{
  "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": 2.3181249915556488,
      "learning_rate": 0.0,
      "loss": 0.8483,
      "step": 1
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.3031609820520065,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.8765,
      "step": 2
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 2.5315969251116233,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.0209,
      "step": 3
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.6115330874356784,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.0621,
      "step": 4
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 2.6177442321379703,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.8563,
      "step": 5
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.2800115956534657,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0083,
      "step": 6
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 1.8440531676316312,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.9982,
      "step": 7
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.818151618586041,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.9474,
      "step": 8
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.7230747772024742,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.9616,
      "step": 9
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.3680905039669917,
      "learning_rate": 6e-06,
      "loss": 0.9869,
      "step": 10
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 1.4455967664395566,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0296,
      "step": 11
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.838519352672828,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.9008,
      "step": 12
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 1.746600094936107,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9385,
      "step": 13
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.5993390926077906,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.9149,
      "step": 14
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.4190530136292803,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.9739,
      "step": 15
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.5476403448451475,
      "learning_rate": 1e-05,
      "loss": 0.9248,
      "step": 16
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 1.8296015433545236,
      "learning_rate": 9.999661540018812e-06,
      "loss": 1.021,
      "step": 17
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.4666326831664898,
      "learning_rate": 9.99864620589731e-06,
      "loss": 0.9051,
      "step": 18
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.2470444433529435,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.9253,
      "step": 19
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.1769038399974867,
      "learning_rate": 9.994585556692624e-06,
      "loss": 0.9595,
      "step": 20
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 2.6056499740362202,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.8963,
      "step": 21
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 1.2892838004713705,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.7664,
      "step": 22
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 1.2011953377876559,
      "learning_rate": 9.98342444022253e-06,
      "loss": 0.9012,
      "step": 23
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.8570506663016774,
      "learning_rate": 9.978353953249023e-06,
      "loss": 0.7982,
      "step": 24
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.8652112443789233,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.9253,
      "step": 25
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.9653001049798393,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.8896,
      "step": 26
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.8846034616258485,
      "learning_rate": 9.959101757706308e-06,
      "loss": 0.8099,
      "step": 27
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7810067582068709,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.8782,
      "step": 28
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 0.6544621596080209,
      "learning_rate": 9.942908597485558e-06,
      "loss": 0.8991,
      "step": 29
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.650602123344418,
      "learning_rate": 9.933807660562898e-06,
      "loss": 0.7848,
      "step": 30
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 0.6643753742626393,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.8407,
      "step": 31
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.6382815668704741,
      "learning_rate": 9.913603233532067e-06,
      "loss": 0.7703,
      "step": 32
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.7892950770322912,
      "learning_rate": 9.902502478779897e-06,
      "loss": 0.8698,
      "step": 33
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.7708210358290128,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.969,
      "step": 34
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.8189039214769849,
      "learning_rate": 9.878311400921072e-06,
      "loss": 0.813,
      "step": 35
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.6904369205020999,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.8283,
      "step": 36
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 0.6148536786862524,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.8632,
      "step": 37
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5768762634588235,
      "learning_rate": 9.83707609731432e-06,
      "loss": 0.8763,
      "step": 38
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.6683735778256117,
      "learning_rate": 9.822018700574696e-06,
      "loss": 0.8983,
      "step": 39
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.5217247956874884,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.8641,
      "step": 40
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 0.58257740620197,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.8692,
      "step": 41
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.6232683716090549,
      "learning_rate": 9.77293816123866e-06,
      "loss": 0.8046,
      "step": 42
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 0.6283296712711599,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.837,
      "step": 43
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5958179302224206,
      "learning_rate": 9.736983212571646e-06,
      "loss": 0.7531,
      "step": 44
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.5679750039894512,
      "learning_rate": 9.718042531967918e-06,
      "loss": 0.8698,
      "step": 45
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5878126492609907,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8466,
      "step": 46
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 0.5818690232830938,
      "learning_rate": 9.678247579197658e-06,
      "loss": 0.851,
      "step": 47
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.538107743012865,
      "learning_rate": 9.657398694630713e-06,
      "loss": 0.835,
      "step": 48
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 0.7126873960175786,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.9265,
      "step": 49
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.532600934634179,
      "learning_rate": 9.613812221777212e-06,
      "loss": 0.6671,
      "step": 50
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.5467907648189101,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.8962,
      "step": 51
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.5277460536404931,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.8645,
      "step": 52
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 0.49079200391848715,
      "learning_rate": 9.543755644867823e-06,
      "loss": 0.8165,
      "step": 53
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.5531673037715197,
      "learning_rate": 9.519168849742603e-06,
      "loss": 0.7718,
      "step": 54
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.514036737329238,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.8105,
      "step": 55
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.5133770699616473,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8217,
      "step": 56
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5937230846401819,
      "learning_rate": 9.441751253965022e-06,
      "loss": 0.7339,
      "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
}