{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 42,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 47.114620208740234,
      "learning_rate": 1e-05,
      "loss": 2.02490234375,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 16.21673011779785,
      "learning_rate": 9.986018985905901e-06,
      "loss": 1.59912109375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 5.822995185852051,
      "learning_rate": 9.944154131125643e-06,
      "loss": 1.351806640625,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 4.2035346031188965,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.27783203125,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 5.645230770111084,
      "learning_rate": 9.777864028930705e-06,
      "loss": 1.2666015625,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.099782705307007,
      "learning_rate": 9.654368743221022e-06,
      "loss": 1.217041015625,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.9546079635620117,
      "learning_rate": 9.504844339512096e-06,
      "loss": 1.25341796875,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.0794341564178467,
      "learning_rate": 9.330127018922195e-06,
      "loss": 1.2431640625,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.338012456893921,
      "learning_rate": 9.131193871579975e-06,
      "loss": 1.24365234375,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.0117416381835938,
      "learning_rate": 8.90915741234015e-06,
      "loss": 1.24462890625,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 1.996274709701538,
      "learning_rate": 8.665259359149132e-06,
      "loss": 1.1787109375,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.036649703979492,
      "learning_rate": 8.400863688854598e-06,
      "loss": 1.11279296875,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.8918031454086304,
      "learning_rate": 8.117449009293668e-06,
      "loss": 1.199951171875,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.9615988731384277,
      "learning_rate": 7.81660029031811e-06,
      "loss": 1.17578125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.84268057346344,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.22509765625,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.0657312870025635,
      "learning_rate": 7.169418695587791e-06,
      "loss": 1.172607421875,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 1.7409400939941406,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 1.19189453125,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.8740795850753784,
      "learning_rate": 6.473775872054522e-06,
      "loss": 1.256683349609375,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 1.955309510231018,
      "learning_rate": 6.112604669781572e-06,
      "loss": 1.189697265625,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.739691972732544,
      "learning_rate": 5.745211330880872e-06,
      "loss": 1.20556640625,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7707955837249756,
      "learning_rate": 5.373650467932122e-06,
      "loss": 1.164306640625,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 1.8814774751663208,
      "learning_rate": 5e-06,
      "loss": 1.023681640625,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 1.913423776626587,
      "learning_rate": 4.626349532067879e-06,
      "loss": 1.11181640625,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 2.2428364753723145,
      "learning_rate": 4.254788669119127e-06,
      "loss": 0.937255859375,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 2.666365623474121,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.790283203125,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 2.26198410987854,
      "learning_rate": 3.526224127945479e-06,
      "loss": 0.847412109375,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 2.1548070907592773,
      "learning_rate": 3.173294878168025e-06,
      "loss": 0.7120361328125,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.8003593683242798,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.794189453125,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 1.9238229990005493,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.773681640625,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 2.063481569290161,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 0.769287109375,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 1.9876765012741089,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.792236328125,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 2.1075704097747803,
      "learning_rate": 1.5991363111454023e-06,
      "loss": 0.782958984375,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 2.1828715801239014,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 0.72314453125,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 2.173276901245117,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.8433837890625,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 2.183286190032959,
      "learning_rate": 8.688061284200266e-07,
      "loss": 0.814208984375,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 2.2698564529418945,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.906494140625,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 2.2014272212982178,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.864990234375,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 2.1251847743988037,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 0.921875,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 2.3024938106536865,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 0.9878044128417969,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 2.252558946609497,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.91650390625,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 2.3827097415924072,
      "learning_rate": 5.584586887435739e-08,
      "loss": 1.00830078125,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.2944517135620117,
      "learning_rate": 1.3981014094099354e-08,
      "loss": 0.984130859375,
      "step": 42
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.21484375,
      "eval_runtime": 12.8117,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.078,
      "step": 42
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.449248628178944e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}