{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00855431993156544,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001710863986313088,
      "grad_norm": 1.584230661392212,
      "learning_rate": 1e-05,
      "loss": 0.7921,
      "step": 1
    },
    {
      "epoch": 0.001710863986313088,
      "eval_loss": 0.9855340719223022,
      "eval_runtime": 68.2666,
      "eval_samples_per_second": 14.429,
      "eval_steps_per_second": 7.222,
      "step": 1
    },
    {
      "epoch": 0.003421727972626176,
      "grad_norm": 1.6465091705322266,
      "learning_rate": 2e-05,
      "loss": 0.8332,
      "step": 2
    },
    {
      "epoch": 0.0051325919589392645,
      "grad_norm": 1.3933875560760498,
      "learning_rate": 3e-05,
      "loss": 0.8667,
      "step": 3
    },
    {
      "epoch": 0.006843455945252352,
      "grad_norm": 1.1915502548217773,
      "learning_rate": 4e-05,
      "loss": 0.7275,
      "step": 4
    },
    {
      "epoch": 0.00855431993156544,
      "grad_norm": 1.950568437576294,
      "learning_rate": 5e-05,
      "loss": 0.8782,
      "step": 5
    },
    {
      "epoch": 0.00855431993156544,
      "eval_loss": 0.9573764204978943,
      "eval_runtime": 4.8483,
      "eval_samples_per_second": 203.163,
      "eval_steps_per_second": 101.685,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 100306002640896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}