{
  "best_metric": 2.059675931930542,
  "best_model_checkpoint": "output/kurt-cobain/checkpoint-63",
  "epoch": 1.0,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.00013507870183531476,
      "loss": 3.0032,
      "step": 5
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012884599993319768,
      "loss": 2.5844,
      "step": 10
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011888735840752609,
      "loss": 2.5435,
      "step": 15
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001058186737011911,
      "loss": 2.4834,
      "step": 20
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.044818420726556e-05,
      "loss": 2.4343,
      "step": 25
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.372648442002871e-05,
      "loss": 2.7558,
      "step": 30
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.668773501204858e-05,
      "loss": 2.5089,
      "step": 35
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.0385704725240065e-05,
      "loss": 2.4147,
      "step": 40
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.5828599592490882e-05,
      "loss": 2.123,
      "step": 45
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.3916710004507539e-05,
      "loss": 2.2562,
      "step": 50
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.38673186569003e-06,
      "loss": 2.4784,
      "step": 55
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.662053209561833e-07,
      "loss": 2.5457,
      "step": 60
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.059675931930542,
      "eval_runtime": 3.6409,
      "eval_samples_per_second": 22.522,
      "eval_steps_per_second": 3.021,
      "step": 63
    }
  ],
  "max_steps": 63,
  "num_train_epochs": 1,
  "total_flos": 64931069952000.0,
  "trial_name": null,
  "trial_params": null
}