{
  "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": 14.322428703308105,
      "learning_rate": 1e-05,
      "loss": 2.4609375,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 15.11201000213623,
      "learning_rate": 9.986018985905901e-06,
      "loss": 2.0888671875,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 9.351886749267578,
      "learning_rate": 9.944154131125643e-06,
      "loss": 1.759765625,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 13.965060234069824,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.71044921875,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 5.491657257080078,
      "learning_rate": 9.777864028930705e-06,
      "loss": 1.615234375,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.9241886138916016,
      "learning_rate": 9.654368743221022e-06,
      "loss": 1.67529296875,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.04229736328125,
      "learning_rate": 9.504844339512096e-06,
      "loss": 1.5458984375,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.428880214691162,
      "learning_rate": 9.330127018922195e-06,
      "loss": 1.57421875,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.3046977519989014,
      "learning_rate": 9.131193871579975e-06,
      "loss": 1.4345703125,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.0754127502441406,
      "learning_rate": 8.90915741234015e-06,
      "loss": 1.5341796875,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 2.0800693035125732,
      "learning_rate": 8.665259359149132e-06,
      "loss": 1.509765625,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.0468623638153076,
      "learning_rate": 8.400863688854598e-06,
      "loss": 1.42529296875,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.7779223918914795,
      "learning_rate": 8.117449009293668e-06,
      "loss": 1.4794921875,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.9640353918075562,
      "learning_rate": 7.81660029031811e-06,
      "loss": 1.45751953125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.9327659606933594,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.48193359375,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.7382633686065674,
      "learning_rate": 7.169418695587791e-06,
      "loss": 1.560546875,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 1.8076167106628418,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 1.516845703125,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.7258213758468628,
      "learning_rate": 6.473775872054522e-06,
      "loss": 1.50341796875,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 1.665819525718689,
      "learning_rate": 6.112604669781572e-06,
      "loss": 1.5205078125,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.7510051727294922,
      "learning_rate": 5.745211330880872e-06,
      "loss": 1.4677734375,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9754207134246826,
      "learning_rate": 5.373650467932122e-06,
      "loss": 1.33544921875,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 2.1669719219207764,
      "learning_rate": 5e-06,
      "loss": 1.20068359375,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 2.0153214931488037,
      "learning_rate": 4.626349532067879e-06,
      "loss": 1.2705078125,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 2.2064366340637207,
      "learning_rate": 4.254788669119127e-06,
      "loss": 1.3056640625,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.9925411939620972,
      "learning_rate": 3.887395330218429e-06,
      "loss": 1.34521484375,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.8726602792739868,
      "learning_rate": 3.526224127945479e-06,
      "loss": 1.2138671875,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 2.018559694290161,
      "learning_rate": 3.173294878168025e-06,
      "loss": 1.187255859375,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 2.3202576637268066,
      "learning_rate": 2.83058130441221e-06,
      "loss": 1.03955078125,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 2.421531915664673,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 1.13671875,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 2.1559412479400635,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 0.9423828125,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 1.8613183498382568,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 1.099853515625,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.944466233253479,
      "learning_rate": 1.5991363111454023e-06,
      "loss": 1.059326171875,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 1.7923849821090698,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 1.00732421875,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 1.8220503330230713,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 1.106201171875,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.9228514432907104,
      "learning_rate": 8.688061284200266e-07,
      "loss": 1.081298828125,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.9409388303756714,
      "learning_rate": 6.698729810778065e-07,
      "loss": 1.1455078125,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 1.8451006412506104,
      "learning_rate": 4.951556604879049e-07,
      "loss": 1.260498046875,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 1.9668972492218018,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 1.248291015625,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.9751290082931519,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 1.265625,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 2.0152292251586914,
      "learning_rate": 1.253604390908819e-07,
      "loss": 1.3232421875,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 2.061882257461548,
      "learning_rate": 5.584586887435739e-08,
      "loss": 1.255126953125,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.83892822265625,
      "learning_rate": 1.3981014094099354e-08,
      "loss": 1.11865234375,
      "step": 42
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.25,
      "eval_runtime": 12.186,
      "eval_samples_per_second": 0.082,
      "eval_steps_per_second": 0.082,
      "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": 8.841841215327437e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}