{
  "best_metric": 1.6946933269500732,
  "best_model_checkpoint": "output/5nizza/checkpoint-78",
  "epoch": 3.0,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 0.00012505669320030482,
      "loss": 2.3877,
      "step": 5
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.292589525111794e-05,
      "loss": 1.9965,
      "step": 10
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.218294542987356e-05,
      "loss": 2.0285,
      "step": 15
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.725216267546246e-05,
      "loss": 1.8764,
      "step": 20
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.001712368734975e-07,
      "loss": 1.9165,
      "step": 25
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.7974467277526855,
      "eval_runtime": 2.0269,
      "eval_samples_per_second": 22.201,
      "eval_steps_per_second": 2.96,
      "step": 26
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.857716640189785e-06,
      "loss": 1.8245,
      "step": 30
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.671999039779749e-05,
      "loss": 1.8956,
      "step": 35
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.686881626551516e-05,
      "loss": 1.7026,
      "step": 40
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00011409021435531856,
      "loss": 1.8252,
      "step": 45
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013520660867542716,
      "loss": 1.9085,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.7314008474349976,
      "eval_runtime": 2.0411,
      "eval_samples_per_second": 22.047,
      "eval_steps_per_second": 2.94,
      "step": 52
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00013274211424821946,
      "loss": 1.9922,
      "step": 55
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00010756924162575734,
      "loss": 1.7016,
      "step": 60
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 1.6856,
      "step": 65
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.9630758374242683e-05,
      "loss": 1.6801,
      "step": 70
    },
    {
      "epoch": 2.88,
      "learning_rate": 4.457885751780558e-06,
      "loss": 1.6953,
      "step": 75
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.6946933269500732,
      "eval_runtime": 2.0414,
      "eval_samples_per_second": 22.044,
      "eval_steps_per_second": 2.939,
      "step": 78
    }
  ],
  "max_steps": 78,
  "num_train_epochs": 3,
  "total_flos": 80739237888000.0,
  "trial_name": null,
  "trial_params": null
}