{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09115770282588878,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036463081130355514,
      "grad_norm": 0.8260515332221985,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.4916,
      "step": 1
    },
    {
      "epoch": 0.0036463081130355514,
      "eval_loss": 1.4711146354675293,
      "eval_runtime": 35.8851,
      "eval_samples_per_second": 6.437,
      "eval_steps_per_second": 3.233,
      "step": 1
    },
    {
      "epoch": 0.007292616226071103,
      "grad_norm": 0.9562111496925354,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.1876,
      "step": 2
    },
    {
      "epoch": 0.010938924339106655,
      "grad_norm": 1.0414786338806152,
      "learning_rate": 0.0001,
      "loss": 10.2457,
      "step": 3
    },
    {
      "epoch": 0.014585232452142206,
      "grad_norm": 1.100989818572998,
      "learning_rate": 9.99524110790929e-05,
      "loss": 9.8543,
      "step": 4
    },
    {
      "epoch": 0.018231540565177756,
      "grad_norm": 1.2875176668167114,
      "learning_rate": 9.980973490458728e-05,
      "loss": 10.6001,
      "step": 5
    },
    {
      "epoch": 0.02187784867821331,
      "grad_norm": 1.292757272720337,
      "learning_rate": 9.957224306869053e-05,
      "loss": 9.8068,
      "step": 6
    },
    {
      "epoch": 0.02552415679124886,
      "grad_norm": 1.4418549537658691,
      "learning_rate": 9.924038765061042e-05,
      "loss": 9.0652,
      "step": 7
    },
    {
      "epoch": 0.02917046490428441,
      "grad_norm": 1.5038715600967407,
      "learning_rate": 9.881480035599667e-05,
      "loss": 10.2297,
      "step": 8
    },
    {
      "epoch": 0.032816773017319965,
      "grad_norm": 1.5690864324569702,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.9497,
      "step": 9
    },
    {
      "epoch": 0.03646308113035551,
      "grad_norm": 1.6616734266281128,
      "learning_rate": 9.768584753741134e-05,
      "loss": 9.5513,
      "step": 10
    },
    {
      "epoch": 0.040109389243391066,
      "grad_norm": 1.8219513893127441,
      "learning_rate": 9.698463103929542e-05,
      "loss": 9.5726,
      "step": 11
    },
    {
      "epoch": 0.04375569735642662,
      "grad_norm": 1.9465745687484741,
      "learning_rate": 9.619397662556435e-05,
      "loss": 9.7049,
      "step": 12
    },
    {
      "epoch": 0.04740200546946217,
      "grad_norm": 1.967482328414917,
      "learning_rate": 9.53153893518325e-05,
      "loss": 9.4006,
      "step": 13
    },
    {
      "epoch": 0.05104831358249772,
      "grad_norm": 1.7798552513122559,
      "learning_rate": 9.435054165891109e-05,
      "loss": 9.8486,
      "step": 14
    },
    {
      "epoch": 0.054694621695533276,
      "grad_norm": 1.8983608484268188,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.0339,
      "step": 15
    },
    {
      "epoch": 0.05834092980856882,
      "grad_norm": 1.9173567295074463,
      "learning_rate": 9.21695722906443e-05,
      "loss": 9.1742,
      "step": 16
    },
    {
      "epoch": 0.06198723792160438,
      "grad_norm": 2.7075579166412354,
      "learning_rate": 9.09576022144496e-05,
      "loss": 9.7573,
      "step": 17
    },
    {
      "epoch": 0.06563354603463993,
      "grad_norm": 1.8774495124816895,
      "learning_rate": 8.966766701456177e-05,
      "loss": 9.7642,
      "step": 18
    },
    {
      "epoch": 0.06927985414767548,
      "grad_norm": 1.7866919040679932,
      "learning_rate": 8.83022221559489e-05,
      "loss": 9.0481,
      "step": 19
    },
    {
      "epoch": 0.07292616226071102,
      "grad_norm": 2.1817097663879395,
      "learning_rate": 8.68638668405062e-05,
      "loss": 10.5923,
      "step": 20
    },
    {
      "epoch": 0.07657247037374658,
      "grad_norm": 1.7108845710754395,
      "learning_rate": 8.535533905932738e-05,
      "loss": 9.1387,
      "step": 21
    },
    {
      "epoch": 0.08021877848678213,
      "grad_norm": 2.11926007270813,
      "learning_rate": 8.377951038078302e-05,
      "loss": 10.3624,
      "step": 22
    },
    {
      "epoch": 0.08386508659981769,
      "grad_norm": 2.068971872329712,
      "learning_rate": 8.213938048432697e-05,
      "loss": 8.0856,
      "step": 23
    },
    {
      "epoch": 0.08751139471285324,
      "grad_norm": 2.0737385749816895,
      "learning_rate": 8.043807145043604e-05,
      "loss": 8.4977,
      "step": 24
    },
    {
      "epoch": 0.09115770282588878,
      "grad_norm": 2.146387815475464,
      "learning_rate": 7.86788218175523e-05,
      "loss": 9.9969,
      "step": 25
    },
    {
      "epoch": 0.09115770282588878,
      "eval_loss": 1.2849068641662598,
      "eval_runtime": 35.9194,
      "eval_samples_per_second": 6.431,
      "eval_steps_per_second": 3.229,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.3785926656e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}