{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02536354413256679,
  "eval_steps": 6,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005072708826513358,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0005072708826513358,
      "eval_loss": NaN,
      "eval_runtime": 264.9243,
      "eval_samples_per_second": 9.403,
      "eval_steps_per_second": 2.352,
      "step": 1
    },
    {
      "epoch": 0.0010145417653026716,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0015218126479540075,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.002536354413256679,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.003043625295908015,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003043625295908015,
      "eval_loss": NaN,
      "eval_runtime": 264.9935,
      "eval_samples_per_second": 9.4,
      "eval_steps_per_second": 2.351,
      "step": 6
    },
    {
      "epoch": 0.003550896178559351,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.004565437943862023,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.005072708826513358,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.005579979709164694,
      "grad_norm": NaN,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.00608725059181603,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00608725059181603,
      "eval_loss": NaN,
      "eval_runtime": 264.2404,
      "eval_samples_per_second": 9.427,
      "eval_steps_per_second": 2.358,
      "step": 12
    },
    {
      "epoch": 0.0065945214744673655,
      "grad_norm": NaN,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.007101792357118702,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.007609063239770037,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.008116334122421373,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.008623605005072709,
      "grad_norm": NaN,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.009130875887724045,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.009130875887724045,
      "eval_loss": NaN,
      "eval_runtime": 263.7037,
      "eval_samples_per_second": 9.446,
      "eval_steps_per_second": 2.363,
      "step": 18
    },
    {
      "epoch": 0.00963814677037538,
      "grad_norm": NaN,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.010145417653026716,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.010652688535678053,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.011159959418329387,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.011667230300980724,
      "grad_norm": NaN,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.01217450118363206,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.01217450118363206,
      "eval_loss": NaN,
      "eval_runtime": 264.6687,
      "eval_samples_per_second": 9.412,
      "eval_steps_per_second": 2.354,
      "step": 24
    },
    {
      "epoch": 0.012681772066283395,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.013189042948934731,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.013696313831586067,
      "grad_norm": NaN,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.014203584714237404,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.014710855596888738,
      "grad_norm": NaN,
      "learning_rate": 5.392295478639225e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.015218126479540075,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.015218126479540075,
      "eval_loss": NaN,
      "eval_runtime": 264.1256,
      "eval_samples_per_second": 9.431,
      "eval_steps_per_second": 2.359,
      "step": 30
    },
    {
      "epoch": 0.01572539736219141,
      "grad_norm": NaN,
      "learning_rate": 4.607704521360776e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.016232668244842745,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.016739939127494084,
      "grad_norm": NaN,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.017247210010145418,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.017754480892796753,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.01826175177544809,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.01826175177544809,
      "eval_loss": NaN,
      "eval_runtime": 264.4171,
      "eval_samples_per_second": 9.421,
      "eval_steps_per_second": 2.356,
      "step": 36
    },
    {
      "epoch": 0.018769022658099425,
      "grad_norm": NaN,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.01927629354075076,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.019783564423402098,
      "grad_norm": NaN,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.020290835306053433,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.020798106188704767,
      "grad_norm": NaN,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.021305377071356105,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.021305377071356105,
      "eval_loss": NaN,
      "eval_runtime": 264.6238,
      "eval_samples_per_second": 9.413,
      "eval_steps_per_second": 2.354,
      "step": 42
    },
    {
      "epoch": 0.02181264795400744,
      "grad_norm": NaN,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.022319918836658775,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.022827189719310113,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.023334460601961447,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.023841731484612782,
      "grad_norm": NaN,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.02434900236726412,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.02434900236726412,
      "eval_loss": NaN,
      "eval_runtime": 264.7641,
      "eval_samples_per_second": 9.408,
      "eval_steps_per_second": 2.353,
      "step": 48
    },
    {
      "epoch": 0.024856273249915455,
      "grad_norm": NaN,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.02536354413256679,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.119015678246912e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}