{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25103830179972314,
  "eval_steps": 500,
  "global_step": 17,
  "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
    }
  ],
  "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": 6.17292722381783e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}