{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2506265664160401,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005012531328320802,
      "grad_norm": 20.089641571044922,
      "learning_rate": 1e-05,
      "loss": 20.1344,
      "step": 1
    },
    {
      "epoch": 0.005012531328320802,
      "eval_loss": 10.39857006072998,
      "eval_runtime": 28.5845,
      "eval_samples_per_second": 5.877,
      "eval_steps_per_second": 0.735,
      "step": 1
    },
    {
      "epoch": 0.010025062656641603,
      "grad_norm": 19.52311134338379,
      "learning_rate": 2e-05,
      "loss": 22.4254,
      "step": 2
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 14.5244140625,
      "learning_rate": 3e-05,
      "loss": 20.1972,
      "step": 3
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 21.34798812866211,
      "learning_rate": 4e-05,
      "loss": 22.7661,
      "step": 4
    },
    {
      "epoch": 0.02506265664160401,
      "grad_norm": 17.969993591308594,
      "learning_rate": 5e-05,
      "loss": 19.4781,
      "step": 5
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 19.54123306274414,
      "learning_rate": 6e-05,
      "loss": 21.2443,
      "step": 6
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 19.612939834594727,
      "learning_rate": 7e-05,
      "loss": 20.0462,
      "step": 7
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 23.63931655883789,
      "learning_rate": 8e-05,
      "loss": 17.3324,
      "step": 8
    },
    {
      "epoch": 0.045112781954887216,
      "grad_norm": 20.25324821472168,
      "learning_rate": 9e-05,
      "loss": 16.8131,
      "step": 9
    },
    {
      "epoch": 0.045112781954887216,
      "eval_loss": 8.083789825439453,
      "eval_runtime": 28.6671,
      "eval_samples_per_second": 5.86,
      "eval_steps_per_second": 0.733,
      "step": 9
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 22.54298210144043,
      "learning_rate": 0.0001,
      "loss": 15.429,
      "step": 10
    },
    {
      "epoch": 0.05513784461152882,
      "grad_norm": 27.352766036987305,
      "learning_rate": 9.99695413509548e-05,
      "loss": 17.369,
      "step": 11
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 24.816608428955078,
      "learning_rate": 9.987820251299122e-05,
      "loss": 12.8618,
      "step": 12
    },
    {
      "epoch": 0.06516290726817042,
      "grad_norm": 22.56251335144043,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.7916,
      "step": 13
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 24.081544876098633,
      "learning_rate": 9.951340343707852e-05,
      "loss": 8.7375,
      "step": 14
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 16.781705856323242,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.8874,
      "step": 15
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 21.11363983154297,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.2726,
      "step": 16
    },
    {
      "epoch": 0.08521303258145363,
      "grad_norm": 17.36714744567871,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.7834,
      "step": 17
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 12.790335655212402,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.3452,
      "step": 18
    },
    {
      "epoch": 0.09022556390977443,
      "eval_loss": 1.4436625242233276,
      "eval_runtime": 28.6933,
      "eval_samples_per_second": 5.855,
      "eval_steps_per_second": 0.732,
      "step": 18
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 12.467353820800781,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.57,
      "step": 19
    },
    {
      "epoch": 0.10025062656641603,
      "grad_norm": 12.546868324279785,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2274,
      "step": 20
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 15.894756317138672,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.0864,
      "step": 21
    },
    {
      "epoch": 0.11027568922305764,
      "grad_norm": 11.902620315551758,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.9417,
      "step": 22
    },
    {
      "epoch": 0.11528822055137844,
      "grad_norm": 7.588188648223877,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6944,
      "step": 23
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 7.501560688018799,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6366,
      "step": 24
    },
    {
      "epoch": 0.12531328320802004,
      "grad_norm": 4.7584309577941895,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5247,
      "step": 25
    },
    {
      "epoch": 0.13032581453634084,
      "grad_norm": 2.9300928115844727,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.4553,
      "step": 26
    },
    {
      "epoch": 0.13533834586466165,
      "grad_norm": 3.2299232482910156,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3305,
      "step": 27
    },
    {
      "epoch": 0.13533834586466165,
      "eval_loss": 0.7951204180717468,
      "eval_runtime": 28.6441,
      "eval_samples_per_second": 5.865,
      "eval_steps_per_second": 0.733,
      "step": 27
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 3.232689142227173,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2491,
      "step": 28
    },
    {
      "epoch": 0.14536340852130325,
      "grad_norm": 5.9495344161987305,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.6638,
      "step": 29
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 9.425905227661133,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6769,
      "step": 30
    },
    {
      "epoch": 0.15538847117794485,
      "grad_norm": 4.587433815002441,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.627,
      "step": 31
    },
    {
      "epoch": 0.16040100250626566,
      "grad_norm": 2.9762625694274902,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.2048,
      "step": 32
    },
    {
      "epoch": 0.16541353383458646,
      "grad_norm": 2.8089957237243652,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.3888,
      "step": 33
    },
    {
      "epoch": 0.17042606516290726,
      "grad_norm": 1.2890253067016602,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.34,
      "step": 34
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.3775737285614014,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4306,
      "step": 35
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 2.7069523334503174,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.4448,
      "step": 36
    },
    {
      "epoch": 0.18045112781954886,
      "eval_loss": 0.6974722743034363,
      "eval_runtime": 28.6505,
      "eval_samples_per_second": 5.864,
      "eval_steps_per_second": 0.733,
      "step": 36
    },
    {
      "epoch": 0.18546365914786966,
      "grad_norm": 2.9651219844818115,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4529,
      "step": 37
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 4.528919219970703,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.3969,
      "step": 38
    },
    {
      "epoch": 0.19548872180451127,
      "grad_norm": 2.145470142364502,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.4055,
      "step": 39
    },
    {
      "epoch": 0.20050125313283207,
      "grad_norm": 3.200515031814575,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4332,
      "step": 40
    },
    {
      "epoch": 0.20551378446115287,
      "grad_norm": 2.2597758769989014,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.4308,
      "step": 41
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.4869681596755981,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.3283,
      "step": 42
    },
    {
      "epoch": 0.21553884711779447,
      "grad_norm": 2.0091750621795654,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.3992,
      "step": 43
    },
    {
      "epoch": 0.22055137844611528,
      "grad_norm": 5.310917377471924,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.599,
      "step": 44
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 3.153137445449829,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.4812,
      "step": 45
    },
    {
      "epoch": 0.22556390977443608,
      "eval_loss": 0.7087278366088867,
      "eval_runtime": 28.9933,
      "eval_samples_per_second": 5.794,
      "eval_steps_per_second": 0.724,
      "step": 45
    },
    {
      "epoch": 0.23057644110275688,
      "grad_norm": 2.8991687297821045,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4612,
      "step": 46
    },
    {
      "epoch": 0.23558897243107768,
      "grad_norm": 2.4431586265563965,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4148,
      "step": 47
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 2.443445920944214,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.4315,
      "step": 48
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.969445824623108,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3969,
      "step": 49
    },
    {
      "epoch": 0.2506265664160401,
      "grad_norm": 2.1230924129486084,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4047,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 5.946469637318246e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}