{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032444124008651765,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003604902667627974,
      "grad_norm": 3.4149161365348846e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0003604902667627974,
      "eval_loss": 11.5,
      "eval_runtime": 7.0048,
      "eval_samples_per_second": 166.887,
      "eval_steps_per_second": 83.515,
      "step": 1
    },
    {
      "epoch": 0.0007209805335255948,
      "grad_norm": 2.2081161660025828e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010814708002883922,
      "grad_norm": 3.4312306524952874e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0010814708002883922,
      "eval_loss": 11.5,
      "eval_runtime": 7.0011,
      "eval_samples_per_second": 166.974,
      "eval_steps_per_second": 83.558,
      "step": 3
    },
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 1.1769106095016468e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.001802451333813987,
      "grad_norm": 2.0270696040824987e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0021629416005767843,
      "grad_norm": 2.0300407413742505e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0021629416005767843,
      "eval_loss": 11.5,
      "eval_runtime": 7.1311,
      "eval_samples_per_second": 163.929,
      "eval_steps_per_second": 82.035,
      "step": 6
    },
    {
      "epoch": 0.0025234318673395817,
      "grad_norm": 2.3294644051929936e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 3.718418884091079e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0032444124008651765,
      "grad_norm": 1.9142440578434616e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0032444124008651765,
      "eval_loss": 11.5,
      "eval_runtime": 7.1544,
      "eval_samples_per_second": 163.397,
      "eval_steps_per_second": 81.768,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 338688933888.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}