{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07370215118153761,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036851075590768807,
      "eval_loss": NaN,
      "eval_runtime": 99.3489,
      "eval_samples_per_second": 46.01,
      "eval_steps_per_second": 23.01,
      "step": 1
    },
    {
      "epoch": 0.014740430236307523,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.014740430236307523,
      "eval_loss": NaN,
      "eval_runtime": 97.8099,
      "eval_samples_per_second": 46.734,
      "eval_steps_per_second": 23.372,
      "step": 40
    },
    {
      "epoch": 0.029480860472615045,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.029480860472615045,
      "eval_loss": NaN,
      "eval_runtime": 98.4188,
      "eval_samples_per_second": 46.444,
      "eval_steps_per_second": 23.227,
      "step": 80
    },
    {
      "epoch": 0.04422129070892257,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.04422129070892257,
      "eval_loss": NaN,
      "eval_runtime": 99.877,
      "eval_samples_per_second": 45.766,
      "eval_steps_per_second": 22.888,
      "step": 120
    },
    {
      "epoch": 0.05896172094523009,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.05896172094523009,
      "eval_loss": NaN,
      "eval_runtime": 98.8283,
      "eval_samples_per_second": 46.252,
      "eval_steps_per_second": 23.131,
      "step": 160
    },
    {
      "epoch": 0.07370215118153761,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.07370215118153761,
      "eval_loss": NaN,
      "eval_runtime": 98.4516,
      "eval_samples_per_second": 46.429,
      "eval_steps_per_second": 23.22,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9533761389330432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}