{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008968609865470852,
      "grad_norm": 53.086448669433594,
      "learning_rate": 8.333333333333333e-08,
      "loss": 1.8832473754882812,
      "step": 1,
      "token_acc": 0.7904509283819628
    },
    {
      "epoch": 0.04484304932735426,
      "grad_norm": 50.739845275878906,
      "learning_rate": 4.1666666666666667e-07,
      "loss": 1.9631423950195312,
      "step": 5,
      "token_acc": 0.7811925400577883
    },
    {
      "epoch": 0.08968609865470852,
      "grad_norm": 57.77216339111328,
      "learning_rate": 4.982452740033792e-07,
      "loss": 1.917200469970703,
      "step": 10,
      "token_acc": 0.7826272088567171
    },
    {
      "epoch": 0.13452914798206278,
      "grad_norm": 45.45051956176758,
      "learning_rate": 4.911588954770896e-07,
      "loss": 1.6417181015014648,
      "step": 15,
      "token_acc": 0.7838668645325418
    },
    {
      "epoch": 0.17937219730941703,
      "grad_norm": 29.748525619506836,
      "learning_rate": 4.787864043107546e-07,
      "loss": 1.3956175804138184,
      "step": 20,
      "token_acc": 0.7983138780804151
    },
    {
      "epoch": 0.2242152466367713,
      "grad_norm": 18.36032485961914,
      "learning_rate": 4.613990008754565e-07,
      "loss": 1.0362204551696776,
      "step": 25,
      "token_acc": 0.823134328358209
    },
    {
      "epoch": 0.26905829596412556,
      "grad_norm": 12.634122848510742,
      "learning_rate": 4.39377810540405e-07,
      "loss": 0.9633771896362304,
      "step": 30,
      "token_acc": 0.8259674349756819
    },
    {
      "epoch": 0.31390134529147984,
      "grad_norm": 12.553196907043457,
      "learning_rate": 4.1320552954763037e-07,
      "loss": 0.9026593208312989,
      "step": 35,
      "token_acc": 0.8319409786264511
    },
    {
      "epoch": 0.35874439461883406,
      "grad_norm": 10.537694931030273,
      "learning_rate": 3.834558444911977e-07,
      "loss": 0.6936460494995117,
      "step": 40,
      "token_acc": 0.8529003311612007
    },
    {
      "epoch": 0.40358744394618834,
      "grad_norm": 8.851151466369629,
      "learning_rate": 3.5078085732199307e-07,
      "loss": 0.5532908916473389,
      "step": 45,
      "token_acc": 0.8564440663547427
    },
    {
      "epoch": 0.4484304932735426,
      "grad_norm": 8.047605514526367,
      "learning_rate": 3.158967915172669e-07,
      "loss": 0.4655792236328125,
      "step": 50,
      "token_acc": 0.8672489082969432
    },
    {
      "epoch": 0.49327354260089684,
      "grad_norm": 5.037430286407471,
      "learning_rate": 2.7956829273034146e-07,
      "loss": 0.4132298469543457,
      "step": 55,
      "token_acc": 0.8758526603001364
    },
    {
      "epoch": 0.5381165919282511,
      "grad_norm": 4.6973795890808105,
      "learning_rate": 2.4259166804436003e-07,
      "loss": 0.37035222053527833,
      "step": 60,
      "token_acc": 0.8859882791688866
    },
    {
      "epoch": 0.5829596412556054,
      "grad_norm": 4.15280818939209,
      "learning_rate": 2.0577743121935682e-07,
      "loss": 0.36975529193878176,
      "step": 65,
      "token_acc": 0.8918689706350048
    },
    {
      "epoch": 0.6278026905829597,
      "grad_norm": 3.9701106548309326,
      "learning_rate": 1.6993253653429062e-07,
      "loss": 0.341289758682251,
      "step": 70,
      "token_acc": 0.8945971765205393
    },
    {
      "epoch": 0.672645739910314,
      "grad_norm": 4.165452480316162,
      "learning_rate": 1.3584269065157172e-07,
      "loss": 0.3513831615447998,
      "step": 75,
      "token_acc": 0.8890205796789139
    },
    {
      "epoch": 0.7174887892376681,
      "grad_norm": 3.6079013347625732,
      "learning_rate": 1.0425513022138202e-07,
      "loss": 0.32526259422302245,
      "step": 80,
      "token_acc": 0.8964762301918265
    },
    {
      "epoch": 0.7623318385650224,
      "grad_norm": 4.192943096160889,
      "learning_rate": 7.586224273425081e-08,
      "loss": 0.3390298366546631,
      "step": 85,
      "token_acc": 0.8946101517530088
    },
    {
      "epoch": 0.8071748878923767,
      "grad_norm": 4.325422763824463,
      "learning_rate": 5.1286389646661654e-08,
      "loss": 0.32544262409210206,
      "step": 90,
      "token_acc": 0.8968119022316684
    },
    {
      "epoch": 0.852017937219731,
      "grad_norm": 4.034622669219971,
      "learning_rate": 3.106626445109081e-08,
      "loss": 0.3152462005615234,
      "step": 95,
      "token_acc": 0.9032049206863062
    },
    {
      "epoch": 0.8968609865470852,
      "grad_norm": 3.9629170894622803,
      "learning_rate": 1.5645084716469776e-08,
      "loss": 0.31574268341064454,
      "step": 100,
      "token_acc": 0.8994632535094963
    },
    {
      "epoch": 0.9417040358744395,
      "grad_norm": 3.703305959701538,
      "learning_rate": 5.360876925123992e-09,
      "loss": 0.3193276166915894,
      "step": 105,
      "token_acc": 0.9001921434671221
    },
    {
      "epoch": 0.9865470852017937,
      "grad_norm": 4.387911796569824,
      "learning_rate": 4.390670589196621e-10,
      "loss": 0.30874266624450686,
      "step": 110,
      "token_acc": 0.9005263157894737
    }
  ],
  "logging_steps": 5,
  "max_steps": 112,
  "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": 5.826709255104758e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}