{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9263157894736844,
  "eval_steps": 100.0,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.09988608956336975,
      "learning_rate": 5e-05,
      "loss": 2.3771400451660156,
      "step": 1,
      "token_acc": 0.4664310954063604
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.04726523533463478,
      "learning_rate": 9.770696282000244e-05,
      "loss": 2.1574275493621826,
      "step": 5,
      "token_acc": 0.519051651143099
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.03580109775066376,
      "learning_rate": 8.444834595378434e-05,
      "loss": 1.7195571899414062,
      "step": 10,
      "token_acc": 0.5904558404558404
    },
    {
      "epoch": 1.3368421052631578,
      "grad_norm": 0.03144058212637901,
      "learning_rate": 6.253262661293604e-05,
      "loss": 1.85762939453125,
      "step": 15,
      "token_acc": 0.6245161290322581
    },
    {
      "epoch": 1.7578947368421054,
      "grad_norm": 0.0300274845212698,
      "learning_rate": 3.746737338706397e-05,
      "loss": 1.3842062950134277,
      "step": 20,
      "token_acc": 0.653372008701958
    },
    {
      "epoch": 2.2526315789473683,
      "grad_norm": 0.02691994234919548,
      "learning_rate": 1.555165404621567e-05,
      "loss": 1.6822933197021483,
      "step": 25,
      "token_acc": 0.6409290646578782
    },
    {
      "epoch": 2.6736842105263157,
      "grad_norm": 0.030764643102884293,
      "learning_rate": 2.2930371799975594e-06,
      "loss": 1.3119495391845704,
      "step": 30,
      "token_acc": 0.6437125748502994
    }
  ],
  "logging_steps": 5,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1367359130171867e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}