{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.38888888888889,
  "eval_steps": 500,
  "global_step": 77,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 3e-05,
      "loss": 1.7262,
      "step": 3
    },
    {
      "epoch": 0.33,
      "learning_rate": 6e-05,
      "loss": 1.9459,
      "step": 6
    },
    {
      "epoch": 1.11,
      "learning_rate": 9e-05,
      "loss": 1.8076,
      "step": 9
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012,
      "loss": 1.4458,
      "step": 12
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6202,
      "step": 15
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018,
      "loss": 1.1957,
      "step": 18
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00019887640449438204,
      "loss": 1.4084,
      "step": 21
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0001955056179775281,
      "loss": 1.2387,
      "step": 24
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00019213483146067416,
      "loss": 1.0168,
      "step": 27
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00018876404494382024,
      "loss": 1.1336,
      "step": 30
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.0001853932584269663,
      "loss": 0.9109,
      "step": 33
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.00018202247191011236,
      "loss": 0.6177,
      "step": 36
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.00017865168539325842,
      "loss": 0.6269,
      "step": 39
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.0001752808988764045,
      "loss": 0.6662,
      "step": 42
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00017191011235955056,
      "loss": 0.5579,
      "step": 45
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00016853932584269662,
      "loss": 0.4686,
      "step": 48
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0001651685393258427,
      "loss": 0.3634,
      "step": 51
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00016179775280898877,
      "loss": 0.4219,
      "step": 54
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00015842696629213485,
      "loss": 0.3465,
      "step": 57
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.0001550561797752809,
      "loss": 0.2471,
      "step": 60
    },
    {
      "epoch": 8.39,
      "learning_rate": 0.00015168539325842697,
      "loss": 0.2689,
      "step": 63
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.00014831460674157306,
      "loss": 0.2027,
      "step": 66
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00014494382022471912,
      "loss": 0.2501,
      "step": 69
    },
    {
      "epoch": 10.11,
      "learning_rate": 0.00014157303370786517,
      "loss": 0.1825,
      "step": 72
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.00013820224719101123,
      "loss": 0.1805,
      "step": 75
    }
  ],
  "logging_steps": 3,
  "max_steps": 198,
  "num_train_epochs": 11,
  "save_steps": 500,
  "total_flos": 6259650928312320.0,
  "trial_name": null,
  "trial_params": null
}