{
  "best_metric": 2.1074936389923096,
  "best_model_checkpoint": "output/ot-rus/checkpoint-188",
  "epoch": 2.0,
  "global_step": 188,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.00013622380795859552,
      "loss": 2.8695,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00013332301465950465,
      "loss": 2.5088,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012858017786751834,
      "loss": 2.4316,
      "step": 15
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001221302806593135,
      "loss": 2.4985,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001141568897498326,
      "loss": 2.414,
      "step": 25
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00010488693110842961,
      "loss": 2.3927,
      "step": 30
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.458423155288552e-05,
      "loss": 2.3658,
      "step": 35
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.35420101301712e-05,
      "loss": 2.3367,
      "step": 40
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.207453298233569e-05,
      "loss": 2.4211,
      "step": 45
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.0508169203451974e-05,
      "loss": 2.3437,
      "step": 50
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.9172102241593944e-05,
      "loss": 2.336,
      "step": 55
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.838896120314628e-05,
      "loss": 2.1511,
      "step": 60
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.8465638696361884e-05,
      "loss": 2.4044,
      "step": 65
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.9684556542098295e-05,
      "loss": 2.1521,
      "step": 70
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2295627933180862e-05,
      "loss": 2.2615,
      "step": 75
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.50914480262796e-06,
      "loss": 2.1909,
      "step": 80
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.4897928291500582e-06,
      "loss": 2.1576,
      "step": 85
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.519644153159924e-07,
      "loss": 2.2327,
      "step": 90
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.1647870540618896,
      "eval_runtime": 5.4363,
      "eval_samples_per_second": 23.177,
      "eval_steps_per_second": 2.943,
      "step": 93
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.152095079421997,
      "eval_runtime": 5.3828,
      "eval_samples_per_second": 23.036,
      "eval_steps_per_second": 2.972,
      "step": 94
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.830872810453363e-08,
      "loss": 2.1472,
      "step": 95
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.3746270344901413e-06,
      "loss": 2.2033,
      "step": 100
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.58381008254605e-06,
      "loss": 2.1682,
      "step": 105
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.576451662754438e-06,
      "loss": 2.1479,
      "step": 110
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.6213459316852997e-05,
      "loss": 2.2949,
      "step": 115
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.4309929383066146e-05,
      "loss": 2.2226,
      "step": 120
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.3640298318194444e-05,
      "loss": 2.1933,
      "step": 125
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.3944626783346644e-05,
      "loss": 2.1917,
      "step": 130
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.493584142187686e-05,
      "loss": 2.2443,
      "step": 135
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.630773257727353e-05,
      "loss": 2.2132,
      "step": 140
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.774348513864122e-05,
      "loss": 2.2304,
      "step": 145
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.892450484875447e-05,
      "loss": 2.0878,
      "step": 150
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.953929417822461e-05,
      "loss": 2.2156,
      "step": 155
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00010929213048843373,
      "loss": 2.165,
      "step": 160
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00011791130471402592,
      "loss": 2.0622,
      "step": 165
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00012515669103944476,
      "loss": 2.2076,
      "step": 170
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00013082643668217578,
      "loss": 2.2435,
      "step": 175
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00013476258540873022,
      "loss": 2.1772,
      "step": 180
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013685547811507137,
      "loss": 2.1434,
      "step": 185
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.1074936389923096,
      "eval_runtime": 5.358,
      "eval_samples_per_second": 23.143,
      "eval_steps_per_second": 2.986,
      "step": 188
    }
  ],
  "max_steps": 188,
  "num_train_epochs": 2,
  "total_flos": 194793209856000.0,
  "trial_name": null,
  "trial_params": null
}