{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005553145336225597,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013882863340563992,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 4002.9109,
      "step": 1
    },
    {
      "epoch": 0.00013882863340563992,
      "eval_loss": NaN,
      "eval_runtime": 182.8563,
      "eval_samples_per_second": 66.347,
      "eval_steps_per_second": 33.174,
      "step": 1
    },
    {
      "epoch": 0.00027765726681127983,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00027765726681127983,
      "eval_loss": NaN,
      "eval_runtime": 125.6618,
      "eval_samples_per_second": 96.545,
      "eval_steps_per_second": 48.272,
      "step": 2
    },
    {
      "epoch": 0.00041648590021691975,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005553145336225597,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0005553145336225597,
      "eval_loss": NaN,
      "eval_runtime": 127.2949,
      "eval_samples_per_second": 95.306,
      "eval_steps_per_second": 47.653,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 222595409510400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}