{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 57,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 2.16679561289133,
      "learning_rate": 0.0,
      "loss": 0.8483,
      "step": 1
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.0661611701125664,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.8763,
      "step": 2
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 2.2703699566521167,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.0209,
      "step": 3
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.3467447169533786,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.0622,
      "step": 4
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 1.843987567276686,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.8564,
      "step": 5
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.025183429740274,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0078,
      "step": 6
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 1.715914844595336,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.9971,
      "step": 7
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.7586304736238754,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.9461,
      "step": 8
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 2.0895766846468975,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.9608,
      "step": 9
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.3266913831957696,
      "learning_rate": 6e-06,
      "loss": 0.9865,
      "step": 10
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 1.3505904361209118,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0305,
      "step": 11
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.406349569576858,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.8987,
      "step": 12
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 1.5607966014683508,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9343,
      "step": 13
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.6420771105271474,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.9125,
      "step": 14
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.2411935656694923,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.9709,
      "step": 15
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.285099856857185,
      "learning_rate": 1e-05,
      "loss": 0.9217,
      "step": 16
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 1.4175055233514002,
      "learning_rate": 9.999661540018812e-06,
      "loss": 1.0184,
      "step": 17
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.4530633248486682,
      "learning_rate": 9.99864620589731e-06,
      "loss": 0.9018,
      "step": 18
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.0989691782403928,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.9223,
      "step": 19
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.5827873971167827,
      "learning_rate": 9.994585556692624e-06,
      "loss": 0.9576,
      "step": 20
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.8592190455694358,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.8955,
      "step": 21
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.8299857961232732,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.764,
      "step": 22
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 0.9171035252108198,
      "learning_rate": 9.98342444022253e-06,
      "loss": 0.8973,
      "step": 23
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.740990179490497,
      "learning_rate": 9.978353953249023e-06,
      "loss": 0.7952,
      "step": 24
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.816867836066284,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.9235,
      "step": 25
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.9174781904591494,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.8875,
      "step": 26
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.8146943719573134,
      "learning_rate": 9.959101757706308e-06,
      "loss": 0.8082,
      "step": 27
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7068924098220349,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.8764,
      "step": 28
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 0.5772155779629496,
      "learning_rate": 9.942908597485558e-06,
      "loss": 0.8979,
      "step": 29
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5957140303254264,
      "learning_rate": 9.933807660562898e-06,
      "loss": 0.7838,
      "step": 30
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 0.5373347072638098,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.8394,
      "step": 31
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.5489672984945708,
      "learning_rate": 9.913603233532067e-06,
      "loss": 0.7705,
      "step": 32
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.7080158661684792,
      "learning_rate": 9.902502478779897e-06,
      "loss": 0.8684,
      "step": 33
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.6637923153891901,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.9679,
      "step": 34
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.614625362769404,
      "learning_rate": 9.878311400921072e-06,
      "loss": 0.8121,
      "step": 35
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.6692936903098997,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.8273,
      "step": 36
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 0.5563500120725223,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.8624,
      "step": 37
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5291416665431522,
      "learning_rate": 9.83707609731432e-06,
      "loss": 0.8753,
      "step": 38
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.5476616236709854,
      "learning_rate": 9.822018700574696e-06,
      "loss": 0.8981,
      "step": 39
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.48226927788687945,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.8637,
      "step": 40
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 0.5462565995554229,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.8686,
      "step": 41
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5505131342762903,
      "learning_rate": 9.77293816123866e-06,
      "loss": 0.8037,
      "step": 42
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 0.5184970156439064,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8363,
      "step": 43
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5089766005853604,
      "learning_rate": 9.736983212571646e-06,
      "loss": 0.7526,
      "step": 44
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.48754905624702916,
      "learning_rate": 9.718042531967918e-06,
      "loss": 0.8691,
      "step": 45
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5413618026254184,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8463,
      "step": 46
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 0.5572304500075312,
      "learning_rate": 9.678247579197658e-06,
      "loss": 0.8501,
      "step": 47
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.4244378287340113,
      "learning_rate": 9.657398694630713e-06,
      "loss": 0.8341,
      "step": 48
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 0.5105742345404872,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.9266,
      "step": 49
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.4564062461733754,
      "learning_rate": 9.613812221777212e-06,
      "loss": 0.6665,
      "step": 50
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.49700992641846237,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.8952,
      "step": 51
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.5028869634727683,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.8637,
      "step": 52
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 0.47195418650900134,
      "learning_rate": 9.543755644867823e-06,
      "loss": 0.8156,
      "step": 53
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.49745215491197114,
      "learning_rate": 9.519168849742603e-06,
      "loss": 0.7709,
      "step": 54
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.5022824826217431,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.8101,
      "step": 55
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.47037159516710164,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8214,
      "step": 56
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5073480413670769,
      "learning_rate": 9.441751253965022e-06,
      "loss": 0.7322,
      "step": 57
    }
  ],
  "logging_steps": 1,
  "max_steps": 285,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 13124895178752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}