{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5020766035994463,
  "eval_steps": 500,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014766958929395477,
      "grad_norm": 2.4889817237854004,
      "learning_rate": 0.0,
      "loss": 1.6905,
      "memory/device_mem_reserved(gib)": 21.22,
      "memory/max_mem_active(gib)": 20.26,
      "memory/max_mem_allocated(gib)": 20.26,
      "step": 1
    },
    {
      "epoch": 0.029533917858790955,
      "grad_norm": 2.847207546234131,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.6684,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 2
    },
    {
      "epoch": 0.044300876788186436,
      "grad_norm": 2.1346399784088135,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.6625,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 3
    },
    {
      "epoch": 0.05906783571758191,
      "grad_norm": 1.5967113971710205,
      "learning_rate": 1e-05,
      "loss": 1.5597,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 4
    },
    {
      "epoch": 0.07383479464697738,
      "grad_norm": 1.1592029333114624,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.61,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 5
    },
    {
      "epoch": 0.08860175357637287,
      "grad_norm": 0.7923451662063599,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.6703,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 6
    },
    {
      "epoch": 0.10336871250576835,
      "grad_norm": 0.8879733085632324,
      "learning_rate": 2e-05,
      "loss": 1.5672,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 7
    },
    {
      "epoch": 0.11813567143516382,
      "grad_norm": 0.8429373502731323,
      "learning_rate": 1.9986740898848306e-05,
      "loss": 1.5304,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 8
    },
    {
      "epoch": 0.1329026303645593,
      "grad_norm": 0.6310297846794128,
      "learning_rate": 1.9946998756145894e-05,
      "loss": 1.5365,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 9
    },
    {
      "epoch": 0.14766958929395477,
      "grad_norm": 0.45904460549354553,
      "learning_rate": 1.9880878960910772e-05,
      "loss": 1.5564,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 10
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 0.4647868573665619,
      "learning_rate": 1.978855685095358e-05,
      "loss": 1.5871,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 11
    },
    {
      "epoch": 0.17720350715274574,
      "grad_norm": 0.47522127628326416,
      "learning_rate": 1.9670277247913205e-05,
      "loss": 1.6906,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 12
    },
    {
      "epoch": 0.19197046608214122,
      "grad_norm": 0.4368882477283478,
      "learning_rate": 1.9526353808033827e-05,
      "loss": 1.5612,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 13
    },
    {
      "epoch": 0.2067374250115367,
      "grad_norm": 0.41860365867614746,
      "learning_rate": 1.9357168190404937e-05,
      "loss": 1.5157,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 14
    },
    {
      "epoch": 0.22150438394093216,
      "grad_norm": 0.35527029633522034,
      "learning_rate": 1.916316904487005e-05,
      "loss": 1.6507,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 15
    },
    {
      "epoch": 0.23627134287032764,
      "grad_norm": 0.3510073125362396,
      "learning_rate": 1.8944870822287957e-05,
      "loss": 1.4494,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 16
    },
    {
      "epoch": 0.25103830179972314,
      "grad_norm": 0.33353254199028015,
      "learning_rate": 1.8702852410301556e-05,
      "loss": 1.592,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 17
    },
    {
      "epoch": 0.2658052607291186,
      "grad_norm": 0.3858069181442261,
      "learning_rate": 1.8437755598231857e-05,
      "loss": 1.5903,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 18
    },
    {
      "epoch": 0.2805722196585141,
      "grad_norm": 0.4120069444179535,
      "learning_rate": 1.8150283375168112e-05,
      "loss": 1.5023,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 19
    },
    {
      "epoch": 0.29533917858790953,
      "grad_norm": 0.37689632177352905,
      "learning_rate": 1.7841198065767107e-05,
      "loss": 1.4686,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 20
    },
    {
      "epoch": 0.31010613751730504,
      "grad_norm": 0.32370489835739136,
      "learning_rate": 1.7511319308705198e-05,
      "loss": 1.6619,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 21
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 0.3516235053539276,
      "learning_rate": 1.7161521883143936e-05,
      "loss": 1.6317,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 22
    },
    {
      "epoch": 0.339640055376096,
      "grad_norm": 0.35210394859313965,
      "learning_rate": 1.679273338897293e-05,
      "loss": 1.4843,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 23
    },
    {
      "epoch": 0.3544070143054915,
      "grad_norm": 0.31570005416870117,
      "learning_rate": 1.6405931786981753e-05,
      "loss": 1.4993,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 24
    },
    {
      "epoch": 0.36917397323488693,
      "grad_norm": 0.3055304288864136,
      "learning_rate": 1.6002142805483686e-05,
      "loss": 1.5752,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 25
    },
    {
      "epoch": 0.38394093216428243,
      "grad_norm": 0.32708096504211426,
      "learning_rate": 1.5582437220268648e-05,
      "loss": 1.5435,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 26
    },
    {
      "epoch": 0.3987078910936779,
      "grad_norm": 0.3059172034263611,
      "learning_rate": 1.5147928015098309e-05,
      "loss": 1.5129,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 27
    },
    {
      "epoch": 0.4134748500230734,
      "grad_norm": 0.31772273778915405,
      "learning_rate": 1.4699767430273202e-05,
      "loss": 1.5566,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 28
    },
    {
      "epoch": 0.4282418089524688,
      "grad_norm": 0.318418949842453,
      "learning_rate": 1.423914390709861e-05,
      "loss": 1.3997,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 29
    },
    {
      "epoch": 0.44300876788186433,
      "grad_norm": 0.33671969175338745,
      "learning_rate": 1.3767278936351853e-05,
      "loss": 1.4731,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 30
    },
    {
      "epoch": 0.45777572681125983,
      "grad_norm": 0.32063713669776917,
      "learning_rate": 1.3285423819108349e-05,
      "loss": 1.5531,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 31
    },
    {
      "epoch": 0.4725426857406553,
      "grad_norm": 0.30657994747161865,
      "learning_rate": 1.2794856348516095e-05,
      "loss": 1.515,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 32
    },
    {
      "epoch": 0.4873096446700508,
      "grad_norm": 0.2942485213279724,
      "learning_rate": 1.2296877421317958e-05,
      "loss": 1.5364,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 33
    },
    {
      "epoch": 0.5020766035994463,
      "grad_norm": 0.3146020472049713,
      "learning_rate": 1.1792807588107358e-05,
      "loss": 1.555,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 34
    }
  ],
  "logging_steps": 1,
  "max_steps": 67,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.234585444763566e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}