{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9993211133740665,
  "eval_steps": 500,
  "global_step": 184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05431093007467753,
      "grad_norm": 1.5025734901428223,
      "learning_rate": 0.00019904804439875633,
      "loss": 3.2617,
      "step": 10
    },
    {
      "epoch": 0.10862186014935506,
      "grad_norm": 1.5902663469314575,
      "learning_rate": 0.00019521176659107142,
      "loss": 1.7882,
      "step": 20
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 0.7277324795722961,
      "learning_rate": 0.000188545602565321,
      "loss": 1.1819,
      "step": 30
    },
    {
      "epoch": 0.2172437202987101,
      "grad_norm": 0.6814110279083252,
      "learning_rate": 0.00017924768419510904,
      "loss": 1.0805,
      "step": 40
    },
    {
      "epoch": 0.27155465037338766,
      "grad_norm": 0.6621173620223999,
      "learning_rate": 0.00016759436441447545,
      "loss": 1.0806,
      "step": 50
    },
    {
      "epoch": 0.3258655804480652,
      "grad_norm": 0.717393696308136,
      "learning_rate": 0.00015393200344991995,
      "loss": 1.0157,
      "step": 60
    },
    {
      "epoch": 0.3801765105227427,
      "grad_norm": 0.6353682279586792,
      "learning_rate": 0.0001386666742941419,
      "loss": 1.0388,
      "step": 70
    },
    {
      "epoch": 0.4344874405974202,
      "grad_norm": 0.7220941185951233,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.9547,
      "step": 80
    },
    {
      "epoch": 0.48879837067209775,
      "grad_norm": 0.7532466650009155,
      "learning_rate": 0.00010517613528842097,
      "loss": 1.0116,
      "step": 90
    },
    {
      "epoch": 0.5431093007467753,
      "grad_norm": 0.8198474645614624,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.9763,
      "step": 100
    },
    {
      "epoch": 0.5974202308214528,
      "grad_norm": 0.79359370470047,
      "learning_rate": 7.107478804634325e-05,
      "loss": 1.0034,
      "step": 110
    },
    {
      "epoch": 0.6517311608961304,
      "grad_norm": 1.1620718240737915,
      "learning_rate": 5.506295990328385e-05,
      "loss": 0.9125,
      "step": 120
    },
    {
      "epoch": 0.7060420909708078,
      "grad_norm": 1.5092897415161133,
      "learning_rate": 4.038675145307747e-05,
      "loss": 0.8748,
      "step": 130
    },
    {
      "epoch": 0.7603530210454854,
      "grad_norm": 1.0216153860092163,
      "learning_rate": 2.7482369285662378e-05,
      "loss": 0.9131,
      "step": 140
    },
    {
      "epoch": 0.814663951120163,
      "grad_norm": 1.5323857069015503,
      "learning_rate": 1.6733357731279377e-05,
      "loss": 0.8702,
      "step": 150
    },
    {
      "epoch": 0.8689748811948405,
      "grad_norm": 0.962648332118988,
      "learning_rate": 8.45919914746337e-06,
      "loss": 0.8396,
      "step": 160
    },
    {
      "epoch": 0.923285811269518,
      "grad_norm": 0.7791914939880371,
      "learning_rate": 2.905818257394799e-06,
      "loss": 0.8633,
      "step": 170
    },
    {
      "epoch": 0.9775967413441955,
      "grad_norm": 0.8390964865684509,
      "learning_rate": 2.382727698752474e-07,
      "loss": 0.8817,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 184,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1445464568266752.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}