{
  "best_metric": 2.3011960983276367,
  "best_model_checkpoint": "output/rammstein/checkpoint-96",
  "epoch": 2.0,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 3.64059311663575e-06,
      "loss": 2.9482,
      "step": 5
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.4175960856021253e-05,
      "loss": 2.7279,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.048788201485529e-05,
      "loss": 3.0408,
      "step": 15
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.084501350596709e-05,
      "loss": 2.8174,
      "step": 20
    },
    {
      "epoch": 0.52,
      "learning_rate": 7.308665466518777e-05,
      "loss": 2.9266,
      "step": 25
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.485208346024518e-05,
      "loss": 2.7754,
      "step": 30
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00011383112291586474,
      "loss": 2.4825,
      "step": 35
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012800934269961248,
      "loss": 2.6286,
      "step": 40
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001358818702356616,
      "loss": 2.681,
      "step": 45
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4657435417175293,
      "eval_runtime": 0.7344,
      "eval_samples_per_second": 81.697,
      "eval_steps_per_second": 10.893,
      "step": 48
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001366131174902434,
      "loss": 2.5211,
      "step": 50
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001301254700691424,
      "loss": 2.3708,
      "step": 55
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011710752518939717,
      "loss": 2.4006,
      "step": 60
    },
    {
      "epoch": 1.35,
      "learning_rate": 9.894100414902355e-05,
      "loss": 2.3993,
      "step": 65
    },
    {
      "epoch": 1.46,
      "learning_rate": 7.755409678629555e-05,
      "loss": 2.4798,
      "step": 70
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.5216803909693664e-05,
      "loss": 2.4973,
      "step": 75
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.4300000000000054e-05,
      "loss": 2.2237,
      "step": 80
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.7023789206942107e-05,
      "loss": 2.2823,
      "step": 85
    },
    {
      "epoch": 1.88,
      "learning_rate": 5.221864069725753e-06,
      "loss": 2.2183,
      "step": 90
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.4687786583180135e-07,
      "loss": 2.2238,
      "step": 95
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.3011960983276367,
      "eval_runtime": 0.7368,
      "eval_samples_per_second": 81.434,
      "eval_steps_per_second": 10.858,
      "step": 96
    }
  ],
  "max_steps": 96,
  "num_train_epochs": 2,
  "total_flos": 99552264192000.0,
  "trial_name": null,
  "trial_params": null
}