{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008123683074814043,
  "eval_steps": 400,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 8.097165991902834e-09,
      "loss": 3.5463,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.048582995951417e-08,
      "loss": 3.6591,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.097165991902834e-08,
      "loss": 3.6377,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.214574898785425e-07,
      "loss": 3.3634,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.6194331983805668e-07,
      "loss": 3.069,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.0242914979757083e-07,
      "loss": 2.6403,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.42914979757085e-07,
      "loss": 2.1059,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.8340080971659917e-07,
      "loss": 1.7116,
      "step": 35
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.2388663967611335e-07,
      "loss": 1.2154,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.6437246963562754e-07,
      "loss": 1.1809,
      "step": 45
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.0485829959514166e-07,
      "loss": 1.1222,
      "step": 50
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.4534412955465585e-07,
      "loss": 1.0215,
      "step": 55
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.8582995951417e-07,
      "loss": 0.9725,
      "step": 60
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.263157894736842e-07,
      "loss": 0.9506,
      "step": 65
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.668016194331983e-07,
      "loss": 0.8981,
      "step": 70
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.072874493927125e-07,
      "loss": 0.8955,
      "step": 75
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.477732793522267e-07,
      "loss": 0.8819,
      "step": 80
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.882591093117408e-07,
      "loss": 0.9384,
      "step": 85
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.287449392712551e-07,
      "loss": 0.9053,
      "step": 90
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.692307692307693e-07,
      "loss": 0.8439,
      "step": 95
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.097165991902833e-07,
      "loss": 0.8176,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.502024291497975e-07,
      "loss": 0.8403,
      "step": 105
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.906882591093117e-07,
      "loss": 0.8365,
      "step": 110
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.311740890688259e-07,
      "loss": 0.8354,
      "step": 115
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.7165991902834e-07,
      "loss": 0.7901,
      "step": 120
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0121457489878542e-06,
      "loss": 0.8182,
      "step": 125
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0526315789473683e-06,
      "loss": 0.8021,
      "step": 130
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0931174089068826e-06,
      "loss": 0.7999,
      "step": 135
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.1336032388663967e-06,
      "loss": 0.7896,
      "step": 140
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.1740890688259108e-06,
      "loss": 0.8225,
      "step": 145
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.214574898785425e-06,
      "loss": 0.8044,
      "step": 150
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2550607287449393e-06,
      "loss": 0.7872,
      "step": 155
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2955465587044534e-06,
      "loss": 0.826,
      "step": 160
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.3360323886639675e-06,
      "loss": 0.772,
      "step": 165
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.3765182186234816e-06,
      "loss": 0.7842,
      "step": 170
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4170040485829959e-06,
      "loss": 0.7833,
      "step": 175
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4574898785425101e-06,
      "loss": 0.7697,
      "step": 180
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4979757085020242e-06,
      "loss": 0.7515,
      "step": 185
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.5384615384615385e-06,
      "loss": 0.7914,
      "step": 190
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.5789473684210526e-06,
      "loss": 0.7729,
      "step": 195
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6194331983805667e-06,
      "loss": 0.7222,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 24619,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "total_flos": 27833727655936.0,
  "trial_name": null,
  "trial_params": null
}