{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.201765447667087,
  "eval_steps": 100,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025220680958385876,
      "grad_norm": 25.350475311279297,
      "learning_rate": 0.0,
      "loss": 2.5568,
      "step": 1
    },
    {
      "epoch": 0.005044136191677175,
      "grad_norm": 24.538068771362305,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.7748,
      "step": 2
    },
    {
      "epoch": 0.007566204287515763,
      "grad_norm": 23.780784606933594,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.5911,
      "step": 3
    },
    {
      "epoch": 0.01008827238335435,
      "grad_norm": 24.780380249023438,
      "learning_rate": 1.2e-05,
      "loss": 2.8427,
      "step": 4
    },
    {
      "epoch": 0.012610340479192938,
      "grad_norm": 22.699949264526367,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.709,
      "step": 5
    },
    {
      "epoch": 0.015132408575031526,
      "grad_norm": 22.106008529663086,
      "learning_rate": 2e-05,
      "loss": 2.5854,
      "step": 6
    },
    {
      "epoch": 0.017654476670870115,
      "grad_norm": 22.497045516967773,
      "learning_rate": 1.9948979591836737e-05,
      "loss": 2.5427,
      "step": 7
    },
    {
      "epoch": 0.0201765447667087,
      "grad_norm": 27.103275299072266,
      "learning_rate": 1.9897959183673473e-05,
      "loss": 2.6599,
      "step": 8
    },
    {
      "epoch": 0.02269861286254729,
      "grad_norm": 21.081985473632812,
      "learning_rate": 1.9846938775510205e-05,
      "loss": 2.5145,
      "step": 9
    },
    {
      "epoch": 0.025220680958385876,
      "grad_norm": 25.964981079101562,
      "learning_rate": 1.979591836734694e-05,
      "loss": 2.4247,
      "step": 10
    },
    {
      "epoch": 0.027742749054224466,
      "grad_norm": 25.353195190429688,
      "learning_rate": 1.9744897959183677e-05,
      "loss": 2.5092,
      "step": 11
    },
    {
      "epoch": 0.03026481715006305,
      "grad_norm": 18.94191551208496,
      "learning_rate": 1.969387755102041e-05,
      "loss": 2.4335,
      "step": 12
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 23.60140037536621,
      "learning_rate": 1.9642857142857145e-05,
      "loss": 2.544,
      "step": 13
    },
    {
      "epoch": 0.03530895334174023,
      "grad_norm": 24.298965454101562,
      "learning_rate": 1.9591836734693877e-05,
      "loss": 2.4987,
      "step": 14
    },
    {
      "epoch": 0.03783102143757881,
      "grad_norm": 20.745506286621094,
      "learning_rate": 1.9540816326530613e-05,
      "loss": 2.4985,
      "step": 15
    },
    {
      "epoch": 0.0403530895334174,
      "grad_norm": 22.54330062866211,
      "learning_rate": 1.948979591836735e-05,
      "loss": 2.6892,
      "step": 16
    },
    {
      "epoch": 0.04287515762925599,
      "grad_norm": 21.46229362487793,
      "learning_rate": 1.9438775510204085e-05,
      "loss": 2.3998,
      "step": 17
    },
    {
      "epoch": 0.04539722572509458,
      "grad_norm": 20.54530143737793,
      "learning_rate": 1.9387755102040817e-05,
      "loss": 2.4244,
      "step": 18
    },
    {
      "epoch": 0.04791929382093316,
      "grad_norm": 18.8839111328125,
      "learning_rate": 1.9336734693877553e-05,
      "loss": 2.3911,
      "step": 19
    },
    {
      "epoch": 0.05044136191677175,
      "grad_norm": 16.924652099609375,
      "learning_rate": 1.928571428571429e-05,
      "loss": 2.3588,
      "step": 20
    },
    {
      "epoch": 0.05296343001261034,
      "grad_norm": 16.996627807617188,
      "learning_rate": 1.9234693877551024e-05,
      "loss": 2.3727,
      "step": 21
    },
    {
      "epoch": 0.05548549810844893,
      "grad_norm": 18.584613800048828,
      "learning_rate": 1.9183673469387756e-05,
      "loss": 2.2974,
      "step": 22
    },
    {
      "epoch": 0.058007566204287514,
      "grad_norm": 14.309200286865234,
      "learning_rate": 1.9132653061224492e-05,
      "loss": 2.4843,
      "step": 23
    },
    {
      "epoch": 0.0605296343001261,
      "grad_norm": 15.074164390563965,
      "learning_rate": 1.9081632653061225e-05,
      "loss": 2.4043,
      "step": 24
    },
    {
      "epoch": 0.06305170239596469,
      "grad_norm": 13.610542297363281,
      "learning_rate": 1.903061224489796e-05,
      "loss": 2.3762,
      "step": 25
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 15.666613578796387,
      "learning_rate": 1.8979591836734696e-05,
      "loss": 2.3249,
      "step": 26
    },
    {
      "epoch": 0.06809583858764187,
      "grad_norm": 14.475164413452148,
      "learning_rate": 1.892857142857143e-05,
      "loss": 2.3317,
      "step": 27
    },
    {
      "epoch": 0.07061790668348046,
      "grad_norm": 16.231687545776367,
      "learning_rate": 1.8877551020408164e-05,
      "loss": 2.5064,
      "step": 28
    },
    {
      "epoch": 0.07313997477931904,
      "grad_norm": 16.8968563079834,
      "learning_rate": 1.88265306122449e-05,
      "loss": 2.3932,
      "step": 29
    },
    {
      "epoch": 0.07566204287515763,
      "grad_norm": 17.74305534362793,
      "learning_rate": 1.8775510204081636e-05,
      "loss": 2.3329,
      "step": 30
    },
    {
      "epoch": 0.07818411097099622,
      "grad_norm": 16.41620445251465,
      "learning_rate": 1.8724489795918368e-05,
      "loss": 2.3982,
      "step": 31
    },
    {
      "epoch": 0.0807061790668348,
      "grad_norm": 17.965959548950195,
      "learning_rate": 1.8673469387755104e-05,
      "loss": 2.4227,
      "step": 32
    },
    {
      "epoch": 0.0832282471626734,
      "grad_norm": 19.92589569091797,
      "learning_rate": 1.862244897959184e-05,
      "loss": 2.5255,
      "step": 33
    },
    {
      "epoch": 0.08575031525851198,
      "grad_norm": 20.62932586669922,
      "learning_rate": 1.8571428571428575e-05,
      "loss": 2.1816,
      "step": 34
    },
    {
      "epoch": 0.08827238335435057,
      "grad_norm": 18.360614776611328,
      "learning_rate": 1.8520408163265307e-05,
      "loss": 2.2827,
      "step": 35
    },
    {
      "epoch": 0.09079445145018916,
      "grad_norm": 19.199546813964844,
      "learning_rate": 1.8469387755102043e-05,
      "loss": 2.1498,
      "step": 36
    },
    {
      "epoch": 0.09331651954602774,
      "grad_norm": 22.727521896362305,
      "learning_rate": 1.8418367346938776e-05,
      "loss": 2.3811,
      "step": 37
    },
    {
      "epoch": 0.09583858764186633,
      "grad_norm": 19.80649757385254,
      "learning_rate": 1.836734693877551e-05,
      "loss": 2.2342,
      "step": 38
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 22.24563217163086,
      "learning_rate": 1.8316326530612247e-05,
      "loss": 2.2287,
      "step": 39
    },
    {
      "epoch": 0.1008827238335435,
      "grad_norm": 25.384042739868164,
      "learning_rate": 1.826530612244898e-05,
      "loss": 2.1259,
      "step": 40
    },
    {
      "epoch": 0.1034047919293821,
      "grad_norm": 23.417089462280273,
      "learning_rate": 1.8214285714285715e-05,
      "loss": 2.0858,
      "step": 41
    },
    {
      "epoch": 0.10592686002522068,
      "grad_norm": 27.639497756958008,
      "learning_rate": 1.816326530612245e-05,
      "loss": 2.2243,
      "step": 42
    },
    {
      "epoch": 0.10844892812105927,
      "grad_norm": 27.390850067138672,
      "learning_rate": 1.8112244897959187e-05,
      "loss": 2.1314,
      "step": 43
    },
    {
      "epoch": 0.11097099621689786,
      "grad_norm": 27.956937789916992,
      "learning_rate": 1.806122448979592e-05,
      "loss": 2.1755,
      "step": 44
    },
    {
      "epoch": 0.11349306431273644,
      "grad_norm": 32.09632873535156,
      "learning_rate": 1.8010204081632655e-05,
      "loss": 2.2365,
      "step": 45
    },
    {
      "epoch": 0.11601513240857503,
      "grad_norm": 33.84647750854492,
      "learning_rate": 1.795918367346939e-05,
      "loss": 2.1671,
      "step": 46
    },
    {
      "epoch": 0.11853720050441362,
      "grad_norm": 32.027130126953125,
      "learning_rate": 1.7908163265306123e-05,
      "loss": 2.09,
      "step": 47
    },
    {
      "epoch": 0.1210592686002522,
      "grad_norm": 35.423587799072266,
      "learning_rate": 1.785714285714286e-05,
      "loss": 2.2479,
      "step": 48
    },
    {
      "epoch": 0.1235813366960908,
      "grad_norm": 31.041240692138672,
      "learning_rate": 1.780612244897959e-05,
      "loss": 1.9687,
      "step": 49
    },
    {
      "epoch": 0.12610340479192939,
      "grad_norm": 28.790103912353516,
      "learning_rate": 1.7755102040816327e-05,
      "loss": 2.1428,
      "step": 50
    },
    {
      "epoch": 0.12862547288776796,
      "grad_norm": 25.089313507080078,
      "learning_rate": 1.7704081632653062e-05,
      "loss": 2.0673,
      "step": 51
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 26.493867874145508,
      "learning_rate": 1.7653061224489798e-05,
      "loss": 2.0814,
      "step": 52
    },
    {
      "epoch": 0.13366960907944514,
      "grad_norm": 19.993173599243164,
      "learning_rate": 1.760204081632653e-05,
      "loss": 2.005,
      "step": 53
    },
    {
      "epoch": 0.13619167717528374,
      "grad_norm": 21.89765167236328,
      "learning_rate": 1.7551020408163266e-05,
      "loss": 2.2262,
      "step": 54
    },
    {
      "epoch": 0.13871374527112232,
      "grad_norm": 23.22844123840332,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 2.0208,
      "step": 55
    },
    {
      "epoch": 0.14123581336696092,
      "grad_norm": 15.864526748657227,
      "learning_rate": 1.7448979591836738e-05,
      "loss": 2.0153,
      "step": 56
    },
    {
      "epoch": 0.1437578814627995,
      "grad_norm": 21.451187133789062,
      "learning_rate": 1.7397959183673473e-05,
      "loss": 2.1386,
      "step": 57
    },
    {
      "epoch": 0.14627994955863807,
      "grad_norm": 18.089811325073242,
      "learning_rate": 1.7346938775510206e-05,
      "loss": 1.9517,
      "step": 58
    },
    {
      "epoch": 0.14880201765447668,
      "grad_norm": 24.029157638549805,
      "learning_rate": 1.729591836734694e-05,
      "loss": 1.9719,
      "step": 59
    },
    {
      "epoch": 0.15132408575031525,
      "grad_norm": 18.722776412963867,
      "learning_rate": 1.7244897959183674e-05,
      "loss": 2.0623,
      "step": 60
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 20.211933135986328,
      "learning_rate": 1.719387755102041e-05,
      "loss": 2.0081,
      "step": 61
    },
    {
      "epoch": 0.15636822194199243,
      "grad_norm": 17.61188507080078,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 1.8484,
      "step": 62
    },
    {
      "epoch": 0.15889029003783103,
      "grad_norm": 20.118955612182617,
      "learning_rate": 1.7091836734693878e-05,
      "loss": 2.0799,
      "step": 63
    },
    {
      "epoch": 0.1614123581336696,
      "grad_norm": 17.271841049194336,
      "learning_rate": 1.7040816326530613e-05,
      "loss": 1.9832,
      "step": 64
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 19.521392822265625,
      "learning_rate": 1.698979591836735e-05,
      "loss": 1.9129,
      "step": 65
    },
    {
      "epoch": 0.1664564943253468,
      "grad_norm": 22.660900115966797,
      "learning_rate": 1.6938775510204085e-05,
      "loss": 2.118,
      "step": 66
    },
    {
      "epoch": 0.16897856242118536,
      "grad_norm": 17.332427978515625,
      "learning_rate": 1.6887755102040817e-05,
      "loss": 1.9632,
      "step": 67
    },
    {
      "epoch": 0.17150063051702397,
      "grad_norm": 22.42765998840332,
      "learning_rate": 1.6836734693877553e-05,
      "loss": 1.954,
      "step": 68
    },
    {
      "epoch": 0.17402269861286254,
      "grad_norm": 23.6208553314209,
      "learning_rate": 1.678571428571429e-05,
      "loss": 1.9917,
      "step": 69
    },
    {
      "epoch": 0.17654476670870115,
      "grad_norm": 19.78505516052246,
      "learning_rate": 1.673469387755102e-05,
      "loss": 1.7964,
      "step": 70
    },
    {
      "epoch": 0.17906683480453972,
      "grad_norm": 19.453041076660156,
      "learning_rate": 1.6683673469387757e-05,
      "loss": 1.9587,
      "step": 71
    },
    {
      "epoch": 0.18158890290037832,
      "grad_norm": 24.731407165527344,
      "learning_rate": 1.6632653061224492e-05,
      "loss": 1.9945,
      "step": 72
    },
    {
      "epoch": 0.1841109709962169,
      "grad_norm": 20.977611541748047,
      "learning_rate": 1.6581632653061225e-05,
      "loss": 2.0617,
      "step": 73
    },
    {
      "epoch": 0.18663303909205547,
      "grad_norm": 22.959585189819336,
      "learning_rate": 1.653061224489796e-05,
      "loss": 1.98,
      "step": 74
    },
    {
      "epoch": 0.18915510718789408,
      "grad_norm": 21.952653884887695,
      "learning_rate": 1.6479591836734696e-05,
      "loss": 2.1094,
      "step": 75
    },
    {
      "epoch": 0.19167717528373265,
      "grad_norm": 22.320383071899414,
      "learning_rate": 1.642857142857143e-05,
      "loss": 1.8418,
      "step": 76
    },
    {
      "epoch": 0.19419924337957126,
      "grad_norm": 24.375411987304688,
      "learning_rate": 1.6377551020408164e-05,
      "loss": 1.8428,
      "step": 77
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 19.64323616027832,
      "learning_rate": 1.63265306122449e-05,
      "loss": 1.9194,
      "step": 78
    },
    {
      "epoch": 0.19924337957124844,
      "grad_norm": 22.459064483642578,
      "learning_rate": 1.6275510204081636e-05,
      "loss": 1.6649,
      "step": 79
    },
    {
      "epoch": 0.201765447667087,
      "grad_norm": 36.789764404296875,
      "learning_rate": 1.6224489795918368e-05,
      "loss": 2.0131,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 397,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1160267070111744.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}