{
  "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": 2.17390962259075,
      "learning_rate": 0.0,
      "loss": 0.8567,
      "step": 1
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.0656455049606737,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.8846,
      "step": 2
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 2.2708121056670953,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.0291,
      "step": 3
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.365595492243331,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.0705,
      "step": 4
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 1.8384054758679238,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.8647,
      "step": 5
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.036117612986614,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0162,
      "step": 6
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 2.325763682934943,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.0055,
      "step": 7
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.7398457854985685,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.9548,
      "step": 8
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.6439720372202178,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.9699,
      "step": 9
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.374454745766853,
      "learning_rate": 6e-06,
      "loss": 0.9953,
      "step": 10
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 1.3979480248099998,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0385,
      "step": 11
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.3821620513994028,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.907,
      "step": 12
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 1.4676374577990563,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9428,
      "step": 13
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.4070454710605471,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.9202,
      "step": 14
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.1923480023349917,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.9786,
      "step": 15
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.261121398600595,
      "learning_rate": 1e-05,
      "loss": 0.9293,
      "step": 16
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 1.3814288026612527,
      "learning_rate": 9.999661540018812e-06,
      "loss": 1.0259,
      "step": 17
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.436314840212135,
      "learning_rate": 9.99864620589731e-06,
      "loss": 0.9098,
      "step": 18
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.1220881828694826,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.9303,
      "step": 19
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.9534985786023815,
      "learning_rate": 9.994585556692624e-06,
      "loss": 0.9658,
      "step": 20
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.8453013121687268,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.904,
      "step": 21
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.82784292842882,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.7715,
      "step": 22
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 0.9205287128744017,
      "learning_rate": 9.98342444022253e-06,
      "loss": 0.9057,
      "step": 23
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.775173804826771,
      "learning_rate": 9.978353953249023e-06,
      "loss": 0.8032,
      "step": 24
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.8335288829302911,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.9325,
      "step": 25
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.888478333312054,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.8962,
      "step": 26
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.8225468788134248,
      "learning_rate": 9.959101757706308e-06,
      "loss": 0.8168,
      "step": 27
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7149445296020257,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.8853,
      "step": 28
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 0.6010876915017637,
      "learning_rate": 9.942908597485558e-06,
      "loss": 0.9066,
      "step": 29
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5720183594087992,
      "learning_rate": 9.933807660562898e-06,
      "loss": 0.7922,
      "step": 30
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 0.5481778830987162,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.8479,
      "step": 31
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.5880660111787017,
      "learning_rate": 9.913603233532067e-06,
      "loss": 0.7787,
      "step": 32
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.7553250242786413,
      "learning_rate": 9.902502478779897e-06,
      "loss": 0.877,
      "step": 33
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.707908642247859,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.9764,
      "step": 34
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.6322147241224138,
      "learning_rate": 9.878311400921072e-06,
      "loss": 0.821,
      "step": 35
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.6043957998914848,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.8361,
      "step": 36
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 0.5786996358697318,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.8706,
      "step": 37
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.554932463436758,
      "learning_rate": 9.83707609731432e-06,
      "loss": 0.8839,
      "step": 38
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.5551379586898564,
      "learning_rate": 9.822018700574696e-06,
      "loss": 0.9064,
      "step": 39
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.48594696065414417,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.8728,
      "step": 40
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 0.5388656565361478,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.877,
      "step": 41
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5567627975551519,
      "learning_rate": 9.77293816123866e-06,
      "loss": 0.8122,
      "step": 42
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 0.5194666382388214,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.845,
      "step": 43
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5091089613539003,
      "learning_rate": 9.736983212571646e-06,
      "loss": 0.7616,
      "step": 44
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.5072634456763613,
      "learning_rate": 9.718042531967918e-06,
      "loss": 0.8778,
      "step": 45
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5399374251736943,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8548,
      "step": 46
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 0.7945467224319946,
      "learning_rate": 9.678247579197658e-06,
      "loss": 0.8591,
      "step": 47
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.43527176017346525,
      "learning_rate": 9.657398694630713e-06,
      "loss": 0.8433,
      "step": 48
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 0.5111674285583461,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.9353,
      "step": 49
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.45287978154695185,
      "learning_rate": 9.613812221777212e-06,
      "loss": 0.6752,
      "step": 50
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.483149833089933,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.9043,
      "step": 51
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.5566166400784528,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.8724,
      "step": 52
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 0.44710547324238276,
      "learning_rate": 9.543755644867823e-06,
      "loss": 0.8242,
      "step": 53
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.49749712723352163,
      "learning_rate": 9.519168849742603e-06,
      "loss": 0.7795,
      "step": 54
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.4946270677335486,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.8189,
      "step": 55
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.48109640594683084,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8304,
      "step": 56
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0373379068156559,
      "learning_rate": 9.441751253965022e-06,
      "loss": 0.7409,
      "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
}