{
  "best_metric": 1.7192894220352173,
  "best_model_checkpoint": "output/zemfira/checkpoint-100",
  "epoch": 2.0,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 3.357522982152468e-06,
      "loss": 1.9295,
      "step": 5
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3101434185878598e-05,
      "loss": 1.7553,
      "step": 10
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.8277931692736335e-05,
      "loss": 1.9311,
      "step": 15
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.74014341858786e-05,
      "loss": 1.854,
      "step": 20
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.859999999999999e-05,
      "loss": 1.8097,
      "step": 25
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.979856581412138e-05,
      "loss": 1.9139,
      "step": 30
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00010892206830726364,
      "loss": 1.8094,
      "step": 35
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001240985658141214,
      "loss": 1.6989,
      "step": 40
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00013384247701784754,
      "loss": 1.7624,
      "step": 45
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001372,
      "loss": 1.8189,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.7890528440475464,
      "eval_runtime": 3.3356,
      "eval_samples_per_second": 21.286,
      "eval_steps_per_second": 2.698,
      "step": 50
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00013384247701784754,
      "loss": 1.7241,
      "step": 55
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012409856581412136,
      "loss": 1.7957,
      "step": 60
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00010892206830726372,
      "loss": 1.7292,
      "step": 65
    },
    {
      "epoch": 1.4,
      "learning_rate": 8.979856581412141e-05,
      "loss": 1.6565,
      "step": 70
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 1.6323,
      "step": 75
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.7401434185878625e-05,
      "loss": 1.6913,
      "step": 80
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.827793169273636e-05,
      "loss": 1.6236,
      "step": 85
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.310143418587862e-05,
      "loss": 1.6434,
      "step": 90
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.3575229821524754e-06,
      "loss": 1.7407,
      "step": 95
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 1.7433,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.7192894220352173,
      "eval_runtime": 3.3307,
      "eval_samples_per_second": 21.317,
      "eval_steps_per_second": 2.702,
      "step": 100
    }
  ],
  "max_steps": 100,
  "num_train_epochs": 2,
  "total_flos": 103471644672000.0,
  "trial_name": null,
  "trial_params": null
}