{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.34088972217487645,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.163015019595623,
      "epoch": 0.01704448610874382,
      "grad_norm": 0.050537109375,
      "learning_rate": 0.00010666666666666667,
      "loss": 2.4524998474121094,
      "mean_token_accuracy": 0.5153323707729578,
      "num_tokens": 132137.0,
      "step": 25
    },
    {
      "entropy": 2.2185084584355352,
      "epoch": 0.03408897221748764,
      "grad_norm": 0.068359375,
      "learning_rate": 0.000199996095299633,
      "loss": 2.173491668701172,
      "mean_token_accuracy": 0.5537562420964242,
      "num_tokens": 261404.0,
      "step": 50
    },
    {
      "entropy": 1.9352111649513244,
      "epoch": 0.051133458326231465,
      "grad_norm": 0.1376953125,
      "learning_rate": 0.0001997948280489004,
      "loss": 1.8705439758300781,
      "mean_token_accuracy": 0.5959619037806988,
      "num_tokens": 396323.0,
      "step": 75
    },
    {
      "entropy": 1.76205413736403,
      "epoch": 0.06817794443497528,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00019928920737019733,
      "loss": 1.6511923217773437,
      "mean_token_accuracy": 0.6337622724473476,
      "num_tokens": 527358.0,
      "step": 100
    },
    {
      "entropy": 1.4949746784381568,
      "epoch": 0.08522243054371911,
      "grad_norm": 0.0625,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.3673600769042968,
      "mean_token_accuracy": 0.6848376739770174,
      "num_tokens": 655447.0,
      "step": 125
    },
    {
      "entropy": 1.4837670608237385,
      "epoch": 0.10226691665246293,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.0001973719973913012,
      "loss": 1.4141250610351563,
      "mean_token_accuracy": 0.6836329951137304,
      "num_tokens": 790490.0,
      "step": 150
    },
    {
      "entropy": 1.3150090302992612,
      "epoch": 0.11931140276120675,
      "grad_norm": 0.091796875,
      "learning_rate": 0.00019596625518199077,
      "loss": 1.2282736968994141,
      "mean_token_accuracy": 0.7172392677515745,
      "num_tokens": 925069.0,
      "step": 175
    },
    {
      "entropy": 1.3966816508676856,
      "epoch": 0.13635588886995056,
      "grad_norm": 0.0712890625,
      "learning_rate": 0.00019426783589406642,
      "loss": 1.3173268127441407,
      "mean_token_accuracy": 0.7017394271492958,
      "num_tokens": 1052891.0,
      "step": 200
    },
    {
      "entropy": 1.2435051177628338,
      "epoch": 0.15340037497869438,
      "grad_norm": 0.042236328125,
      "learning_rate": 0.00019228191935240007,
      "loss": 1.115916519165039,
      "mean_token_accuracy": 0.7378023877739907,
      "num_tokens": 1184065.0,
      "step": 225
    },
    {
      "entropy": 1.3924890440981834,
      "epoch": 0.17044486108743823,
      "grad_norm": 0.072265625,
      "learning_rate": 0.00019001456218857208,
      "loss": 1.288157958984375,
      "mean_token_accuracy": 0.7004149560630322,
      "num_tokens": 1313612.0,
      "step": 250
    },
    {
      "entropy": 1.3593159637693315,
      "epoch": 0.18748934719618204,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.00018747267936940722,
      "loss": 1.2840399169921874,
      "mean_token_accuracy": 0.7129683202505112,
      "num_tokens": 1444287.0,
      "step": 275
    },
    {
      "entropy": 1.2371155321784317,
      "epoch": 0.20453383330492586,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00018466402310776708,
      "loss": 1.1687215423583985,
      "mean_token_accuracy": 0.73335683144629,
      "num_tokens": 1577307.0,
      "step": 300
    },
    {
      "entropy": 1.2478438840154558,
      "epoch": 0.22157831941366968,
      "grad_norm": 0.06005859375,
      "learning_rate": 0.00018159715921991612,
      "loss": 1.20022216796875,
      "mean_token_accuracy": 0.732666322439909,
      "num_tokens": 1711348.0,
      "step": 325
    },
    {
      "entropy": 1.1931916671898215,
      "epoch": 0.2386228055224135,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00017828144100156754,
      "loss": 1.082593002319336,
      "mean_token_accuracy": 0.7456949570775032,
      "num_tokens": 1842011.0,
      "step": 350
    },
    {
      "entropy": 1.1265690931119026,
      "epoch": 0.2556672916311573,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.00017472698070228047,
      "loss": 1.0630721282958984,
      "mean_token_accuracy": 0.7553409574180842,
      "num_tokens": 1976056.0,
      "step": 375
    },
    {
      "entropy": 1.1145534914545714,
      "epoch": 0.27271177773990113,
      "grad_norm": 0.06787109375,
      "learning_rate": 0.00017094461868520622,
      "loss": 1.0225981903076171,
      "mean_token_accuracy": 0.7580388783663511,
      "num_tokens": 2109389.0,
      "step": 400
    },
    {
      "entropy": 1.25198206695728,
      "epoch": 0.28975626384864495,
      "grad_norm": 0.048828125,
      "learning_rate": 0.00016694589036623988,
      "loss": 1.194885482788086,
      "mean_token_accuracy": 0.7303700438886881,
      "num_tokens": 2240117.0,
      "step": 425
    },
    {
      "entropy": 1.1865128787327557,
      "epoch": 0.30680074995738876,
      "grad_norm": 0.0556640625,
      "learning_rate": 0.0001627429910334058,
      "loss": 1.118544158935547,
      "mean_token_accuracy": 0.7400260034948587,
      "num_tokens": 2364080.0,
      "step": 450
    },
    {
      "entropy": 1.274649427868426,
      "epoch": 0.3238452360661326,
      "grad_norm": 0.06591796875,
      "learning_rate": 0.00015834873865377077,
      "loss": 1.1928933715820313,
      "mean_token_accuracy": 0.7288886807858944,
      "num_tokens": 2497166.0,
      "step": 475
    },
    {
      "entropy": 1.1076703028334305,
      "epoch": 0.34088972217487645,
      "grad_norm": 0.0693359375,
      "learning_rate": 0.00015377653478131556,
      "loss": 1.0115528869628907,
      "mean_token_accuracy": 0.7560868422687054,
      "num_tokens": 2632559.0,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 1467,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1232059347325645e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}