{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 487,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.3576307667791843,
      "epoch": 0.05136106831022085,
      "grad_norm": 0.043701171875,
      "learning_rate": 0.00019982063367958905,
      "loss": 1.4367686462402345,
      "mean_token_accuracy": 0.674539436250925,
      "num_tokens": 137943.0,
      "step": 25
    },
    {
      "entropy": 1.2529647310450673,
      "epoch": 0.1027221366204417,
      "grad_norm": 0.0556640625,
      "learning_rate": 0.00019745029836206813,
      "loss": 1.2378319549560546,
      "mean_token_accuracy": 0.6993680514395237,
      "num_tokens": 275874.0,
      "step": 50
    },
    {
      "entropy": 1.072294548302889,
      "epoch": 0.15408320493066255,
      "grad_norm": 0.0693359375,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.0764490509033202,
      "mean_token_accuracy": 0.7323865121603013,
      "num_tokens": 415735.0,
      "step": 75
    },
    {
      "entropy": 0.9906732020527125,
      "epoch": 0.2054442732408834,
      "grad_norm": 0.0771484375,
      "learning_rate": 0.0001847734427889671,
      "loss": 0.9877787780761719,
      "mean_token_accuracy": 0.7549690430611372,
      "num_tokens": 554028.0,
      "step": 100
    },
    {
      "entropy": 0.9013515400886536,
      "epoch": 0.25680534155110424,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.00017481711355307736,
      "loss": 0.8821546173095703,
      "mean_token_accuracy": 0.7694066467881203,
      "num_tokens": 692688.0,
      "step": 125
    },
    {
      "entropy": 0.8495864383503795,
      "epoch": 0.3081664098613251,
      "grad_norm": 0.173828125,
      "learning_rate": 0.0001627940035501152,
      "loss": 0.8549539184570313,
      "mean_token_accuracy": 0.7832678698003293,
      "num_tokens": 830965.0,
      "step": 150
    },
    {
      "entropy": 0.8344065735861659,
      "epoch": 0.35952747817154596,
      "grad_norm": 0.115234375,
      "learning_rate": 0.00014903624444534316,
      "loss": 0.814236068725586,
      "mean_token_accuracy": 0.7979693514108658,
      "num_tokens": 969488.0,
      "step": 175
    },
    {
      "entropy": 0.6604279239103198,
      "epoch": 0.4108885464817668,
      "grad_norm": 0.11328125,
      "learning_rate": 0.00013392388661180303,
      "loss": 0.6531913757324219,
      "mean_token_accuracy": 0.8297484306991101,
      "num_tokens": 1108408.0,
      "step": 200
    },
    {
      "entropy": 0.6039412962645292,
      "epoch": 0.4622496147919877,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.00011787440045208286,
      "loss": 0.5853654098510742,
      "mean_token_accuracy": 0.8489190977811814,
      "num_tokens": 1243022.0,
      "step": 225
    },
    {
      "entropy": 0.5606526596471667,
      "epoch": 0.5136106831022085,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00010133114401277139,
      "loss": 0.5556794738769532,
      "mean_token_accuracy": 0.8629096284508705,
      "num_tokens": 1380348.0,
      "step": 250
    },
    {
      "entropy": 0.474326101411134,
      "epoch": 0.5649717514124294,
      "grad_norm": 0.1328125,
      "learning_rate": 8.475111546727802e-05,
      "loss": 0.4202105712890625,
      "mean_token_accuracy": 0.8853555226325989,
      "num_tokens": 1515854.0,
      "step": 275
    },
    {
      "entropy": 0.38802217997610566,
      "epoch": 0.6163328197226502,
      "grad_norm": 0.109375,
      "learning_rate": 6.859232879780515e-05,
      "loss": 0.34782024383544924,
      "mean_token_accuracy": 0.9080075736343861,
      "num_tokens": 1654779.0,
      "step": 300
    },
    {
      "entropy": 0.3737848504073918,
      "epoch": 0.6676938880328711,
      "grad_norm": 0.1376953125,
      "learning_rate": 5.330116141617308e-05,
      "loss": 0.3438681030273438,
      "mean_token_accuracy": 0.9156272406876087,
      "num_tokens": 1791738.0,
      "step": 325
    },
    {
      "entropy": 0.28668822450563314,
      "epoch": 0.7190549563430919,
      "grad_norm": 0.08544921875,
      "learning_rate": 3.930002323837025e-05,
      "loss": 0.2531709861755371,
      "mean_token_accuracy": 0.9349550317972899,
      "num_tokens": 1929352.0,
      "step": 350
    },
    {
      "entropy": 0.25361579390242694,
      "epoch": 0.7704160246533128,
      "grad_norm": 0.09375,
      "learning_rate": 2.6975687847722196e-05,
      "loss": 0.20507081985473632,
      "mean_token_accuracy": 0.94629997164011,
      "num_tokens": 2071685.0,
      "step": 375
    },
    {
      "entropy": 0.2485706583969295,
      "epoch": 0.8217770929635336,
      "grad_norm": 0.1279296875,
      "learning_rate": 1.6668608091748495e-05,
      "loss": 0.2095647621154785,
      "mean_token_accuracy": 0.9520989653468132,
      "num_tokens": 2211970.0,
      "step": 400
    },
    {
      "entropy": 0.2243186465650797,
      "epoch": 0.8731381612737545,
      "grad_norm": 0.158203125,
      "learning_rate": 8.663511263346114e-06,
      "loss": 0.15317897796630858,
      "mean_token_accuracy": 0.9573097968101502,
      "num_tokens": 2349802.0,
      "step": 425
    },
    {
      "entropy": 0.17523488430306317,
      "epoch": 0.9244992295839753,
      "grad_norm": 0.1083984375,
      "learning_rate": 3.181533669140346e-06,
      "loss": 0.12748973846435546,
      "mean_token_accuracy": 0.966678860783577,
      "num_tokens": 2486071.0,
      "step": 450
    },
    {
      "entropy": 0.19582400802522898,
      "epoch": 0.9758602978941961,
      "grad_norm": 0.123046875,
      "learning_rate": 3.7411186313812687e-07,
      "loss": 0.14464641571044923,
      "mean_token_accuracy": 0.9607194331288338,
      "num_tokens": 2622509.0,
      "step": 475
    }
  ],
  "logging_steps": 25,
  "max_steps": 487,
  "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": 2.2664497318482125e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}