{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 12,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 7.683346271514893,
      "learning_rate": 0.0,
      "loss": 2.7236328125,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 8.30794906616211,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.80615234375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 8.94153881072998,
      "learning_rate": 2.857142857142857e-05,
      "loss": 3.1728515625,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 7.938409328460693,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 2.9375,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.4468631744384766,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.834716796875,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.7402069568634033,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.4140625,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.0219361782073975,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.1376953125,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.2759617567062378,
      "learning_rate": 0.0001,
      "loss": 0.978515625,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.3914451599121094,
      "learning_rate": 9.992920667580176e-05,
      "loss": 0.91015625,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.0541131496429443,
      "learning_rate": 9.971704944519594e-05,
      "loss": 0.894287109375,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.7295523285865784,
      "learning_rate": 9.936419583332062e-05,
      "loss": 0.747314453125,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.9586805701255798,
      "learning_rate": 9.887175604818206e-05,
      "loss": 0.73583984375,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.9399129748344421,
      "learning_rate": 9.82412794875295e-05,
      "loss": 0.91162109375,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5930038690567017,
      "learning_rate": 9.747474986387654e-05,
      "loss": 0.665283203125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.6943517327308655,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.68115234375,
      "step": 15
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 1.125,
      "eval_runtime": 3.7655,
      "eval_samples_per_second": 0.266,
      "eval_steps_per_second": 0.266,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.6625951528549194,
      "learning_rate": 9.554359905560886e-05,
      "loss": 0.820556640625,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.7600706219673157,
      "learning_rate": 9.438505398589392e-05,
      "loss": 0.614013671875,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.5712336301803589,
      "learning_rate": 9.310258896527278e-05,
      "loss": 0.68603515625,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.6201907992362976,
      "learning_rate": 9.17002391031667e-05,
      "loss": 0.6240234375,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.6295406818389893,
      "learning_rate": 9.018241671106134e-05,
      "loss": 0.636962890625,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7266039252281189,
      "learning_rate": 8.855389741974244e-05,
      "loss": 0.641845703125,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.6056920289993286,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.50732421875,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.5053836107254028,
      "learning_rate": 8.498559600784018e-05,
      "loss": 0.4849853515625,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.5425382256507874,
      "learning_rate": 8.305704108364301e-05,
      "loss": 0.560791015625,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.6988992691040039,
      "learning_rate": 8.104020832809127e-05,
      "loss": 0.66650390625,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.5177556872367859,
      "learning_rate": 7.894144344319014e-05,
      "loss": 1.3883743286132812,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.6992603540420532,
      "learning_rate": 7.67673499197358e-05,
      "loss": 0.667724609375,
      "step": 27
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 1.0234375,
      "eval_runtime": 3.7364,
      "eval_samples_per_second": 0.268,
      "eval_steps_per_second": 0.268,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.5518877506256104,
      "learning_rate": 7.452476826029011e-05,
      "loss": 0.6201171875,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.48834937810897827,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.59765625,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7777575254440308,
      "learning_rate": 6.986255778798253e-05,
      "loss": 0.549560546875,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.5613299012184143,
      "learning_rate": 6.745759801411822e-05,
      "loss": 0.591552734375,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.48722875118255615,
      "learning_rate": 6.501344202803414e-05,
      "loss": 0.4981689453125,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.45788365602493286,
      "learning_rate": 6.253778004871315e-05,
      "loss": 0.47705078125,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.5666241645812988,
      "learning_rate": 6.003840142464886e-05,
      "loss": 0.628173828125,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.49418237805366516,
      "learning_rate": 5.752317012567363e-05,
      "loss": 0.474609375,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.6069824695587158,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.467041015625,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.5141736268997192,
      "learning_rate": 5.247682987432637e-05,
      "loss": 0.596435546875,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.49380624294281006,
      "learning_rate": 4.9961598575351155e-05,
      "loss": 0.4202880859375,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.48107779026031494,
      "learning_rate": 4.7462219951286867e-05,
      "loss": 0.49169921875,
      "step": 39
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 0.99609375,
      "eval_runtime": 3.7334,
      "eval_samples_per_second": 0.268,
      "eval_steps_per_second": 0.268,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.4944271743297577,
      "learning_rate": 4.498655797196586e-05,
      "loss": 0.435791015625,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.46663668751716614,
      "learning_rate": 4.2542401985881784e-05,
      "loss": 0.45556640625,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5421565175056458,
      "learning_rate": 4.01374422120175e-05,
      "loss": 0.4136962890625,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.47634458541870117,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.3116455078125,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.4998021125793457,
      "learning_rate": 3.547523173970989e-05,
      "loss": 0.36248779296875,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.6161043643951416,
      "learning_rate": 3.323265008026421e-05,
      "loss": 0.395263671875,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.5737324357032776,
      "learning_rate": 3.105855655680986e-05,
      "loss": 0.4962158203125,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.45135700702667236,
      "learning_rate": 2.8959791671908742e-05,
      "loss": 1.2419204711914062,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.6822405457496643,
      "learning_rate": 2.6942958916356998e-05,
      "loss": 0.49658203125,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.6327748894691467,
      "learning_rate": 2.501440399215983e-05,
      "loss": 0.4644775390625,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.5168265104293823,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.458740234375,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.5705485939979553,
      "learning_rate": 2.144610258025755e-05,
      "loss": 0.402587890625,
      "step": 51
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 0.99609375,
      "eval_runtime": 3.7308,
      "eval_samples_per_second": 0.268,
      "eval_steps_per_second": 0.268,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.616422176361084,
      "learning_rate": 1.981758328893866e-05,
      "loss": 0.4619140625,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.5285511612892151,
      "learning_rate": 1.8299760896833295e-05,
      "loss": 0.39013671875,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.5321851968765259,
      "learning_rate": 1.6897411034727218e-05,
      "loss": 0.36767578125,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.5941992402076721,
      "learning_rate": 1.5614946014106085e-05,
      "loss": 0.4990234375,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.5202521085739136,
      "learning_rate": 1.4456400944391146e-05,
      "loss": 0.3797607421875,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.6072654724121094,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.375,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.6598243713378906,
      "learning_rate": 1.252525013612346e-05,
      "loss": 0.496337890625,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.5702089071273804,
      "learning_rate": 1.1758720512470523e-05,
      "loss": 0.3341064453125,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.550778329372406,
      "learning_rate": 1.1128243951817937e-05,
      "loss": 0.404296875,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.5884420871734619,
      "learning_rate": 1.0635804166679386e-05,
      "loss": 0.3558349609375,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.5809072256088257,
      "learning_rate": 1.0282950554804085e-05,
      "loss": 0.376708984375,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6065093874931335,
      "learning_rate": 1.0070793324198253e-05,
      "loss": 0.31134033203125,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.984375,
      "eval_runtime": 3.7577,
      "eval_samples_per_second": 0.266,
      "eval_steps_per_second": 0.266,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.0104242682923581e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}