{
  "best_metric": 1.9292813539505005,
  "best_model_checkpoint": "output/big-russian-boss/checkpoint-248",
  "epoch": 2.0,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00013665032034568096,
      "loss": 2.5025,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001350100903542216,
      "loss": 2.3418,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001323055957706572,
      "loss": 2.1866,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012858017786751834,
      "loss": 2.2697,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012389353887294475,
      "loss": 2.131,
      "step": 25
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011832078520391764,
      "loss": 2.0523,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011195122383741646,
      "loss": 2.0523,
      "step": 35
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00010488693110842961,
      "loss": 2.0586,
      "step": 40
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.724111687075534e-05,
      "loss": 2.1215,
      "step": 45
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.913631023597238e-05,
      "loss": 2.0016,
      "step": 50
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.070239596528567e-05,
      "loss": 2.0287,
      "step": 55
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.207453298233569e-05,
      "loss": 1.9277,
      "step": 60
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.339098836414812e-05,
      "loss": 1.9488,
      "step": 65
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.4790921521917906e-05,
      "loss": 1.9926,
      "step": 70
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.641215408156227e-05,
      "loss": 1.8875,
      "step": 75
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.838896120314628e-05,
      "loss": 1.9105,
      "step": 80
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.084991973471496e-05,
      "loss": 1.8968,
      "step": 85
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.3915847685255567e-05,
      "loss": 1.9608,
      "step": 90
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.7697868038067536e-05,
      "loss": 1.8985,
      "step": 95
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2295627933180862e-05,
      "loss": 1.9667,
      "step": 100
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.795701757575202e-06,
      "loss": 2.0107,
      "step": 105
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.270203734710291e-06,
      "loss": 1.7971,
      "step": 110
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7756322475164567e-06,
      "loss": 2.0397,
      "step": 115
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.519644153159924e-07,
      "loss": 1.9473,
      "step": 120
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.9632209539413452,
      "eval_runtime": 8.8591,
      "eval_samples_per_second": 20.544,
      "eval_steps_per_second": 2.596,
      "step": 124
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.2015434664866374e-08,
      "loss": 2.0051,
      "step": 125
    },
    {
      "epoch": 1.05,
      "learning_rate": 7.910729510915516e-07,
      "loss": 1.9063,
      "step": 130
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.6468123211622144e-06,
      "loss": 1.9292,
      "step": 135
    },
    {
      "epoch": 1.13,
      "learning_rate": 5.559494122852188e-06,
      "loss": 1.8741,
      "step": 140
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.482440748992502e-06,
      "loss": 1.9671,
      "step": 145
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.4352784446073873e-05,
      "loss": 1.9278,
      "step": 150
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.009247481060283e-05,
      "loss": 1.8776,
      "step": 155
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.660952959723034e-05,
      "loss": 1.8322,
      "step": 160
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.379950879364461e-05,
      "loss": 1.9671,
      "step": 165
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.154718833922634e-05,
      "loss": 1.8845,
      "step": 170
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.972840666504281e-05,
      "loss": 1.9002,
      "step": 175
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.8212054463186014e-05,
      "loss": 1.8912,
      "step": 180
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.686217579811531e-05,
      "loss": 1.9383,
      "step": 185
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.554014688833781e-05,
      "loss": 1.9313,
      "step": 190
    },
    {
      "epoch": 1.57,
      "learning_rate": 8.410689764204419e-05,
      "loss": 1.8199,
      "step": 195
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.242514034515462e-05,
      "loss": 1.8346,
      "step": 200
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001003615697856113,
      "loss": 1.8638,
      "step": 205
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00010778899955550273,
      "loss": 1.8885,
      "step": 210
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001145884002954007,
      "loss": 1.8695,
      "step": 215
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00012065080721672542,
      "loss": 1.8793,
      "step": 220
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00012587906633286313,
      "loss": 1.8785,
      "step": 225
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00013018939141455285,
      "loss": 1.8644,
      "step": 230
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00013351270671832803,
      "loss": 1.85,
      "step": 235
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013579575396992113,
      "loss": 1.8876,
      "step": 240
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001370019458625086,
      "loss": 1.8228,
      "step": 245
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9292813539505005,
      "eval_runtime": 8.8397,
      "eval_samples_per_second": 20.589,
      "eval_steps_per_second": 2.602,
      "step": 248
    }
  ],
  "max_steps": 248,
  "num_train_epochs": 2,
  "total_flos": 258156527616000.0,
  "trial_name": null,
  "trial_params": null
}