{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05468215994531784,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010936431989063567,
      "grad_norm": 28.85504913330078,
      "learning_rate": 1e-05,
      "loss": 61.9596,
      "step": 1
    },
    {
      "epoch": 0.0010936431989063567,
      "eval_loss": NaN,
      "eval_runtime": 55.2379,
      "eval_samples_per_second": 27.898,
      "eval_steps_per_second": 13.958,
      "step": 1
    },
    {
      "epoch": 0.0021872863978127134,
      "grad_norm": 27.06040382385254,
      "learning_rate": 2e-05,
      "loss": 55.4659,
      "step": 2
    },
    {
      "epoch": 0.0032809295967190706,
      "grad_norm": 28.58708953857422,
      "learning_rate": 3e-05,
      "loss": 59.2286,
      "step": 3
    },
    {
      "epoch": 0.004374572795625427,
      "grad_norm": 33.11997604370117,
      "learning_rate": 4e-05,
      "loss": 56.7791,
      "step": 4
    },
    {
      "epoch": 0.005468215994531784,
      "grad_norm": 31.91828155517578,
      "learning_rate": 5e-05,
      "loss": 62.7061,
      "step": 5
    },
    {
      "epoch": 0.006561859193438141,
      "grad_norm": 35.19359588623047,
      "learning_rate": 6e-05,
      "loss": 59.0522,
      "step": 6
    },
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 31.660709381103516,
      "learning_rate": 7e-05,
      "loss": 58.0115,
      "step": 7
    },
    {
      "epoch": 0.008749145591250854,
      "grad_norm": 42.28495788574219,
      "learning_rate": 8e-05,
      "loss": 62.949,
      "step": 8
    },
    {
      "epoch": 0.00984278879015721,
      "grad_norm": 50.0612907409668,
      "learning_rate": 9e-05,
      "loss": 59.3017,
      "step": 9
    },
    {
      "epoch": 0.010936431989063569,
      "grad_norm": 47.29265594482422,
      "learning_rate": 0.0001,
      "loss": 56.7495,
      "step": 10
    },
    {
      "epoch": 0.012030075187969926,
      "grad_norm": 55.60464096069336,
      "learning_rate": 9.98458666866564e-05,
      "loss": 54.7309,
      "step": 11
    },
    {
      "epoch": 0.013123718386876282,
      "grad_norm": 52.25802993774414,
      "learning_rate": 9.938441702975689e-05,
      "loss": 46.0491,
      "step": 12
    },
    {
      "epoch": 0.014217361585782639,
      "grad_norm": 53.76634979248047,
      "learning_rate": 9.861849601988383e-05,
      "loss": 44.4741,
      "step": 13
    },
    {
      "epoch": 0.014217361585782639,
      "eval_loss": NaN,
      "eval_runtime": 29.7353,
      "eval_samples_per_second": 51.824,
      "eval_steps_per_second": 25.929,
      "step": 13
    },
    {
      "epoch": 0.015311004784688996,
      "grad_norm": 46.58119201660156,
      "learning_rate": 9.755282581475769e-05,
      "loss": 35.13,
      "step": 14
    },
    {
      "epoch": 0.016404647983595352,
      "grad_norm": 37.509063720703125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 31.4067,
      "step": 15
    },
    {
      "epoch": 0.017498291182501707,
      "grad_norm": 26.47342300415039,
      "learning_rate": 9.45503262094184e-05,
      "loss": 28.0434,
      "step": 16
    },
    {
      "epoch": 0.018591934381408066,
      "grad_norm": 33.73512649536133,
      "learning_rate": 9.263200821770461e-05,
      "loss": 28.5491,
      "step": 17
    },
    {
      "epoch": 0.01968557758031442,
      "grad_norm": 30.662729263305664,
      "learning_rate": 9.045084971874738e-05,
      "loss": 28.1228,
      "step": 18
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 29.663869857788086,
      "learning_rate": 8.802029828000156e-05,
      "loss": 26.2821,
      "step": 19
    },
    {
      "epoch": 0.021872863978127138,
      "grad_norm": 25.14940643310547,
      "learning_rate": 8.535533905932738e-05,
      "loss": 26.3426,
      "step": 20
    },
    {
      "epoch": 0.022966507177033493,
      "grad_norm": 25.627132415771484,
      "learning_rate": 8.247240241650918e-05,
      "loss": 23.1896,
      "step": 21
    },
    {
      "epoch": 0.02406015037593985,
      "grad_norm": 24.37764549255371,
      "learning_rate": 7.938926261462366e-05,
      "loss": 20.1499,
      "step": 22
    },
    {
      "epoch": 0.025153793574846206,
      "grad_norm": 21.951433181762695,
      "learning_rate": 7.612492823579745e-05,
      "loss": 18.7962,
      "step": 23
    },
    {
      "epoch": 0.026247436773752564,
      "grad_norm": 21.490671157836914,
      "learning_rate": 7.269952498697734e-05,
      "loss": 17.1975,
      "step": 24
    },
    {
      "epoch": 0.02734107997265892,
      "grad_norm": 27.6579532623291,
      "learning_rate": 6.91341716182545e-05,
      "loss": 19.7459,
      "step": 25
    },
    {
      "epoch": 0.028434723171565278,
      "grad_norm": 24.457176208496094,
      "learning_rate": 6.545084971874738e-05,
      "loss": 17.8861,
      "step": 26
    },
    {
      "epoch": 0.028434723171565278,
      "eval_loss": NaN,
      "eval_runtime": 29.8157,
      "eval_samples_per_second": 51.684,
      "eval_steps_per_second": 25.859,
      "step": 26
    },
    {
      "epoch": 0.029528366370471633,
      "grad_norm": 20.9813289642334,
      "learning_rate": 6.167226819279528e-05,
      "loss": 16.0026,
      "step": 27
    },
    {
      "epoch": 0.03062200956937799,
      "grad_norm": 25.871700286865234,
      "learning_rate": 5.782172325201155e-05,
      "loss": 13.681,
      "step": 28
    },
    {
      "epoch": 0.03171565276828435,
      "grad_norm": 22.013635635375977,
      "learning_rate": 5.392295478639225e-05,
      "loss": 12.6155,
      "step": 29
    },
    {
      "epoch": 0.032809295967190705,
      "grad_norm": 25.675172805786133,
      "learning_rate": 5e-05,
      "loss": 12.0468,
      "step": 30
    },
    {
      "epoch": 0.03390293916609706,
      "grad_norm": 26.090190887451172,
      "learning_rate": 4.607704521360776e-05,
      "loss": 10.7349,
      "step": 31
    },
    {
      "epoch": 0.034996582365003415,
      "grad_norm": 32.42118453979492,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 12.2017,
      "step": 32
    },
    {
      "epoch": 0.03609022556390978,
      "grad_norm": 22.70758819580078,
      "learning_rate": 3.832773180720475e-05,
      "loss": 10.3959,
      "step": 33
    },
    {
      "epoch": 0.03718386876281613,
      "grad_norm": 22.697429656982422,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.4618,
      "step": 34
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 22.032344818115234,
      "learning_rate": 3.086582838174551e-05,
      "loss": 12.4779,
      "step": 35
    },
    {
      "epoch": 0.03937115516062884,
      "grad_norm": 17.23045539855957,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 8.9037,
      "step": 36
    },
    {
      "epoch": 0.0404647983595352,
      "grad_norm": 18.696378707885742,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 10.774,
      "step": 37
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 19.836345672607422,
      "learning_rate": 2.061073738537635e-05,
      "loss": 9.4798,
      "step": 38
    },
    {
      "epoch": 0.04265208475734791,
      "grad_norm": 25.298463821411133,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 11.0674,
      "step": 39
    },
    {
      "epoch": 0.04265208475734791,
      "eval_loss": NaN,
      "eval_runtime": 29.7293,
      "eval_samples_per_second": 51.834,
      "eval_steps_per_second": 25.934,
      "step": 39
    },
    {
      "epoch": 0.043745727956254275,
      "grad_norm": 22.722843170166016,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.415,
      "step": 40
    },
    {
      "epoch": 0.04483937115516063,
      "grad_norm": 20.1871395111084,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 8.9222,
      "step": 41
    },
    {
      "epoch": 0.045933014354066985,
      "grad_norm": 19.610918045043945,
      "learning_rate": 9.549150281252633e-06,
      "loss": 7.8748,
      "step": 42
    },
    {
      "epoch": 0.04702665755297334,
      "grad_norm": 19.86541175842285,
      "learning_rate": 7.367991782295391e-06,
      "loss": 9.8181,
      "step": 43
    },
    {
      "epoch": 0.0481203007518797,
      "grad_norm": 15.583364486694336,
      "learning_rate": 5.449673790581611e-06,
      "loss": 8.7584,
      "step": 44
    },
    {
      "epoch": 0.04921394395078606,
      "grad_norm": 19.862598419189453,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 7.7709,
      "step": 45
    },
    {
      "epoch": 0.05030758714969241,
      "grad_norm": 22.887357711791992,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 9.1935,
      "step": 46
    },
    {
      "epoch": 0.05140123034859877,
      "grad_norm": 20.946556091308594,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 6.5477,
      "step": 47
    },
    {
      "epoch": 0.05249487354750513,
      "grad_norm": 19.912525177001953,
      "learning_rate": 6.15582970243117e-07,
      "loss": 7.5449,
      "step": 48
    },
    {
      "epoch": 0.053588516746411484,
      "grad_norm": 17.380966186523438,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 7.0048,
      "step": 49
    },
    {
      "epoch": 0.05468215994531784,
      "grad_norm": 26.645334243774414,
      "learning_rate": 0.0,
      "loss": 13.126,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.40962761654272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}