{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 5.3746,
      "step": 1
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 5.2868,
      "step": 2
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9458172417006347e-05,
      "loss": 4.0309,
      "step": 3
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.879473751206489e-05,
      "loss": 3.4518,
      "step": 4
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.789140509396394e-05,
      "loss": 2.8369,
      "step": 5
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 2.2651,
      "step": 6
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 2.1772,
      "step": 7
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 1.9791,
      "step": 8
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2454854871407993e-05,
      "loss": 1.8638,
      "step": 9
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 1.8646,
      "step": 10
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.174206545276678e-06,
      "loss": 1.6432,
      "step": 11
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.545145128592009e-06,
      "loss": 1.6805,
      "step": 12
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.983045753470308e-06,
      "loss": 1.6166,
      "step": 13
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.530518418775734e-06,
      "loss": 1.6272,
      "step": 14
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.2271842837425917e-06,
      "loss": 1.5397,
      "step": 15
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1085949060360654e-06,
      "loss": 1.6125,
      "step": 16
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 1.4847,
      "step": 17
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.418275829936537e-07,
      "loss": 1.5863,
      "step": 18
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3638696597277678e-07,
      "loss": 1.5869,
      "step": 19
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.5296,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 528928358400.0,
      "train_loss": 2.351900500059128,
      "train_runtime": 55.52,
      "train_samples_per_second": 2.864,
      "train_steps_per_second": 0.36
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 528928358400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}