{
  "best_metric": 1.8946211338043213,
  "best_model_checkpoint": "output/big-baby-tape/checkpoint-126",
  "epoch": 1.0,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0001366676095727718,
      "loss": 2.7486,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013507870183531476,
      "loss": 2.6211,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001324579391569924,
      "loss": 2.2625,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012884599993319768,
      "loss": 2.3757,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012429894719210777,
      "loss": 2.3396,
      "step": 25
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011888735840752609,
      "loss": 2.2627,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011269523002449659,
      "loss": 2.226,
      "step": 35
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001058186737011911,
      "loss": 2.1916,
      "step": 40
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.836442450346448e-05,
      "loss": 2.2987,
      "step": 45
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.044818420726556e-05,
      "loss": 2.0771,
      "step": 50
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.219282542347867e-05,
      "loss": 2.1651,
      "step": 55
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.372648442002871e-05,
      "loss": 2.1705,
      "step": 60
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.518057224367617e-05,
      "loss": 2.0684,
      "step": 65
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.668773501204858e-05,
      "loss": 2.025,
      "step": 70
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.837979503541197e-05,
      "loss": 2.1328,
      "step": 75
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.0385704725240065e-05,
      "loss": 2.076,
      "step": 80
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.282954504816644e-05,
      "loss": 2.0965,
      "step": 85
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.5828599592490882e-05,
      "loss": 2.157,
      "step": 90
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.9491534140783314e-05,
      "loss": 2.0402,
      "step": 95
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.3916710004507539e-05,
      "loss": 2.0006,
      "step": 100
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.190657300387505e-06,
      "loss": 1.993,
      "step": 105
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.38673186569003e-06,
      "loss": 2.0394,
      "step": 110
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.5639766592291746e-06,
      "loss": 1.9176,
      "step": 115
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.662053209561833e-07,
      "loss": 2.0078,
      "step": 120
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.132211474400556e-08,
      "loss": 2.0426,
      "step": 125
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.8946211338043213,
      "eval_runtime": 10.3833,
      "eval_samples_per_second": 22.44,
      "eval_steps_per_second": 2.889,
      "step": 126
    }
  ],
  "max_steps": 126,
  "num_train_epochs": 1,
  "total_flos": 130776662016000.0,
  "trial_name": null,
  "trial_params": null
}