{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00373948270489249,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00041549807832138777,
      "eval_loss": 1.8511379957199097,
      "eval_runtime": 172.841,
      "eval_samples_per_second": 23.455,
      "eval_steps_per_second": 2.933,
      "step": 1
    },
    {
      "epoch": 0.0012464942349641633,
      "grad_norm": 1.7350784540176392,
      "learning_rate": 1.5e-05,
      "loss": 1.8182,
      "step": 3
    },
    {
      "epoch": 0.0024929884699283265,
      "grad_norm": 1.777970314025879,
      "learning_rate": 3e-05,
      "loss": 1.8417,
      "step": 6
    },
    {
      "epoch": 0.00373948270489249,
      "grad_norm": 1.0666847229003906,
      "learning_rate": 4.5e-05,
      "loss": 1.6831,
      "step": 9
    },
    {
      "epoch": 0.00373948270489249,
      "eval_loss": 1.645044207572937,
      "eval_runtime": 173.3911,
      "eval_samples_per_second": 23.381,
      "eval_steps_per_second": 2.924,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3619073845886976.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}