{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.3042053000070155,
      "epoch": 0.09633911368015415,
      "grad_norm": 0.0284423828125,
      "learning_rate": 0.00019801724878485438,
      "loss": 1.2869200134277343,
      "mean_token_accuracy": 0.7155025105923414,
      "num_tokens": 341278.0,
      "step": 25
    },
    {
      "entropy": 0.7955485013616271,
      "epoch": 0.1926782273603083,
      "grad_norm": 0.02880859375,
      "learning_rate": 0.00018721912643966055,
      "loss": 0.7173126220703125,
      "mean_token_accuracy": 0.8372970945760607,
      "num_tokens": 686260.0,
      "step": 50
    },
    {
      "entropy": 0.47250107586733064,
      "epoch": 0.28901734104046245,
      "grad_norm": 0.032958984375,
      "learning_rate": 0.00016801727377709194,
      "loss": 0.4062905502319336,
      "mean_token_accuracy": 0.9038537470623851,
      "num_tokens": 1030728.0,
      "step": 75
    },
    {
      "entropy": 0.422030293449061,
      "epoch": 0.3853564547206166,
      "grad_norm": 0.031494140625,
      "learning_rate": 0.00014226182617406996,
      "loss": 0.3915938568115234,
      "mean_token_accuracy": 0.919415234401822,
      "num_tokens": 1373086.0,
      "step": 100
    },
    {
      "entropy": 0.28425011701183395,
      "epoch": 0.4816955684007707,
      "grad_norm": 0.038330078125,
      "learning_rate": 0.00011243437046474853,
      "loss": 0.2796792221069336,
      "mean_token_accuracy": 0.9474510619416833,
      "num_tokens": 1719238.0,
      "step": 125
    },
    {
      "entropy": 0.26716867173672654,
      "epoch": 0.5780346820809249,
      "grad_norm": 0.0118408203125,
      "learning_rate": 8.140883928370855e-05,
      "loss": 0.2717741394042969,
      "mean_token_accuracy": 0.9527556761726736,
      "num_tokens": 2061582.0,
      "step": 150
    },
    {
      "entropy": 0.18072416053852067,
      "epoch": 0.674373795761079,
      "grad_norm": 0.02587890625,
      "learning_rate": 5.217460213786821e-05,
      "loss": 0.17744203567504882,
      "mean_token_accuracy": 0.9676880412921309,
      "num_tokens": 2401754.0,
      "step": 175
    },
    {
      "entropy": 0.20998084332444705,
      "epoch": 0.7707129094412332,
      "grad_norm": 0.01416015625,
      "learning_rate": 2.7548433914072734e-05,
      "loss": 0.21284116744995119,
      "mean_token_accuracy": 0.9640939806401729,
      "num_tokens": 2745913.0,
      "step": 200
    },
    {
      "entropy": 0.19917077658581547,
      "epoch": 0.8670520231213873,
      "grad_norm": 0.01226806640625,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.2105904006958008,
      "mean_token_accuracy": 0.9653056095913053,
      "num_tokens": 3084344.0,
      "step": 225
    },
    {
      "entropy": 0.26477424080716444,
      "epoch": 0.9633911368015414,
      "grad_norm": 0.01068115234375,
      "learning_rate": 9.388005586947191e-07,
      "loss": 0.28103506088256835,
      "mean_token_accuracy": 0.9547687808051706,
      "num_tokens": 3427378.0,
      "step": 250
    }
  ],
  "logging_steps": 25,
  "max_steps": 260,
  "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": 1.519335256379996e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}