{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.3193361535668373,
      "epoch": 0.051118210862619806,
      "grad_norm": 0.8119011521339417,
      "learning_rate": 0.0,
      "loss": 1.692,
      "mean_token_accuracy": 0.654717817902565,
      "num_tokens": 133947.0,
      "step": 1
    },
    {
      "entropy": 1.3207192197442055,
      "epoch": 0.10223642172523961,
      "grad_norm": 0.8001739382743835,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.6938,
      "mean_token_accuracy": 0.6540814265608788,
      "num_tokens": 267949.0,
      "step": 2
    },
    {
      "entropy": 1.3139144703745842,
      "epoch": 0.15335463258785942,
      "grad_norm": 0.8021382689476013,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6875,
      "mean_token_accuracy": 0.6542951986193657,
      "num_tokens": 402435.0,
      "step": 3
    },
    {
      "entropy": 1.3238477781414986,
      "epoch": 0.20447284345047922,
      "grad_norm": 0.8046473264694214,
      "learning_rate": 6e-06,
      "loss": 1.6979,
      "mean_token_accuracy": 0.6523041352629662,
      "num_tokens": 536339.0,
      "step": 4
    },
    {
      "entropy": 1.3151762038469315,
      "epoch": 0.25559105431309903,
      "grad_norm": 0.7999162077903748,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6884,
      "mean_token_accuracy": 0.6541883014142513,
      "num_tokens": 670396.0,
      "step": 5
    },
    {
      "entropy": 1.3171968907117844,
      "epoch": 0.30670926517571884,
      "grad_norm": 0.8070191740989685,
      "learning_rate": 1e-05,
      "loss": 1.6881,
      "mean_token_accuracy": 0.6536356993019581,
      "num_tokens": 804575.0,
      "step": 6
    },
    {
      "entropy": 1.3177252262830734,
      "epoch": 0.35782747603833864,
      "grad_norm": 0.8115559220314026,
      "learning_rate": 1.2e-05,
      "loss": 1.6852,
      "mean_token_accuracy": 0.6539545804262161,
      "num_tokens": 938351.0,
      "step": 7
    },
    {
      "entropy": 1.3142458871006966,
      "epoch": 0.40894568690095845,
      "grad_norm": 0.809145987033844,
      "learning_rate": 1.4e-05,
      "loss": 1.6739,
      "mean_token_accuracy": 0.6544475704431534,
      "num_tokens": 1072655.0,
      "step": 8
    },
    {
      "entropy": 1.3176514655351639,
      "epoch": 0.46006389776357826,
      "grad_norm": 0.8079097270965576,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6733,
      "mean_token_accuracy": 0.6541223935782909,
      "num_tokens": 1206472.0,
      "step": 9
    },
    {
      "entropy": 1.3175865784287453,
      "epoch": 0.5111821086261981,
      "grad_norm": 0.8009534478187561,
      "learning_rate": 1.8e-05,
      "loss": 1.657,
      "mean_token_accuracy": 0.655005007982254,
      "num_tokens": 1340462.0,
      "step": 10
    },
    {
      "entropy": 1.3152535259723663,
      "epoch": 0.5623003194888179,
      "grad_norm": 0.7782304883003235,
      "learning_rate": 2e-05,
      "loss": 1.6391,
      "mean_token_accuracy": 0.6572432741522789,
      "num_tokens": 1474818.0,
      "step": 11
    },
    {
      "entropy": 1.31825902312994,
      "epoch": 0.6134185303514377,
      "grad_norm": 0.7459490299224854,
      "learning_rate": 1.977777777777778e-05,
      "loss": 1.6261,
      "mean_token_accuracy": 0.6601505167782307,
      "num_tokens": 1608731.0,
      "step": 12
    },
    {
      "entropy": 1.322536252439022,
      "epoch": 0.6645367412140575,
      "grad_norm": 0.7278594970703125,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 1.6056,
      "mean_token_accuracy": 0.6621886678040028,
      "num_tokens": 1742229.0,
      "step": 13
    },
    {
      "entropy": 1.3205925300717354,
      "epoch": 0.7156549520766773,
      "grad_norm": 0.6732656359672546,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 1.587,
      "mean_token_accuracy": 0.6625417172908783,
      "num_tokens": 1875890.0,
      "step": 14
    },
    {
      "entropy": 1.3151337951421738,
      "epoch": 0.7667731629392971,
      "grad_norm": 0.6385083794593811,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 1.5551,
      "mean_token_accuracy": 0.6706915572285652,
      "num_tokens": 2009719.0,
      "step": 15
    },
    {
      "entropy": 1.3125323951244354,
      "epoch": 0.8178913738019169,
      "grad_norm": 0.6251479387283325,
      "learning_rate": 1.888888888888889e-05,
      "loss": 1.5312,
      "mean_token_accuracy": 0.6725872829556465,
      "num_tokens": 2143710.0,
      "step": 16
    },
    {
      "entropy": 1.3094838485121727,
      "epoch": 0.8690095846645367,
      "grad_norm": 0.6229560375213623,
      "learning_rate": 1.866666666666667e-05,
      "loss": 1.5063,
      "mean_token_accuracy": 0.6759799160063267,
      "num_tokens": 2277556.0,
      "step": 17
    },
    {
      "entropy": 1.3096359893679619,
      "epoch": 0.9201277955271565,
      "grad_norm": 0.6263618469238281,
      "learning_rate": 1.8444444444444448e-05,
      "loss": 1.4846,
      "mean_token_accuracy": 0.6817599721252918,
      "num_tokens": 2411448.0,
      "step": 18
    },
    {
      "entropy": 1.2960194796323776,
      "epoch": 0.9712460063897763,
      "grad_norm": 0.6250044703483582,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 1.4525,
      "mean_token_accuracy": 0.6899448521435261,
      "num_tokens": 2545738.0,
      "step": 19
    },
    {
      "entropy": 1.2956058846579657,
      "epoch": 1.0,
      "grad_norm": 0.6314756870269775,
      "learning_rate": 1.8e-05,
      "loss": 1.4391,
      "mean_token_accuracy": 0.6940541995896233,
      "num_tokens": 2616926.0,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2829632706174976e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}