{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1e-05,
      "loss": 1.3352,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 1.3294,
      "step": 2
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.99658449300667e-05,
      "loss": 1.2557,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 1.186,
      "step": 4
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9694002659393306e-05,
      "loss": 1.2848,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9458172417006347e-05,
      "loss": 1.2104,
      "step": 6
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9157733266550577e-05,
      "loss": 1.1841,
      "step": 7
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.879473751206489e-05,
      "loss": 1.1415,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 1.123,
      "step": 9
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.789140509396394e-05,
      "loss": 1.1093,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.735723910673132e-05,
      "loss": 1.1141,
      "step": 11
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 1.1025,
      "step": 12
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.6142127126896682e-05,
      "loss": 1.0939,
      "step": 13
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 1.0804,
      "step": 14
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.4759473930370738e-05,
      "loss": 1.0524,
      "step": 15
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 1.0686,
      "step": 16
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.3246994692046837e-05,
      "loss": 1.0337,
      "step": 17
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2454854871407993e-05,
      "loss": 1.0374,
      "step": 18
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.164594590280734e-05,
      "loss": 1.0419,
      "step": 19
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 1.05,
      "step": 20
    },
    {
      "epoch": 0.53,
      "learning_rate": 1e-05,
      "loss": 1.0303,
      "step": 21
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.174206545276678e-06,
      "loss": 1.0276,
      "step": 22
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.35405409719266e-06,
      "loss": 1.0197,
      "step": 23
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.545145128592009e-06,
      "loss": 1.0207,
      "step": 24
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.7530053079531664e-06,
      "loss": 1.0217,
      "step": 25
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.983045753470308e-06,
      "loss": 1.0422,
      "step": 26
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.240526069629265e-06,
      "loss": 1.0093,
      "step": 27
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.530518418775734e-06,
      "loss": 1.0293,
      "step": 28
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.857872873103322e-06,
      "loss": 1.02,
      "step": 29
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.2271842837425917e-06,
      "loss": 1.0099,
      "step": 30
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.642760893268684e-06,
      "loss": 1.0175,
      "step": 31
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1085949060360654e-06,
      "loss": 1.0033,
      "step": 32
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6283352173747148e-06,
      "loss": 1.0104,
      "step": 33
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 1.0234,
      "step": 34
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.42266733449425e-07,
      "loss": 1.0084,
      "step": 35
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.418275829936537e-07,
      "loss": 1.0042,
      "step": 36
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.059973406066963e-07,
      "loss": 1.0211,
      "step": 37
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3638696597277678e-07,
      "loss": 0.9801,
      "step": 38
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.4155069933301535e-08,
      "loss": 1.0242,
      "step": 39
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.8541,
      "step": 40
    },
    {
      "epoch": 1.0,
      "step": 40,
      "total_flos": 20207034040320.0,
      "train_loss": 1.0752930834889411,
      "train_runtime": 575.3001,
      "train_samples_per_second": 8.691,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 20207034040320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}