{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 4850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002061855670103093,
      "grad_norm": 0.5331169366836548,
      "learning_rate": 2.061855670103093e-07,
      "loss": 0.5976,
      "step": 1
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.42875760793685913,
      "learning_rate": 2.0618556701030927e-05,
      "loss": 0.5552,
      "step": 100
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.44043704867362976,
      "learning_rate": 4.1237113402061855e-05,
      "loss": 0.5911,
      "step": 200
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.39276885986328125,
      "learning_rate": 6.185567010309279e-05,
      "loss": 0.5676,
      "step": 300
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.3910420835018158,
      "learning_rate": 8.247422680412371e-05,
      "loss": 0.5516,
      "step": 400
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.3953075408935547,
      "learning_rate": 0.00010309278350515463,
      "loss": 0.5785,
      "step": 500
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.38498565554618835,
      "learning_rate": 0.00012371134020618558,
      "loss": 0.6043,
      "step": 600
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.36671698093414307,
      "learning_rate": 0.0001443298969072165,
      "loss": 0.579,
      "step": 700
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.3693369925022125,
      "learning_rate": 0.00016494845360824742,
      "loss": 0.5443,
      "step": 800
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.3997150659561157,
      "learning_rate": 0.00018556701030927837,
      "loss": 0.5798,
      "step": 900
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.4547862708568573,
      "learning_rate": 0.0001999704996306308,
      "loss": 0.6046,
      "step": 1000
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.34885653853416443,
      "learning_rate": 0.00019944653267951504,
      "loss": 0.5694,
      "step": 1100
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.5895730257034302,
      "learning_rate": 0.00019827095435098925,
      "loss": 0.5858,
      "step": 1200
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.3080294132232666,
      "learning_rate": 0.0001964514674798659,
      "loss": 0.592,
      "step": 1300
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.2972188889980316,
      "learning_rate": 0.00019399999403380266,
      "loss": 0.5726,
      "step": 1400
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.28474223613739014,
      "learning_rate": 0.00019093259699605125,
      "loss": 0.5729,
      "step": 1500
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.39205971360206604,
      "learning_rate": 0.00018726937511470246,
      "loss": 0.5815,
      "step": 1600
    },
    {
      "epoch": 0.35051546391752575,
      "grad_norm": 0.43681225180625916,
      "learning_rate": 0.0001830343312080704,
      "loss": 0.5555,
      "step": 1700
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.3381674885749817,
      "learning_rate": 0.0001782552148891283,
      "loss": 0.5404,
      "step": 1800
    },
    {
      "epoch": 0.3917525773195876,
      "grad_norm": 0.3750503361225128,
      "learning_rate": 0.00017296334073952605,
      "loss": 0.5795,
      "step": 1900
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.45220425724983215,
      "learning_rate": 0.00016719338312458124,
      "loss": 0.5602,
      "step": 2000
    },
    {
      "epoch": 0.4329896907216495,
      "grad_norm": 0.43047139048576355,
      "learning_rate": 0.00016098314899369446,
      "loss": 0.5571,
      "step": 2100
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.7484344840049744,
      "learning_rate": 0.00015437333015488587,
      "loss": 0.5526,
      "step": 2200
    },
    {
      "epoch": 0.4742268041237113,
      "grad_norm": 0.39876288175582886,
      "learning_rate": 0.00014747851305720256,
      "loss": 0.5495,
      "step": 2300
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.2668340802192688,
      "learning_rate": 0.00014020466278830452,
      "loss": 0.5603,
      "step": 2400
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 0.2944701611995697,
      "learning_rate": 0.0001326673763292055,
      "loss": 0.5728,
      "step": 2500
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.5645434856414795,
      "learning_rate": 0.0001249160408378004,
      "loss": 0.552,
      "step": 2600
    },
    {
      "epoch": 0.5567010309278351,
      "grad_norm": 0.3050793707370758,
      "learning_rate": 0.0001170014460023793,
      "loss": 0.5735,
      "step": 2700
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.4726704955101013,
      "learning_rate": 0.00010897545124833783,
      "loss": 0.5672,
      "step": 2800
    },
    {
      "epoch": 0.5979381443298969,
      "grad_norm": 0.5890568494796753,
      "learning_rate": 0.00010089064593556474,
      "loss": 0.5377,
      "step": 2900
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.33398109674453735,
      "learning_rate": 9.280000477302173e-05,
      "loss": 0.5624,
      "step": 3000
    },
    {
      "epoch": 0.6391752577319587,
      "grad_norm": 0.43066734075546265,
      "learning_rate": 8.48365683413172e-05,
      "loss": 0.5712,
      "step": 3100
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 0.41674667596817017,
      "learning_rate": 7.689172737117389e-05,
      "loss": 0.5458,
      "step": 3200
    },
    {
      "epoch": 0.6804123711340206,
      "grad_norm": 0.4635225832462311,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.5449,
      "step": 3300
    },
    {
      "epoch": 0.7010309278350515,
      "grad_norm": 1.0104267597198486,
      "learning_rate": 6.15073534018669e-05,
      "loss": 0.5475,
      "step": 3400
    },
    {
      "epoch": 0.7216494845360825,
      "grad_norm": 0.24354267120361328,
      "learning_rate": 5.416862465241033e-05,
      "loss": 0.516,
      "step": 3500
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": 0.500800609588623,
      "learning_rate": 4.7130200446653475e-05,
      "loss": 0.5138,
      "step": 3600
    },
    {
      "epoch": 0.7628865979381443,
      "grad_norm": 0.26592689752578735,
      "learning_rate": 4.043819920791322e-05,
      "loss": 0.5543,
      "step": 3700
    },
    {
      "epoch": 0.7835051546391752,
      "grad_norm": 0.549505352973938,
      "learning_rate": 3.4136469464914575e-05,
      "loss": 0.5576,
      "step": 3800
    },
    {
      "epoch": 0.8041237113402062,
      "grad_norm": 0.38464662432670593,
      "learning_rate": 2.8266302539609745e-05,
      "loss": 0.5578,
      "step": 3900
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 0.5664867758750916,
      "learning_rate": 2.2866161990785228e-05,
      "loss": 0.5433,
      "step": 4000
    },
    {
      "epoch": 0.845360824742268,
      "grad_norm": 0.3998001217842102,
      "learning_rate": 1.7971431586244815e-05,
      "loss": 0.557,
      "step": 4100
    },
    {
      "epoch": 0.865979381443299,
      "grad_norm": 0.3722541332244873,
      "learning_rate": 1.3614183454950824e-05,
      "loss": 0.5021,
      "step": 4200
    },
    {
      "epoch": 0.8865979381443299,
      "grad_norm": 0.7536567449569702,
      "learning_rate": 9.822967938278171e-06,
      "loss": 0.547,
      "step": 4300
    },
    {
      "epoch": 0.9072164948453608,
      "grad_norm": 0.18647919595241547,
      "learning_rate": 6.622626517355557e-06,
      "loss": 0.5207,
      "step": 4400
    },
    {
      "epoch": 0.9278350515463918,
      "grad_norm": 0.4656095504760742,
      "learning_rate": 4.034129042265066e-06,
      "loss": 0.5498,
      "step": 4500
    },
    {
      "epoch": 0.9484536082474226,
      "grad_norm": 0.544163167476654,
      "learning_rate": 2.074436329635687e-06,
      "loss": 0.5319,
      "step": 4600
    },
    {
      "epoch": 0.9690721649484536,
      "grad_norm": 0.3850492537021637,
      "learning_rate": 7.563890289437825e-07,
      "loss": 0.5569,
      "step": 4700
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 0.5212803483009338,
      "learning_rate": 8.862348571043733e-08,
      "loss": 0.5224,
      "step": 4800
    }
  ],
  "logging_steps": 100,
  "max_steps": 4850,
  "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": 2.346791597607813e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}