{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021855534914217024,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004371106982843405,
      "grad_norm": 1.0720200538635254,
      "learning_rate": 2e-05,
      "loss": 12.2248,
      "step": 1
    },
    {
      "epoch": 0.0004371106982843405,
      "eval_loss": 3.090006113052368,
      "eval_runtime": 63.2698,
      "eval_samples_per_second": 15.236,
      "eval_steps_per_second": 7.618,
      "step": 1
    },
    {
      "epoch": 0.000874221396568681,
      "grad_norm": 1.0658981800079346,
      "learning_rate": 4e-05,
      "loss": 12.6966,
      "step": 2
    },
    {
      "epoch": 0.0013113320948530216,
      "grad_norm": 1.0887017250061035,
      "learning_rate": 6e-05,
      "loss": 11.9003,
      "step": 3
    },
    {
      "epoch": 0.001748442793137362,
      "grad_norm": 1.080330729484558,
      "learning_rate": 8e-05,
      "loss": 12.5687,
      "step": 4
    },
    {
      "epoch": 0.0021855534914217026,
      "grad_norm": 1.2502211332321167,
      "learning_rate": 0.0001,
      "loss": 13.564,
      "step": 5
    },
    {
      "epoch": 0.0026226641897060432,
      "grad_norm": 1.2538820505142212,
      "learning_rate": 0.00012,
      "loss": 11.9462,
      "step": 6
    },
    {
      "epoch": 0.0030597748879903834,
      "grad_norm": 1.472439169883728,
      "learning_rate": 0.00014,
      "loss": 11.4779,
      "step": 7
    },
    {
      "epoch": 0.003496885586274724,
      "grad_norm": 1.660061001777649,
      "learning_rate": 0.00016,
      "loss": 11.2724,
      "step": 8
    },
    {
      "epoch": 0.003933996284559064,
      "grad_norm": 1.9470425844192505,
      "learning_rate": 0.00018,
      "loss": 12.1637,
      "step": 9
    },
    {
      "epoch": 0.004371106982843405,
      "grad_norm": 2.017232656478882,
      "learning_rate": 0.0002,
      "loss": 11.3892,
      "step": 10
    },
    {
      "epoch": 0.004808217681127745,
      "grad_norm": 2.3584163188934326,
      "learning_rate": 0.0001996917333733128,
      "loss": 11.9319,
      "step": 11
    },
    {
      "epoch": 0.0052453283794120864,
      "grad_norm": 2.078613519668579,
      "learning_rate": 0.00019876883405951377,
      "loss": 10.9623,
      "step": 12
    },
    {
      "epoch": 0.005682439077696427,
      "grad_norm": 2.032031774520874,
      "learning_rate": 0.00019723699203976766,
      "loss": 9.7538,
      "step": 13
    },
    {
      "epoch": 0.005682439077696427,
      "eval_loss": 2.5488393306732178,
      "eval_runtime": 63.2629,
      "eval_samples_per_second": 15.238,
      "eval_steps_per_second": 7.619,
      "step": 13
    },
    {
      "epoch": 0.006119549775980767,
      "grad_norm": 2.107053518295288,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.6207,
      "step": 14
    },
    {
      "epoch": 0.006556660474265108,
      "grad_norm": 2.612135648727417,
      "learning_rate": 0.0001923879532511287,
      "loss": 10.3166,
      "step": 15
    },
    {
      "epoch": 0.006993771172549448,
      "grad_norm": 2.8533310890197754,
      "learning_rate": 0.0001891006524188368,
      "loss": 8.8425,
      "step": 16
    },
    {
      "epoch": 0.007430881870833789,
      "grad_norm": 3.393040895462036,
      "learning_rate": 0.00018526401643540922,
      "loss": 9.7548,
      "step": 17
    },
    {
      "epoch": 0.007867992569118128,
      "grad_norm": 2.70773983001709,
      "learning_rate": 0.00018090169943749476,
      "loss": 9.8796,
      "step": 18
    },
    {
      "epoch": 0.00830510326740247,
      "grad_norm": 3.1191604137420654,
      "learning_rate": 0.0001760405965600031,
      "loss": 10.5876,
      "step": 19
    },
    {
      "epoch": 0.00874221396568681,
      "grad_norm": 5.541699409484863,
      "learning_rate": 0.00017071067811865476,
      "loss": 9.718,
      "step": 20
    },
    {
      "epoch": 0.009179324663971151,
      "grad_norm": 2.043881416320801,
      "learning_rate": 0.00016494480483301836,
      "loss": 9.6695,
      "step": 21
    },
    {
      "epoch": 0.00961643536225549,
      "grad_norm": 1.9487366676330566,
      "learning_rate": 0.00015877852522924732,
      "loss": 9.9164,
      "step": 22
    },
    {
      "epoch": 0.010053546060539832,
      "grad_norm": 1.9174864292144775,
      "learning_rate": 0.0001522498564715949,
      "loss": 9.524,
      "step": 23
    },
    {
      "epoch": 0.010490656758824173,
      "grad_norm": 1.9436492919921875,
      "learning_rate": 0.00014539904997395468,
      "loss": 9.6679,
      "step": 24
    },
    {
      "epoch": 0.010927767457108512,
      "grad_norm": 1.965125322341919,
      "learning_rate": 0.000138268343236509,
      "loss": 9.0866,
      "step": 25
    },
    {
      "epoch": 0.011364878155392853,
      "grad_norm": 1.902687430381775,
      "learning_rate": 0.00013090169943749476,
      "loss": 9.9846,
      "step": 26
    },
    {
      "epoch": 0.011364878155392853,
      "eval_loss": 2.3784422874450684,
      "eval_runtime": 63.2504,
      "eval_samples_per_second": 15.241,
      "eval_steps_per_second": 7.621,
      "step": 26
    },
    {
      "epoch": 0.011801988853677194,
      "grad_norm": 1.7030318975448608,
      "learning_rate": 0.00012334453638559057,
      "loss": 8.5876,
      "step": 27
    },
    {
      "epoch": 0.012239099551961534,
      "grad_norm": 1.8353570699691772,
      "learning_rate": 0.0001156434465040231,
      "loss": 9.3324,
      "step": 28
    },
    {
      "epoch": 0.012676210250245875,
      "grad_norm": 1.808311104774475,
      "learning_rate": 0.0001078459095727845,
      "loss": 9.664,
      "step": 29
    },
    {
      "epoch": 0.013113320948530216,
      "grad_norm": 1.7533966302871704,
      "learning_rate": 0.0001,
      "loss": 9.677,
      "step": 30
    },
    {
      "epoch": 0.013550431646814555,
      "grad_norm": 1.7341312170028687,
      "learning_rate": 9.215409042721552e-05,
      "loss": 8.741,
      "step": 31
    },
    {
      "epoch": 0.013987542345098896,
      "grad_norm": 1.6899504661560059,
      "learning_rate": 8.435655349597689e-05,
      "loss": 9.4402,
      "step": 32
    },
    {
      "epoch": 0.014424653043383237,
      "grad_norm": 1.7885587215423584,
      "learning_rate": 7.66554636144095e-05,
      "loss": 9.9986,
      "step": 33
    },
    {
      "epoch": 0.014861763741667578,
      "grad_norm": 1.6995981931686401,
      "learning_rate": 6.909830056250527e-05,
      "loss": 9.6771,
      "step": 34
    },
    {
      "epoch": 0.015298874439951917,
      "grad_norm": 1.615052342414856,
      "learning_rate": 6.173165676349103e-05,
      "loss": 9.5959,
      "step": 35
    },
    {
      "epoch": 0.015735985138236257,
      "grad_norm": 1.6668000221252441,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 9.7952,
      "step": 36
    },
    {
      "epoch": 0.016173095836520598,
      "grad_norm": 1.7205054759979248,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 10.3494,
      "step": 37
    },
    {
      "epoch": 0.01661020653480494,
      "grad_norm": 1.6884719133377075,
      "learning_rate": 4.12214747707527e-05,
      "loss": 9.6771,
      "step": 38
    },
    {
      "epoch": 0.01704731723308928,
      "grad_norm": 1.766587734222412,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 10.4286,
      "step": 39
    },
    {
      "epoch": 0.01704731723308928,
      "eval_loss": 2.3304331302642822,
      "eval_runtime": 63.286,
      "eval_samples_per_second": 15.232,
      "eval_steps_per_second": 7.616,
      "step": 39
    },
    {
      "epoch": 0.01748442793137362,
      "grad_norm": 1.740352749824524,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 9.5432,
      "step": 40
    },
    {
      "epoch": 0.017921538629657962,
      "grad_norm": 1.7021613121032715,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 9.3533,
      "step": 41
    },
    {
      "epoch": 0.018358649327942303,
      "grad_norm": 1.6590347290039062,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 9.7998,
      "step": 42
    },
    {
      "epoch": 0.01879576002622664,
      "grad_norm": 1.6528631448745728,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 9.4514,
      "step": 43
    },
    {
      "epoch": 0.01923287072451098,
      "grad_norm": 1.6342215538024902,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 8.8211,
      "step": 44
    },
    {
      "epoch": 0.019669981422795323,
      "grad_norm": 1.6100610494613647,
      "learning_rate": 7.612046748871327e-06,
      "loss": 8.5215,
      "step": 45
    },
    {
      "epoch": 0.020107092121079664,
      "grad_norm": 1.6995798349380493,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 10.238,
      "step": 46
    },
    {
      "epoch": 0.020544202819364005,
      "grad_norm": 1.6126399040222168,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 8.8309,
      "step": 47
    },
    {
      "epoch": 0.020981313517648346,
      "grad_norm": 1.634695291519165,
      "learning_rate": 1.231165940486234e-06,
      "loss": 9.3769,
      "step": 48
    },
    {
      "epoch": 0.021418424215932683,
      "grad_norm": 1.7255252599716187,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 8.8856,
      "step": 49
    },
    {
      "epoch": 0.021855534914217024,
      "grad_norm": 1.6557931900024414,
      "learning_rate": 0.0,
      "loss": 9.1025,
      "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": 1.44039040278528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}