{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015980331899200985,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006146281499692685,
      "eval_loss": 32.18796920776367,
      "eval_runtime": 9.9698,
      "eval_samples_per_second": 68.708,
      "eval_steps_per_second": 34.404,
      "step": 1
    },
    {
      "epoch": 0.003073140749846343,
      "grad_norm": 1042.032958984375,
      "learning_rate": 5e-05,
      "loss": 151.3782,
      "step": 5
    },
    {
      "epoch": 0.006146281499692686,
      "grad_norm": 1655.912109375,
      "learning_rate": 0.0001,
      "loss": 90.5781,
      "step": 10
    },
    {
      "epoch": 0.006146281499692686,
      "eval_loss": 32.177650451660156,
      "eval_runtime": 7.9223,
      "eval_samples_per_second": 86.465,
      "eval_steps_per_second": 43.296,
      "step": 10
    },
    {
      "epoch": 0.00921942224953903,
      "grad_norm": 1991.4852294921875,
      "learning_rate": 9.619397662556435e-05,
      "loss": 130.4381,
      "step": 15
    },
    {
      "epoch": 0.012292562999385371,
      "grad_norm": 642.9652099609375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 99.3049,
      "step": 20
    },
    {
      "epoch": 0.012292562999385371,
      "eval_loss": 32.11423873901367,
      "eval_runtime": 7.9533,
      "eval_samples_per_second": 86.128,
      "eval_steps_per_second": 43.127,
      "step": 20
    },
    {
      "epoch": 0.015365703749231715,
      "grad_norm": 820.176513671875,
      "learning_rate": 6.91341716182545e-05,
      "loss": 36.4627,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 47345521655808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}