{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010689756540794784,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004275902616317913,
      "grad_norm": 17.016149520874023,
      "learning_rate": 5e-05,
      "loss": 14.1219,
      "step": 1
    },
    {
      "epoch": 0.0004275902616317913,
      "eval_loss": 0.6975424289703369,
      "eval_runtime": 4.7188,
      "eval_samples_per_second": 10.596,
      "eval_steps_per_second": 2.755,
      "step": 1
    },
    {
      "epoch": 0.0008551805232635826,
      "grad_norm": 24.373233795166016,
      "learning_rate": 0.0001,
      "loss": 19.0381,
      "step": 2
    },
    {
      "epoch": 0.001282770784895374,
      "grad_norm": 18.29240608215332,
      "learning_rate": 9.990365154573717e-05,
      "loss": 18.5439,
      "step": 3
    },
    {
      "epoch": 0.0017103610465271652,
      "grad_norm": 55.57586669921875,
      "learning_rate": 9.961501876182148e-05,
      "loss": 20.8671,
      "step": 4
    },
    {
      "epoch": 0.0021379513081589566,
      "grad_norm": 40.574012756347656,
      "learning_rate": 9.913533761814537e-05,
      "loss": 20.9025,
      "step": 5
    },
    {
      "epoch": 0.002565541569790748,
      "grad_norm": 19.65155601501465,
      "learning_rate": 9.846666218300807e-05,
      "loss": 19.7865,
      "step": 6
    },
    {
      "epoch": 0.0029931318314225393,
      "grad_norm": 17.976009368896484,
      "learning_rate": 9.761185582727977e-05,
      "loss": 20.1064,
      "step": 7
    },
    {
      "epoch": 0.0034207220930543305,
      "grad_norm": 17.989582061767578,
      "learning_rate": 9.657457896300791e-05,
      "loss": 20.7254,
      "step": 8
    },
    {
      "epoch": 0.003848312354686122,
      "grad_norm": 16.528972625732422,
      "learning_rate": 9.535927336897098e-05,
      "loss": 21.4587,
      "step": 9
    },
    {
      "epoch": 0.004275902616317913,
      "grad_norm": 16.301668167114258,
      "learning_rate": 9.397114317029975e-05,
      "loss": 20.2535,
      "step": 10
    },
    {
      "epoch": 0.004703492877949704,
      "grad_norm": 16.937824249267578,
      "learning_rate": 9.241613255361455e-05,
      "loss": 20.0616,
      "step": 11
    },
    {
      "epoch": 0.005131083139581496,
      "grad_norm": 20.719322204589844,
      "learning_rate": 9.070090031310558e-05,
      "loss": 21.4276,
      "step": 12
    },
    {
      "epoch": 0.0055586734012132875,
      "grad_norm": 14.288154602050781,
      "learning_rate": 8.883279133655399e-05,
      "loss": 15.3058,
      "step": 13
    },
    {
      "epoch": 0.005986263662845079,
      "grad_norm": 22.180660247802734,
      "learning_rate": 8.681980515339464e-05,
      "loss": 16.3832,
      "step": 14
    },
    {
      "epoch": 0.00641385392447687,
      "grad_norm": 15.857145309448242,
      "learning_rate": 8.467056167950311e-05,
      "loss": 17.4158,
      "step": 15
    },
    {
      "epoch": 0.006841444186108661,
      "grad_norm": 13.35568618774414,
      "learning_rate": 8.239426430539243e-05,
      "loss": 17.8514,
      "step": 16
    },
    {
      "epoch": 0.007269034447740453,
      "grad_norm": 13.346510887145996,
      "learning_rate": 8.000066048588211e-05,
      "loss": 16.1613,
      "step": 17
    },
    {
      "epoch": 0.007696624709372244,
      "grad_norm": 13.989509582519531,
      "learning_rate": 7.75e-05,
      "loss": 18.1431,
      "step": 18
    },
    {
      "epoch": 0.008124214971004035,
      "grad_norm": 13.145577430725098,
      "learning_rate": 7.490299105985507e-05,
      "loss": 18.4521,
      "step": 19
    },
    {
      "epoch": 0.008551805232635826,
      "grad_norm": 13.035820960998535,
      "learning_rate": 7.222075445642904e-05,
      "loss": 18.0997,
      "step": 20
    },
    {
      "epoch": 0.008979395494267618,
      "grad_norm": 13.4092378616333,
      "learning_rate": 6.946477593864228e-05,
      "loss": 18.836,
      "step": 21
    },
    {
      "epoch": 0.009406985755899409,
      "grad_norm": 14.309627532958984,
      "learning_rate": 6.664685702961344e-05,
      "loss": 19.516,
      "step": 22
    },
    {
      "epoch": 0.009834576017531202,
      "grad_norm": 13.839709281921387,
      "learning_rate": 6.377906449072578e-05,
      "loss": 19.228,
      "step": 23
    },
    {
      "epoch": 0.010262166279162993,
      "grad_norm": 15.516990661621094,
      "learning_rate": 6.087367864990233e-05,
      "loss": 19.8197,
      "step": 24
    },
    {
      "epoch": 0.010689756540794784,
      "grad_norm": 19.321626663208008,
      "learning_rate": 5.794314081535644e-05,
      "loss": 21.2602,
      "step": 25
    },
    {
      "epoch": 0.010689756540794784,
      "eval_loss": 0.5550210475921631,
      "eval_runtime": 4.7886,
      "eval_samples_per_second": 10.441,
      "eval_steps_per_second": 2.715,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 2.874098022487163e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}