{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015205945524700159,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030411891049400314,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00030411891049400314,
      "eval_loss": NaN,
      "eval_runtime": 551.3396,
      "eval_samples_per_second": 10.045,
      "eval_steps_per_second": 5.022,
      "step": 1
    },
    {
      "epoch": 0.0006082378209880063,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0009123567314820094,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0012164756419760126,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 30.1683,
      "step": 4
    },
    {
      "epoch": 0.0015205945524700158,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0018247134629640188,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002128832373458022,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 1.6907,
      "step": 7
    },
    {
      "epoch": 0.002432951283952025,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0027370701944460286,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0030411891049400316,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0033453080154340347,
      "grad_norm": NaN,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0036494269259280377,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.003953545836422041,
      "grad_norm": NaN,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.003953545836422041,
      "eval_loss": NaN,
      "eval_runtime": 389.7867,
      "eval_samples_per_second": 14.208,
      "eval_steps_per_second": 7.104,
      "step": 13
    },
    {
      "epoch": 0.004257664746916044,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.004561783657410047,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.4067,
      "step": 15
    },
    {
      "epoch": 0.00486590256790405,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.005170021478398053,
      "grad_norm": NaN,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.005474140388892057,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00577825929938606,
      "grad_norm": NaN,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.006082378209880063,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.006386497120374066,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.006690616030868069,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.006994734941362072,
      "grad_norm": NaN,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.007298853851856075,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.007602972762350079,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.007907091672844082,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 684.1104,
      "step": 26
    },
    {
      "epoch": 0.007907091672844082,
      "eval_loss": NaN,
      "eval_runtime": 390.2284,
      "eval_samples_per_second": 14.192,
      "eval_steps_per_second": 7.096,
      "step": 26
    },
    {
      "epoch": 0.008211210583338084,
      "grad_norm": NaN,
      "learning_rate": 6.167226819279528e-05,
      "loss": 3596.0974,
      "step": 27
    },
    {
      "epoch": 0.008515329493832088,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.008819448404326092,
      "grad_norm": NaN,
      "learning_rate": 5.392295478639225e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.009123567314820094,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.009427686225314098,
      "grad_norm": NaN,
      "learning_rate": 4.607704521360776e-05,
      "loss": 97.7615,
      "step": 31
    },
    {
      "epoch": 0.0097318051358081,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.010035924046302104,
      "grad_norm": NaN,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.010340042956796107,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.01064416186729011,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.010948280777784114,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.011252399688278117,
      "grad_norm": NaN,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.01155651859877212,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.011860637509266123,
      "grad_norm": NaN,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.011860637509266123,
      "eval_loss": NaN,
      "eval_runtime": 390.3928,
      "eval_samples_per_second": 14.186,
      "eval_steps_per_second": 7.093,
      "step": 39
    },
    {
      "epoch": 0.012164756419760126,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.012468875330254129,
      "grad_norm": NaN,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.012772994240748133,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.013077113151242136,
      "grad_norm": NaN,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.013381232061736139,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.013685350972230143,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 890.1249,
      "step": 45
    },
    {
      "epoch": 0.013989469882724145,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.014293588793218149,
      "grad_norm": NaN,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 864.3728,
      "step": 47
    },
    {
      "epoch": 0.01459770770371215,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.014901826614206155,
      "grad_norm": NaN,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.015205945524700159,
      "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": 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": 1.256623184019456e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}