{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 11,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017241379310344827,
      "grad_norm": 0.21293413639068604,
      "learning_rate": 0.0,
      "loss": 1.57470703125,
      "step": 1
    },
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 0.2269705981016159,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.6982421875,
      "step": 2
    },
    {
      "epoch": 0.05172413793103448,
      "grad_norm": 0.2178458869457245,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.34033203125,
      "step": 3
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 0.21527980268001556,
      "learning_rate": 5e-06,
      "loss": 1.51416015625,
      "step": 4
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.21911631524562836,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.59765625,
      "step": 5
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 0.1833397001028061,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.54833984375,
      "step": 6
    },
    {
      "epoch": 0.1206896551724138,
      "grad_norm": 0.20413196086883545,
      "learning_rate": 1e-05,
      "loss": 1.45361328125,
      "step": 7
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.19401277601718903,
      "learning_rate": 9.991789994004929e-06,
      "loss": 1.41455078125,
      "step": 8
    },
    {
      "epoch": 0.15517241379310345,
      "grad_norm": 0.23864445090293884,
      "learning_rate": 9.967189933441243e-06,
      "loss": 1.4365234375,
      "step": 9
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.2296784520149231,
      "learning_rate": 9.926289581262147e-06,
      "loss": 1.35986328125,
      "step": 10
    },
    {
      "epoch": 0.1896551724137931,
      "grad_norm": 0.24175795912742615,
      "learning_rate": 9.869238178417235e-06,
      "loss": 1.5634765625,
      "step": 11
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 0.20265139639377594,
      "learning_rate": 9.796243899288455e-06,
      "loss": 1.52880859375,
      "step": 12
    },
    {
      "epoch": 0.22413793103448276,
      "grad_norm": 0.23336376249790192,
      "learning_rate": 9.707573092084368e-06,
      "loss": 1.689453125,
      "step": 13
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 0.2111799418926239,
      "learning_rate": 9.603549306964408e-06,
      "loss": 1.61328125,
      "step": 14
    },
    {
      "epoch": 0.2413793103448276,
      "eval_loss": 1.4794921875,
      "eval_runtime": 2.5217,
      "eval_samples_per_second": 1.586,
      "eval_steps_per_second": 0.397,
      "step": 14
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 0.21442772448062897,
      "learning_rate": 9.484552115439445e-06,
      "loss": 1.39990234375,
      "step": 15
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.21152661740779877,
      "learning_rate": 9.351015725356515e-06,
      "loss": 1.42919921875,
      "step": 16
    },
    {
      "epoch": 0.29310344827586204,
      "grad_norm": 0.21132130920886993,
      "learning_rate": 9.203427396521454e-06,
      "loss": 1.5087890625,
      "step": 17
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 0.22954435646533966,
      "learning_rate": 9.042325662740726e-06,
      "loss": 1.46826171875,
      "step": 18
    },
    {
      "epoch": 0.3275862068965517,
      "grad_norm": 0.23091132938861847,
      "learning_rate": 8.868298366769956e-06,
      "loss": 1.6494140625,
      "step": 19
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.27502211928367615,
      "learning_rate": 8.681980515339464e-06,
      "loss": 1.5244140625,
      "step": 20
    },
    {
      "epoch": 0.3620689655172414,
      "grad_norm": 0.20342087745666504,
      "learning_rate": 8.484051962083579e-06,
      "loss": 1.42333984375,
      "step": 21
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 0.21416571736335754,
      "learning_rate": 8.275234926828446e-06,
      "loss": 1.396484375,
      "step": 22
    },
    {
      "epoch": 0.39655172413793105,
      "grad_norm": 0.21919746696949005,
      "learning_rate": 8.056291360290202e-06,
      "loss": 1.42626953125,
      "step": 23
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.2595324218273163,
      "learning_rate": 7.828020163799455e-06,
      "loss": 1.7578125,
      "step": 24
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.2378513365983963,
      "learning_rate": 7.5912542741969585e-06,
      "loss": 1.453125,
      "step": 25
    },
    {
      "epoch": 0.43103448275862066,
      "eval_loss": 1.455078125,
      "eval_runtime": 2.5283,
      "eval_samples_per_second": 1.582,
      "eval_steps_per_second": 0.396,
      "step": 25
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 0.2067023515701294,
      "learning_rate": 7.346857624537407e-06,
      "loss": 1.52197265625,
      "step": 26
    },
    {
      "epoch": 0.46551724137931033,
      "grad_norm": 0.1973377913236618,
      "learning_rate": 7.095721991691411e-06,
      "loss": 1.3515625,
      "step": 27
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 0.2518433928489685,
      "learning_rate": 6.838763742348414e-06,
      "loss": 1.6005859375,
      "step": 28
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.24979768693447113,
      "learning_rate": 6.576920489294011e-06,
      "loss": 1.748046875,
      "step": 29
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.21077397465705872,
      "learning_rate": 6.311147670162576e-06,
      "loss": 1.2763671875,
      "step": 30
    },
    {
      "epoch": 0.5344827586206896,
      "grad_norm": 0.23148714005947113,
      "learning_rate": 6.042415061148954e-06,
      "loss": 1.5751953125,
      "step": 31
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.21228323876857758,
      "learning_rate": 5.771703238400288e-06,
      "loss": 1.53271484375,
      "step": 32
    },
    {
      "epoch": 0.5689655172413793,
      "grad_norm": 0.197456955909729,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.246337890625,
      "step": 33
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 0.20909880101680756,
      "learning_rate": 5.228296761599713e-06,
      "loss": 1.29736328125,
      "step": 34
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 0.20181578397750854,
      "learning_rate": 4.957584938851048e-06,
      "loss": 1.521484375,
      "step": 35
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 0.2005235105752945,
      "learning_rate": 4.6888523298374245e-06,
      "loss": 1.2978515625,
      "step": 36
    },
    {
      "epoch": 0.6206896551724138,
      "eval_loss": 1.435546875,
      "eval_runtime": 2.5169,
      "eval_samples_per_second": 1.589,
      "eval_steps_per_second": 0.397,
      "step": 36
    },
    {
      "epoch": 0.6379310344827587,
      "grad_norm": 0.21248990297317505,
      "learning_rate": 4.423079510705992e-06,
      "loss": 1.6171875,
      "step": 37
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 0.22428344190120697,
      "learning_rate": 4.1612362576515875e-06,
      "loss": 1.5224609375,
      "step": 38
    },
    {
      "epoch": 0.6724137931034483,
      "grad_norm": 0.2146124243736267,
      "learning_rate": 3.904278008308589e-06,
      "loss": 1.2802734375,
      "step": 39
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.19008564949035645,
      "learning_rate": 3.653142375462596e-06,
      "loss": 1.40625,
      "step": 40
    },
    {
      "epoch": 0.7068965517241379,
      "grad_norm": 0.18319071829319,
      "learning_rate": 3.408745725803042e-06,
      "loss": 1.484375,
      "step": 41
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 0.21213003993034363,
      "learning_rate": 3.1719798362005444e-06,
      "loss": 1.52490234375,
      "step": 42
    },
    {
      "epoch": 0.7413793103448276,
      "grad_norm": 0.21247462928295135,
      "learning_rate": 2.9437086397097996e-06,
      "loss": 1.4072265625,
      "step": 43
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 0.22428198158740997,
      "learning_rate": 2.7247650731715563e-06,
      "loss": 1.412109375,
      "step": 44
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 0.18434979021549225,
      "learning_rate": 2.515948037916423e-06,
      "loss": 1.41943359375,
      "step": 45
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 0.22083927690982819,
      "learning_rate": 2.3180194846605367e-06,
      "loss": 1.50927734375,
      "step": 46
    },
    {
      "epoch": 0.8103448275862069,
      "grad_norm": 0.21267378330230713,
      "learning_rate": 2.131701633230045e-06,
      "loss": 1.55126953125,
      "step": 47
    },
    {
      "epoch": 0.8103448275862069,
      "eval_loss": 1.421875,
      "eval_runtime": 2.527,
      "eval_samples_per_second": 1.583,
      "eval_steps_per_second": 0.396,
      "step": 47
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.18734264373779297,
      "learning_rate": 1.957674337259275e-06,
      "loss": 1.30615234375,
      "step": 48
    },
    {
      "epoch": 0.8448275862068966,
      "grad_norm": 0.18868029117584229,
      "learning_rate": 1.7965726034785466e-06,
      "loss": 1.3740234375,
      "step": 49
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.19361327588558197,
      "learning_rate": 1.648984274643487e-06,
      "loss": 1.40380859375,
      "step": 50
    },
    {
      "epoch": 0.8793103448275862,
      "grad_norm": 0.1973700374364853,
      "learning_rate": 1.515447884560556e-06,
      "loss": 1.3046875,
      "step": 51
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 0.2214573472738266,
      "learning_rate": 1.3964506930355947e-06,
      "loss": 1.58349609375,
      "step": 52
    },
    {
      "epoch": 0.9137931034482759,
      "grad_norm": 0.2411319464445114,
      "learning_rate": 1.292426907915634e-06,
      "loss": 1.6142578125,
      "step": 53
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 0.24840229749679565,
      "learning_rate": 1.203756100711545e-06,
      "loss": 1.728515625,
      "step": 54
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 0.20567460358142853,
      "learning_rate": 1.130761821582766e-06,
      "loss": 1.4443359375,
      "step": 55
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.1932135969400406,
      "learning_rate": 1.0737104187378543e-06,
      "loss": 1.4521484375,
      "step": 56
    },
    {
      "epoch": 0.9827586206896551,
      "grad_norm": 0.2393965870141983,
      "learning_rate": 1.0328100665587573e-06,
      "loss": 1.59716796875,
      "step": 57
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.19470740854740143,
      "learning_rate": 1.0082100059950713e-06,
      "loss": 1.38720703125,
      "step": 58
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4189453125,
      "eval_runtime": 2.523,
      "eval_samples_per_second": 1.585,
      "eval_steps_per_second": 0.396,
      "step": 58
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 58,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.0371028860744499e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}