{
  "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": 2.1658732413844044,
      "learning_rate": 0.0,
      "loss": 0.8483,
      "step": 1
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.092006940468524,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.8765,
      "step": 2
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 2.275864451889245,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.0208,
      "step": 3
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.3835659363654167,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.062,
      "step": 4
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 1.8668614513642336,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.8564,
      "step": 5
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.042827888630328,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0079,
      "step": 6
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 1.7108395348483465,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.9971,
      "step": 7
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.7285480717242914,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.9464,
      "step": 8
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.4329487505630585,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.9607,
      "step": 9
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.2795124499162036,
      "learning_rate": 6e-06,
      "loss": 0.9863,
      "step": 10
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 1.2605076330876026,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0293,
      "step": 11
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.3904361544294626,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.8981,
      "step": 12
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 1.4934089139203042,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9339,
      "step": 13
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.426034050887767,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.9114,
      "step": 14
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.2195840821985733,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.9704,
      "step": 15
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.3112838302645187,
      "learning_rate": 1e-05,
      "loss": 0.921,
      "step": 16
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 1.4147363764085927,
      "learning_rate": 9.999661540018812e-06,
      "loss": 1.0178,
      "step": 17
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 3.0364757241727425,
      "learning_rate": 9.99864620589731e-06,
      "loss": 0.9016,
      "step": 18
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.1966597334373839,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.9241,
      "step": 19
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.0673860693223811,
      "learning_rate": 9.994585556692624e-06,
      "loss": 0.9605,
      "step": 20
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.9159275821464556,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.8978,
      "step": 21
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.8662523471810823,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.7651,
      "step": 22
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 0.9013821931274979,
      "learning_rate": 9.98342444022253e-06,
      "loss": 0.8986,
      "step": 23
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.7877029407981232,
      "learning_rate": 9.978353953249023e-06,
      "loss": 0.7958,
      "step": 24
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.8224354382712344,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.9247,
      "step": 25
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.908198561067024,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.8886,
      "step": 26
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.8471005617195208,
      "learning_rate": 9.959101757706308e-06,
      "loss": 0.8091,
      "step": 27
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7441058742609257,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.8774,
      "step": 28
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 0.6415749968368839,
      "learning_rate": 9.942908597485558e-06,
      "loss": 0.8987,
      "step": 29
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5945595943682435,
      "learning_rate": 9.933807660562898e-06,
      "loss": 0.7845,
      "step": 30
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 0.5348299561393488,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.8401,
      "step": 31
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.5449412249752669,
      "learning_rate": 9.913603233532067e-06,
      "loss": 0.7708,
      "step": 32
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.7606361821473685,
      "learning_rate": 9.902502478779897e-06,
      "loss": 0.8696,
      "step": 33
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.6987567739630257,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.9685,
      "step": 34
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.6577860614813181,
      "learning_rate": 9.878311400921072e-06,
      "loss": 0.8129,
      "step": 35
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.613409929779683,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.8279,
      "step": 36
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 0.8310936385078747,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.8629,
      "step": 37
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5401034869147716,
      "learning_rate": 9.83707609731432e-06,
      "loss": 0.8763,
      "step": 38
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.5645732604776249,
      "learning_rate": 9.822018700574696e-06,
      "loss": 0.8987,
      "step": 39
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.48907017080577125,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.8645,
      "step": 40
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 0.5336160010922303,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.8694,
      "step": 41
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5616846107481482,
      "learning_rate": 9.77293816123866e-06,
      "loss": 0.8044,
      "step": 42
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 0.5285876380934174,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8373,
      "step": 43
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5339805004772071,
      "learning_rate": 9.736983212571646e-06,
      "loss": 0.7534,
      "step": 44
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.4965160387028941,
      "learning_rate": 9.718042531967918e-06,
      "loss": 0.87,
      "step": 45
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5512110498718402,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8465,
      "step": 46
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 0.5556768293250771,
      "learning_rate": 9.678247579197658e-06,
      "loss": 0.8509,
      "step": 47
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.43424614496891145,
      "learning_rate": 9.657398694630713e-06,
      "loss": 0.8351,
      "step": 48
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 0.517819637053559,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.9268,
      "step": 49
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.4573125121358173,
      "learning_rate": 9.613812221777212e-06,
      "loss": 0.6669,
      "step": 50
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.4918423165455613,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.896,
      "step": 51
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.4873519914477964,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.8642,
      "step": 52
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 0.4959554344589731,
      "learning_rate": 9.543755644867823e-06,
      "loss": 0.8161,
      "step": 53
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.5053982708053872,
      "learning_rate": 9.519168849742603e-06,
      "loss": 0.7712,
      "step": 54
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.4999876957766244,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.8104,
      "step": 55
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.4802283149352191,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8219,
      "step": 56
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5730089270450355,
      "learning_rate": 9.441751253965022e-06,
      "loss": 0.733,
      "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
}