{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0012910305651486298,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 9.0945,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 9.0429,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 9.2676,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.000000000000001e-07,
      "loss": 9.3776,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-07,
      "loss": 8.9559,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 9.6033,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 9.5622,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 9.1352,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 9.4911,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.8e-06,
      "loss": 9.2504,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 13280654057472.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}