{
  "best_metric": 3.1992340087890625,
  "best_model_checkpoint": "output/death-grips/checkpoint-66",
  "epoch": 2.0,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 0.00012909979873429716,
      "loss": 3.5364,
      "step": 5
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010671211798514472,
      "loss": 3.4591,
      "step": 10
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.532397582660788e-05,
      "loss": 3.5388,
      "step": 15
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.2347916539754844e-05,
      "loss": 3.3558,
      "step": 20
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.557148289931624e-05,
      "loss": 3.3211,
      "step": 25
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.3181297643383925e-06,
      "loss": 3.2263,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.4941582679748535,
      "eval_runtime": 0.5841,
      "eval_samples_per_second": 75.33,
      "eval_steps_per_second": 10.272,
      "step": 32
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.25174617767334,
      "eval_runtime": 0.4993,
      "eval_samples_per_second": 76.107,
      "eval_steps_per_second": 10.014,
      "step": 33
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.2396913677783124e-06,
      "loss": 3.1933,
      "step": 35
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.4676757700644785e-05,
      "loss": 3.1172,
      "step": 40
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.0102530108070535e-05,
      "loss": 3.4529,
      "step": 45
    },
    {
      "epoch": 1.52,
      "learning_rate": 7.186411942550872e-05,
      "loss": 3.2121,
      "step": 50
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00010290000000000001,
      "loss": 3.1379,
      "step": 55
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.000126309992352219,
      "loss": 3.1008,
      "step": 60
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001368893738885136,
      "loss": 3.1177,
      "step": 65
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.1992340087890625,
      "eval_runtime": 0.4988,
      "eval_samples_per_second": 76.185,
      "eval_steps_per_second": 10.024,
      "step": 66
    }
  ],
  "max_steps": 2013,
  "num_train_epochs": 61,
  "total_flos": 66890760192000.0,
  "trial_name": null,
  "trial_params": null
}