{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002497939200159868,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.497939200159868e-05,
      "eval_loss": 2.177466869354248,
      "eval_runtime": 418.6691,
      "eval_samples_per_second": 40.263,
      "eval_steps_per_second": 20.133,
      "step": 1
    },
    {
      "epoch": 7.493817600479604e-05,
      "grad_norm": 2.524216413497925,
      "learning_rate": 6e-05,
      "loss": 8.8213,
      "step": 3
    },
    {
      "epoch": 0.0001498763520095921,
      "grad_norm": 2.597292423248291,
      "learning_rate": 0.00012,
      "loss": 9.1385,
      "step": 6
    },
    {
      "epoch": 0.00019983513601278945,
      "eval_loss": 2.051755428314209,
      "eval_runtime": 415.2269,
      "eval_samples_per_second": 40.597,
      "eval_steps_per_second": 20.3,
      "step": 8
    },
    {
      "epoch": 0.00022481452801438812,
      "grad_norm": 2.427201747894287,
      "learning_rate": 0.00018,
      "loss": 8.4028,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 202207697829888.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}