{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01703940362087327,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004259850905218318,
      "grad_norm": 17.62246322631836,
      "learning_rate": 1e-05,
      "loss": 13.5679,
      "step": 1
    },
    {
      "epoch": 0.004259850905218318,
      "eval_loss": 0.9506049156188965,
      "eval_runtime": 50.1289,
      "eval_samples_per_second": 7.9,
      "eval_steps_per_second": 3.95,
      "step": 1
    },
    {
      "epoch": 0.008519701810436636,
      "grad_norm": 17.284486770629883,
      "learning_rate": 2e-05,
      "loss": 13.5645,
      "step": 2
    },
    {
      "epoch": 0.008519701810436636,
      "eval_loss": 0.947167694568634,
      "eval_runtime": 32.3344,
      "eval_samples_per_second": 12.247,
      "eval_steps_per_second": 6.124,
      "step": 2
    },
    {
      "epoch": 0.012779552715654952,
      "grad_norm": 19.740352630615234,
      "learning_rate": 3e-05,
      "loss": 16.2762,
      "step": 3
    },
    {
      "epoch": 0.01703940362087327,
      "grad_norm": 19.82746124267578,
      "learning_rate": 4e-05,
      "loss": 15.088,
      "step": 4
    },
    {
      "epoch": 0.01703940362087327,
      "eval_loss": 0.9377003908157349,
      "eval_runtime": 32.3171,
      "eval_samples_per_second": 12.254,
      "eval_steps_per_second": 6.127,
      "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": 5170375868547072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}