{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014311270125223614,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035778175313059034,
      "grad_norm": 0.5825825929641724,
      "learning_rate": 0.00019928443649373882,
      "loss": 1.248,
      "num_input_tokens_seen": 6646,
      "step": 10
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.5380188822746277,
      "learning_rate": 0.00019856887298747765,
      "loss": 0.5478,
      "num_input_tokens_seen": 13063,
      "step": 20
    },
    {
      "epoch": 0.01073345259391771,
      "grad_norm": 0.3872911036014557,
      "learning_rate": 0.00019785330948121648,
      "loss": 0.5135,
      "num_input_tokens_seen": 19512,
      "step": 30
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 0.4991438686847687,
      "learning_rate": 0.0001971377459749553,
      "loss": 0.5092,
      "num_input_tokens_seen": 26884,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 2795,
  "num_input_tokens_seen": 26884,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 604526222057472.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}