{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0381788679965639,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000763577359931278,
      "grad_norm": 6.9851579666137695,
      "learning_rate": 1e-05,
      "loss": 12.5487,
      "step": 1
    },
    {
      "epoch": 0.000763577359931278,
      "eval_loss": 0.7887275815010071,
      "eval_runtime": 80.2667,
      "eval_samples_per_second": 27.483,
      "eval_steps_per_second": 13.742,
      "step": 1
    },
    {
      "epoch": 0.001527154719862556,
      "grad_norm": 6.761019229888916,
      "learning_rate": 2e-05,
      "loss": 13.5168,
      "step": 2
    },
    {
      "epoch": 0.002290732079793834,
      "grad_norm": 6.743908882141113,
      "learning_rate": 3e-05,
      "loss": 13.3954,
      "step": 3
    },
    {
      "epoch": 0.003054309439725112,
      "grad_norm": 6.837331295013428,
      "learning_rate": 4e-05,
      "loss": 11.6344,
      "step": 4
    },
    {
      "epoch": 0.00381788679965639,
      "grad_norm": 6.844388961791992,
      "learning_rate": 5e-05,
      "loss": 13.2186,
      "step": 5
    },
    {
      "epoch": 0.004581464159587668,
      "grad_norm": 5.9204230308532715,
      "learning_rate": 6e-05,
      "loss": 11.8832,
      "step": 6
    },
    {
      "epoch": 0.005345041519518946,
      "grad_norm": 7.299534797668457,
      "learning_rate": 7e-05,
      "loss": 13.6356,
      "step": 7
    },
    {
      "epoch": 0.006108618879450224,
      "grad_norm": 8.429487228393555,
      "learning_rate": 8e-05,
      "loss": 11.1401,
      "step": 8
    },
    {
      "epoch": 0.006872196239381502,
      "grad_norm": 8.498945236206055,
      "learning_rate": 9e-05,
      "loss": 12.6653,
      "step": 9
    },
    {
      "epoch": 0.00763577359931278,
      "grad_norm": 8.767837524414062,
      "learning_rate": 0.0001,
      "loss": 12.3936,
      "step": 10
    },
    {
      "epoch": 0.008399350959244059,
      "grad_norm": 9.360711097717285,
      "learning_rate": 9.98458666866564e-05,
      "loss": 12.5907,
      "step": 11
    },
    {
      "epoch": 0.009162928319175336,
      "grad_norm": 8.662163734436035,
      "learning_rate": 9.938441702975689e-05,
      "loss": 12.2145,
      "step": 12
    },
    {
      "epoch": 0.009926505679106615,
      "grad_norm": 7.386740207672119,
      "learning_rate": 9.861849601988383e-05,
      "loss": 11.7387,
      "step": 13
    },
    {
      "epoch": 0.009926505679106615,
      "eval_loss": 0.5773345828056335,
      "eval_runtime": 57.9076,
      "eval_samples_per_second": 38.095,
      "eval_steps_per_second": 19.048,
      "step": 13
    },
    {
      "epoch": 0.010690083039037892,
      "grad_norm": 6.743459224700928,
      "learning_rate": 9.755282581475769e-05,
      "loss": 9.5671,
      "step": 14
    },
    {
      "epoch": 0.011453660398969171,
      "grad_norm": 6.072397708892822,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.8066,
      "step": 15
    },
    {
      "epoch": 0.012217237758900448,
      "grad_norm": 5.454479694366455,
      "learning_rate": 9.45503262094184e-05,
      "loss": 8.8087,
      "step": 16
    },
    {
      "epoch": 0.012980815118831727,
      "grad_norm": 5.446474075317383,
      "learning_rate": 9.263200821770461e-05,
      "loss": 6.3246,
      "step": 17
    },
    {
      "epoch": 0.013744392478763004,
      "grad_norm": 7.096211910247803,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.9731,
      "step": 18
    },
    {
      "epoch": 0.014507969838694283,
      "grad_norm": 7.596373081207275,
      "learning_rate": 8.802029828000156e-05,
      "loss": 11.1521,
      "step": 19
    },
    {
      "epoch": 0.01527154719862556,
      "grad_norm": 7.020569801330566,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.0913,
      "step": 20
    },
    {
      "epoch": 0.016035124558556837,
      "grad_norm": 6.659214496612549,
      "learning_rate": 8.247240241650918e-05,
      "loss": 9.9801,
      "step": 21
    },
    {
      "epoch": 0.016798701918488118,
      "grad_norm": 8.3117094039917,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.9851,
      "step": 22
    },
    {
      "epoch": 0.017562279278419395,
      "grad_norm": 6.354142189025879,
      "learning_rate": 7.612492823579745e-05,
      "loss": 9.8489,
      "step": 23
    },
    {
      "epoch": 0.018325856638350672,
      "grad_norm": 5.176619052886963,
      "learning_rate": 7.269952498697734e-05,
      "loss": 7.758,
      "step": 24
    },
    {
      "epoch": 0.01908943399828195,
      "grad_norm": 6.188883304595947,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.0848,
      "step": 25
    },
    {
      "epoch": 0.01985301135821323,
      "grad_norm": 5.500777244567871,
      "learning_rate": 6.545084971874738e-05,
      "loss": 7.5921,
      "step": 26
    },
    {
      "epoch": 0.01985301135821323,
      "eval_loss": 0.5127847194671631,
      "eval_runtime": 57.9261,
      "eval_samples_per_second": 38.083,
      "eval_steps_per_second": 19.041,
      "step": 26
    },
    {
      "epoch": 0.020616588718144507,
      "grad_norm": 6.461605072021484,
      "learning_rate": 6.167226819279528e-05,
      "loss": 9.5291,
      "step": 27
    },
    {
      "epoch": 0.021380166078075784,
      "grad_norm": 4.939523220062256,
      "learning_rate": 5.782172325201155e-05,
      "loss": 8.5546,
      "step": 28
    },
    {
      "epoch": 0.02214374343800706,
      "grad_norm": 5.237279415130615,
      "learning_rate": 5.392295478639225e-05,
      "loss": 8.9906,
      "step": 29
    },
    {
      "epoch": 0.022907320797938342,
      "grad_norm": 4.521339416503906,
      "learning_rate": 5e-05,
      "loss": 8.4193,
      "step": 30
    },
    {
      "epoch": 0.02367089815786962,
      "grad_norm": 4.841592311859131,
      "learning_rate": 4.607704521360776e-05,
      "loss": 7.0662,
      "step": 31
    },
    {
      "epoch": 0.024434475517800897,
      "grad_norm": 4.56219482421875,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 7.6356,
      "step": 32
    },
    {
      "epoch": 0.025198052877732174,
      "grad_norm": 4.925192832946777,
      "learning_rate": 3.832773180720475e-05,
      "loss": 8.7584,
      "step": 33
    },
    {
      "epoch": 0.025961630237663454,
      "grad_norm": 4.916022777557373,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 7.8437,
      "step": 34
    },
    {
      "epoch": 0.02672520759759473,
      "grad_norm": 4.674169063568115,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.6427,
      "step": 35
    },
    {
      "epoch": 0.02748878495752601,
      "grad_norm": 5.386457920074463,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 10.0201,
      "step": 36
    },
    {
      "epoch": 0.028252362317457286,
      "grad_norm": 5.543281555175781,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 7.2569,
      "step": 37
    },
    {
      "epoch": 0.029015939677388566,
      "grad_norm": 6.018548488616943,
      "learning_rate": 2.061073738537635e-05,
      "loss": 8.205,
      "step": 38
    },
    {
      "epoch": 0.029779517037319844,
      "grad_norm": 6.134002208709717,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 10.1897,
      "step": 39
    },
    {
      "epoch": 0.029779517037319844,
      "eval_loss": 0.4907377064228058,
      "eval_runtime": 57.9204,
      "eval_samples_per_second": 38.087,
      "eval_steps_per_second": 19.043,
      "step": 39
    },
    {
      "epoch": 0.03054309439725112,
      "grad_norm": 4.678173065185547,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.2103,
      "step": 40
    },
    {
      "epoch": 0.0313066717571824,
      "grad_norm": 4.426128387451172,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 7.455,
      "step": 41
    },
    {
      "epoch": 0.032070249117113675,
      "grad_norm": 5.750243186950684,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.0289,
      "step": 42
    },
    {
      "epoch": 0.032833826477044956,
      "grad_norm": 5.712514400482178,
      "learning_rate": 7.367991782295391e-06,
      "loss": 10.2319,
      "step": 43
    },
    {
      "epoch": 0.033597403836976236,
      "grad_norm": 4.766389846801758,
      "learning_rate": 5.449673790581611e-06,
      "loss": 7.6648,
      "step": 44
    },
    {
      "epoch": 0.03436098119690751,
      "grad_norm": 5.167623996734619,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 7.2538,
      "step": 45
    },
    {
      "epoch": 0.03512455855683879,
      "grad_norm": 5.637135982513428,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 6.7357,
      "step": 46
    },
    {
      "epoch": 0.03588813591677007,
      "grad_norm": 4.531375885009766,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 6.535,
      "step": 47
    },
    {
      "epoch": 0.036651713276701345,
      "grad_norm": 6.260673522949219,
      "learning_rate": 6.15582970243117e-07,
      "loss": 8.6059,
      "step": 48
    },
    {
      "epoch": 0.037415290636632625,
      "grad_norm": 5.334906578063965,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 8.5101,
      "step": 49
    },
    {
      "epoch": 0.0381788679965639,
      "grad_norm": 4.816957950592041,
      "learning_rate": 0.0,
      "loss": 8.5046,
      "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": 2.8708991888523264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}