{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1978021978021978,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.068535327911377,
      "learning_rate": 0.0,
      "loss": 1.0606,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.268423318862915,
      "learning_rate": 9.56e-05,
      "loss": 1.1983,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.045927882194519,
      "learning_rate": 0.0001912,
      "loss": 1.0628,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.028908371925354,
      "learning_rate": 0.0002868,
      "loss": 0.9173,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6483846306800842,
      "learning_rate": 0.0003824,
      "loss": 0.7759,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.7689517736434937,
      "learning_rate": 0.000478,
      "loss": 0.9309,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5526404976844788,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.96,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.4260517656803131,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8695,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.34387385845184326,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8246,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.33756059408187866,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.805,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.5314936637878418,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8365,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5229127407073975,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.838,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.48703446984291077,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.773,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.524895966053009,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7794,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5241197347640991,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7233,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.427020788192749,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7957,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5390051603317261,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.8339,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.31555530428886414,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7379,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3968167304992676,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.6715,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.37160152196884155,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7653,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40373656153678894,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7728,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.360177218914032,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7641,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5294693112373352,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7356,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.353331595659256,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7071,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.49404677748680115,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.7861,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3531878590583801,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7469,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4992196261882782,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7605,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.39656317234039307,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.772,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.41846686601638794,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7356,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.4010296165943146,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7164,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3715005166843904e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}