{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05653710247349823,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014134275618374558,
      "grad_norm": 1064.3748779296875,
      "learning_rate": 1e-05,
      "loss": 183.7587,
      "step": 1
    },
    {
      "epoch": 0.014134275618374558,
      "eval_loss": 11.566619873046875,
      "eval_runtime": 52.6742,
      "eval_samples_per_second": 2.278,
      "eval_steps_per_second": 1.139,
      "step": 1
    },
    {
      "epoch": 0.028268551236749116,
      "grad_norm": 1140.489990234375,
      "learning_rate": 2e-05,
      "loss": 191.7578,
      "step": 2
    },
    {
      "epoch": 0.028268551236749116,
      "eval_loss": 10.923598289489746,
      "eval_runtime": 2.7444,
      "eval_samples_per_second": 43.725,
      "eval_steps_per_second": 21.862,
      "step": 2
    },
    {
      "epoch": 0.04240282685512368,
      "grad_norm": 1056.725830078125,
      "learning_rate": 3e-05,
      "loss": 175.362,
      "step": 3
    },
    {
      "epoch": 0.05653710247349823,
      "grad_norm": 1097.4027099609375,
      "learning_rate": 4e-05,
      "loss": 158.5189,
      "step": 4
    },
    {
      "epoch": 0.05653710247349823,
      "eval_loss": 8.754026412963867,
      "eval_runtime": 2.821,
      "eval_samples_per_second": 42.538,
      "eval_steps_per_second": 21.269,
      "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": 2804274878742528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}