{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 244,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.0842015266418457,
      "epoch": 0.0823045267489712,
      "grad_norm": 1.2566404342651367,
      "learning_rate": 1.999911398855782e-05,
      "loss": 1.1726,
      "mean_token_accuracy": 0.6686171144247055,
      "num_tokens": 609981.0,
      "step": 10
    },
    {
      "entropy": 0.9032916635274887,
      "epoch": 0.1646090534979424,
      "grad_norm": 0.7735289931297302,
      "learning_rate": 1.9892982458192286e-05,
      "loss": 0.8736,
      "mean_token_accuracy": 0.7255816429853439,
      "num_tokens": 1206011.0,
      "step": 20
    },
    {
      "entropy": 0.8239103972911834,
      "epoch": 0.24691358024691357,
      "grad_norm": 0.6542304158210754,
      "learning_rate": 1.9611801152462715e-05,
      "loss": 0.7927,
      "mean_token_accuracy": 0.7448168516159057,
      "num_tokens": 1810330.0,
      "step": 30
    },
    {
      "entropy": 0.7995721608400345,
      "epoch": 0.3292181069958848,
      "grad_norm": 0.6543221473693848,
      "learning_rate": 1.916054538842971e-05,
      "loss": 0.7673,
      "mean_token_accuracy": 0.7500824242830276,
      "num_tokens": 2411257.0,
      "step": 40
    },
    {
      "entropy": 0.7843733370304108,
      "epoch": 0.411522633744856,
      "grad_norm": 0.6735917329788208,
      "learning_rate": 1.8547199838102904e-05,
      "loss": 0.7481,
      "mean_token_accuracy": 0.7548356115818023,
      "num_tokens": 3022014.0,
      "step": 50
    },
    {
      "entropy": 0.76707524061203,
      "epoch": 0.49382716049382713,
      "grad_norm": 0.6267600655555725,
      "learning_rate": 1.778261724495566e-05,
      "loss": 0.7368,
      "mean_token_accuracy": 0.7574090182781219,
      "num_tokens": 3637233.0,
      "step": 60
    },
    {
      "entropy": 0.7542366564273835,
      "epoch": 0.5761316872427984,
      "grad_norm": 0.6589949131011963,
      "learning_rate": 1.6880326391813917e-05,
      "loss": 0.7172,
      "mean_token_accuracy": 0.7609850108623505,
      "num_tokens": 4242671.0,
      "step": 70
    },
    {
      "entropy": 0.74325290620327,
      "epoch": 0.6584362139917695,
      "grad_norm": 0.6847052574157715,
      "learning_rate": 1.5856292718000235e-05,
      "loss": 0.7053,
      "mean_token_accuracy": 0.7654363572597503,
      "num_tokens": 4842730.0,
      "step": 80
    },
    {
      "entropy": 0.7401553928852082,
      "epoch": 0.7407407407407407,
      "grad_norm": 0.6277093291282654,
      "learning_rate": 1.4728635821454255e-05,
      "loss": 0.7037,
      "mean_token_accuracy": 0.7650831431150437,
      "num_tokens": 5460571.0,
      "step": 90
    },
    {
      "entropy": 0.7254371553659439,
      "epoch": 0.823045267489712,
      "grad_norm": 0.6459594368934631,
      "learning_rate": 1.351730884444245e-05,
      "loss": 0.6869,
      "mean_token_accuracy": 0.7702283948659897,
      "num_tokens": 6058130.0,
      "step": 100
    },
    {
      "entropy": 0.7227081388235093,
      "epoch": 0.9053497942386831,
      "grad_norm": 0.6610374450683594,
      "learning_rate": 1.2243745415914882e-05,
      "loss": 0.6827,
      "mean_token_accuracy": 0.7705969363451004,
      "num_tokens": 6665354.0,
      "step": 110
    },
    {
      "entropy": 0.7182952612638474,
      "epoch": 0.9876543209876543,
      "grad_norm": 0.6171860098838806,
      "learning_rate": 1.0930480397630146e-05,
      "loss": 0.6793,
      "mean_token_accuracy": 0.7711377799510956,
      "num_tokens": 7279924.0,
      "step": 120
    },
    {
      "entropy": 0.6223280147502297,
      "epoch": 1.0658436213991769,
      "grad_norm": 0.6846635341644287,
      "learning_rate": 9.600751144694827e-06,
      "loss": 0.5587,
      "mean_token_accuracy": 0.8087636044150904,
      "num_tokens": 7855601.0,
      "step": 130
    },
    {
      "entropy": 0.5616398304700851,
      "epoch": 1.1481481481481481,
      "grad_norm": 0.6427133083343506,
      "learning_rate": 8.278086335948191e-06,
      "loss": 0.5056,
      "mean_token_accuracy": 0.821845856308937,
      "num_tokens": 8458600.0,
      "step": 140
    },
    {
      "entropy": 0.5549788802862168,
      "epoch": 1.2304526748971194,
      "grad_norm": 0.623350203037262,
      "learning_rate": 6.9858896495663046e-06,
      "loss": 0.5165,
      "mean_token_accuracy": 0.8178219944238663,
      "num_tokens": 9066971.0,
      "step": 150
    },
    {
      "entropy": 0.556912761926651,
      "epoch": 1.3127572016460904,
      "grad_norm": 0.6478646397590637,
      "learning_rate": 5.747025650470135e-06,
      "loss": 0.5115,
      "mean_token_accuracy": 0.8192351371049881,
      "num_tokens": 9676134.0,
      "step": 160
    },
    {
      "entropy": 0.5518900156021118,
      "epoch": 1.3950617283950617,
      "grad_norm": 0.6248000264167786,
      "learning_rate": 4.583415216985791e-06,
      "loss": 0.5095,
      "mean_token_accuracy": 0.8200697928667069,
      "num_tokens": 10281801.0,
      "step": 170
    },
    {
      "entropy": 0.5520358562469483,
      "epoch": 1.477366255144033,
      "grad_norm": 0.6373401284217834,
      "learning_rate": 3.51564766541435e-06,
      "loss": 0.5063,
      "mean_token_accuracy": 0.8212656050920486,
      "num_tokens": 10894137.0,
      "step": 180
    },
    {
      "entropy": 0.5422273725271225,
      "epoch": 1.5596707818930042,
      "grad_norm": 0.6336973905563354,
      "learning_rate": 2.5626164357101857e-06,
      "loss": 0.5016,
      "mean_token_accuracy": 0.8229126304388046,
      "num_tokens": 11497132.0,
      "step": 190
    },
    {
      "entropy": 0.5529572516679764,
      "epoch": 1.6419753086419753,
      "grad_norm": 0.6020342707633972,
      "learning_rate": 1.7411847845686082e-06,
      "loss": 0.5072,
      "mean_token_accuracy": 0.8205246955156327,
      "num_tokens": 12111651.0,
      "step": 200
    },
    {
      "entropy": 0.5367681249976158,
      "epoch": 1.7242798353909465,
      "grad_norm": 0.6049624681472778,
      "learning_rate": 1.0658874012622244e-06,
      "loss": 0.4914,
      "mean_token_accuracy": 0.8258270412683487,
      "num_tokens": 12715771.0,
      "step": 210
    },
    {
      "entropy": 0.5322598591446877,
      "epoch": 1.8065843621399176,
      "grad_norm": 0.6055402755737305,
      "learning_rate": 5.486732259363647e-07,
      "loss": 0.4899,
      "mean_token_accuracy": 0.8261870980262757,
      "num_tokens": 13321360.0,
      "step": 220
    },
    {
      "entropy": 0.537242217361927,
      "epoch": 1.8888888888888888,
      "grad_norm": 0.6070998311042786,
      "learning_rate": 1.986940210234922e-07,
      "loss": 0.4928,
      "mean_token_accuracy": 0.8254955172538757,
      "num_tokens": 13923829.0,
      "step": 230
    },
    {
      "entropy": 0.5378372967243195,
      "epoch": 1.97119341563786,
      "grad_norm": 0.6216578483581543,
      "learning_rate": 2.2142436865499884e-08,
      "loss": 0.4978,
      "mean_token_accuracy": 0.823452839255333,
      "num_tokens": 14530681.0,
      "step": 240
    }
  ],
  "logging_steps": 10,
  "max_steps": 244,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.30369816421335e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}