{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 25,
  "global_step": 115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04381161007667032,
      "grad_norm": 0.6445760726928711,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.44997148513793944,
      "step": 5
    },
    {
      "epoch": 0.08762322015334063,
      "grad_norm": 0.2040737122297287,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.253184175491333,
      "step": 10
    },
    {
      "epoch": 0.13143483023001096,
      "grad_norm": 0.11370108276605606,
      "learning_rate": 9.990699835799469e-05,
      "loss": 0.1890493392944336,
      "step": 15
    },
    {
      "epoch": 0.17524644030668127,
      "grad_norm": 0.0560263991355896,
      "learning_rate": 9.886469909625625e-05,
      "loss": 0.16157859563827515,
      "step": 20
    },
    {
      "epoch": 0.21905805038335158,
      "grad_norm": 0.05086812004446983,
      "learning_rate": 9.668812408047679e-05,
      "loss": 0.14776169061660765,
      "step": 25
    },
    {
      "epoch": 0.21905805038335158,
      "eval_loss": 0.15636882185935974,
      "eval_runtime": 2.7445,
      "eval_samples_per_second": 13.481,
      "eval_steps_per_second": 3.644,
      "step": 25
    },
    {
      "epoch": 0.2628696604600219,
      "grad_norm": 0.4398188889026642,
      "learning_rate": 9.342779723309745e-05,
      "loss": 0.13989536762237548,
      "step": 30
    },
    {
      "epoch": 0.3066812705366922,
      "grad_norm": 0.03143283724784851,
      "learning_rate": 8.915939915302968e-05,
      "loss": 0.13840868473052978,
      "step": 35
    },
    {
      "epoch": 0.35049288061336253,
      "grad_norm": 0.030261408537626266,
      "learning_rate": 8.398201037367201e-05,
      "loss": 0.13194940090179444,
      "step": 40
    },
    {
      "epoch": 0.39430449069003287,
      "grad_norm": 0.027745651081204414,
      "learning_rate": 7.801581144806752e-05,
      "loss": 0.1258658289909363,
      "step": 45
    },
    {
      "epoch": 0.43811610076670315,
      "grad_norm": 0.028578005731105804,
      "learning_rate": 7.139929324815965e-05,
      "loss": 0.1307690382003784,
      "step": 50
    },
    {
      "epoch": 0.43811610076670315,
      "eval_loss": 0.13964250683784485,
      "eval_runtime": 2.7343,
      "eval_samples_per_second": 13.532,
      "eval_steps_per_second": 3.657,
      "step": 50
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.02204604260623455,
      "learning_rate": 6.42860422342998e-05,
      "loss": 0.11970643997192383,
      "step": 55
    },
    {
      "epoch": 0.5257393209200438,
      "grad_norm": 0.01909324899315834,
      "learning_rate": 5.6841175317195515e-05,
      "loss": 0.12441145181655884,
      "step": 60
    },
    {
      "epoch": 0.5695509309967142,
      "grad_norm": 0.02801951766014099,
      "learning_rate": 4.923750706835371e-05,
      "loss": 0.11856402158737182,
      "step": 65
    },
    {
      "epoch": 0.6133625410733844,
      "grad_norm": 0.02440124936401844,
      "learning_rate": 4.16515382479539e-05,
      "loss": 0.12577390670776367,
      "step": 70
    },
    {
      "epoch": 0.6571741511500547,
      "grad_norm": 0.03482368588447571,
      "learning_rate": 3.4259358766770766e-05,
      "loss": 0.12301583290100097,
      "step": 75
    },
    {
      "epoch": 0.6571741511500547,
      "eval_loss": 0.13510531187057495,
      "eval_runtime": 2.7462,
      "eval_samples_per_second": 13.473,
      "eval_steps_per_second": 3.641,
      "step": 75
    },
    {
      "epoch": 0.7009857612267251,
      "grad_norm": 0.03209087997674942,
      "learning_rate": 2.7232560184971434e-05,
      "loss": 0.11824085712432861,
      "step": 80
    },
    {
      "epoch": 0.7447973713033954,
      "grad_norm": 0.027280066162347794,
      "learning_rate": 2.0734252629237894e-05,
      "loss": 0.1161639928817749,
      "step": 85
    },
    {
      "epoch": 0.7886089813800657,
      "grad_norm": 0.024801179766654968,
      "learning_rate": 1.491527858584535e-05,
      "loss": 0.1195792555809021,
      "step": 90
    },
    {
      "epoch": 0.8324205914567361,
      "grad_norm": 0.023875568062067032,
      "learning_rate": 9.91071145732948e-06,
      "loss": 0.11831022500991821,
      "step": 95
    },
    {
      "epoch": 0.8762322015334063,
      "grad_norm": 0.02501710318028927,
      "learning_rate": 5.83672016027697e-06,
      "loss": 0.11868228912353515,
      "step": 100
    },
    {
      "epoch": 0.8762322015334063,
      "eval_loss": 0.1338396519422531,
      "eval_runtime": 2.7535,
      "eval_samples_per_second": 13.437,
      "eval_steps_per_second": 3.632,
      "step": 100
    },
    {
      "epoch": 0.9200438116100766,
      "grad_norm": 0.02370544523000717,
      "learning_rate": 2.787872545015069e-06,
      "loss": 0.1251981019973755,
      "step": 105
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.01968785747885704,
      "learning_rate": 8.349402317873789e-07,
      "loss": 0.11879189014434814,
      "step": 110
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.05922802537679672,
      "learning_rate": 2.3255818832423894e-08,
      "loss": 0.12383102178573609,
      "step": 115
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.1337558627128601,
      "eval_runtime": 2.7386,
      "eval_samples_per_second": 13.511,
      "eval_steps_per_second": 3.652,
      "step": 115
    }
  ],
  "logging_steps": 5,
  "max_steps": 115,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.099298143947981e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}