    {
      "entropy": 2.3309614181518556,
      "epoch": 63.333333333333336,
      "grad_norm": 0.9028099179267883,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 2.577,
      "mean_token_accuracy": 0.5494851708412171,
      "num_tokens": 99176.0,
      "step": 190
    },
    {
      "entropy": 2.3660804867744445,
      "epoch": 66.66666666666667,
      "grad_norm": 1.1050912141799927,
      "learning_rate": 1.5365768346438797e-05,
      "loss": 2.6015,
      "mean_token_accuracy": 0.5429237529635429,
      "num_tokens": 104369.0,
      "step": 200
    },
    {
      "entropy": 2.2412913620471953,
      "epoch": 70.0,
      "grad_norm": 1.1248013973236084,
      "learning_rate": 1.2752757044047827e-05,
      "loss": 2.4471,
      "mean_token_accuracy": 0.5652078241109848,
      "num_tokens": 109867.0,
      "step": 210
    },
    {
      "entropy": 2.2687363147735597,
      "epoch": 73.33333333333333,
      "grad_norm": 0.8138008117675781,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 2.4754,
      "mean_token_accuracy": 0.5577909976243973,
      "num_tokens": 115316.0,
      "step": 220
    },
    {
      "entropy": 2.2360614061355593,
      "epoch": 76.66666666666667,
      "grad_norm": 0.9668932557106018,
      "learning_rate": 8.056700021356694e-06,
      "loss": 2.4623,
      "mean_token_accuracy": 0.5630308628082276,
      "num_tokens": 120487.0,
      "step": 230
    },
    {
      "entropy": 2.28078556060791,
      "epoch": 80.0,
      "grad_norm": 0.9901016354560852,
      "learning_rate": 6.037160416278278e-06,
      "loss": 2.5002,
      "mean_token_accuracy": 0.5567112416028976,
      "num_tokens": 125629.0,
      "step": 240
    },
    {
      "entropy": 2.2194084882736207,
      "epoch": 83.33333333333333,
      "grad_norm": 1.047966480255127,
      "learning_rate": 4.274060686123959e-06,
      "loss": 2.418,
      "mean_token_accuracy": 0.5643551826477051,
      "num_tokens": 130811.0,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5636363954499584e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}