{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.17873810231685638,
      "learning_rate": 8.695652173913044e-06,
      "loss": 0.9284,
      "step": 2
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.1875726729631424,
      "learning_rate": 1.739130434782609e-05,
      "loss": 0.9365,
      "step": 4
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.2115127593278885,
      "learning_rate": 2.608695652173913e-05,
      "loss": 0.9367,
      "step": 6
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.2282930463552475,
      "learning_rate": 3.478260869565218e-05,
      "loss": 0.8894,
      "step": 8
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.2383526861667633,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.9455,
      "step": 10
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.23653796315193176,
      "learning_rate": 5.217391304347826e-05,
      "loss": 1.0121,
      "step": 12
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.253218412399292,
      "learning_rate": 6.086956521739131e-05,
      "loss": 0.8756,
      "step": 14
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.24895112216472626,
      "learning_rate": 6.956521739130436e-05,
      "loss": 0.9091,
      "step": 16
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.2350614368915558,
      "learning_rate": 7.82608695652174e-05,
      "loss": 0.9091,
      "step": 18
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.27106258273124695,
      "learning_rate": 8.695652173913044e-05,
      "loss": 0.8018,
      "step": 20
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.3147624731063843,
      "learning_rate": 9.565217391304348e-05,
      "loss": 0.796,
      "step": 22
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.3592516779899597,
      "learning_rate": 9.999395316300748e-05,
      "loss": 0.8837,
      "step": 24
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.27557510137557983,
      "learning_rate": 9.994558724213054e-05,
      "loss": 0.8367,
      "step": 26
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.2757929861545563,
      "learning_rate": 9.984890219128146e-05,
      "loss": 0.8764,
      "step": 28
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.30082619190216064,
      "learning_rate": 9.970399154700263e-05,
      "loss": 0.8687,
      "step": 30
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.26034796237945557,
      "learning_rate": 9.951099550098349e-05,
      "loss": 0.8371,
      "step": 32
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.22807522118091583,
      "learning_rate": 9.927010076443407e-05,
      "loss": 0.8085,
      "step": 34
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.22343170642852783,
      "learning_rate": 9.898154038745408e-05,
      "loss": 0.8812,
      "step": 36
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.18960116803646088,
      "learning_rate": 9.864559353357187e-05,
      "loss": 0.7953,
      "step": 38
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.21037450432777405,
      "learning_rate": 9.826258520967178e-05,
      "loss": 0.7484,
      "step": 40
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.2212020456790924,
      "learning_rate": 9.783288595157098e-05,
      "loss": 0.7931,
      "step": 42
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.23480449616909027,
      "learning_rate": 9.735691146555002e-05,
      "loss": 0.8413,
      "step": 44
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 0.22327324748039246,
      "learning_rate": 9.683512222618377e-05,
      "loss": 0.8391,
      "step": 46
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.24856683611869812,
      "learning_rate": 9.626802303086208e-05,
      "loss": 0.7997,
      "step": 48
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2144002616405487,
      "learning_rate": 9.565616251143094e-05,
      "loss": 0.9146,
      "step": 50
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.24486525356769562,
      "learning_rate": 9.500013260342651e-05,
      "loss": 0.7813,
      "step": 52
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.23040799796581268,
      "learning_rate": 9.430056797341574e-05,
      "loss": 0.7282,
      "step": 54
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.24283307790756226,
      "learning_rate": 9.355814540499752e-05,
      "loss": 0.7598,
      "step": 56
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 0.25237399339675903,
      "learning_rate": 9.27735831440582e-05,
      "loss": 0.7959,
      "step": 58
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.2991330325603485,
      "learning_rate": 9.194764020391506e-05,
      "loss": 0.7853,
      "step": 60
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 0.27033334970474243,
      "learning_rate": 9.108111563102004e-05,
      "loss": 0.7553,
      "step": 62
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.32717347145080566,
      "learning_rate": 9.017484773193378e-05,
      "loss": 0.7809,
      "step": 64
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.29897943139076233,
      "learning_rate": 8.92297132623183e-05,
      "loss": 0.7628,
      "step": 66
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.30663371086120605,
      "learning_rate": 8.824662657873239e-05,
      "loss": 0.7763,
      "step": 68
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.28747016191482544,
      "learning_rate": 8.722653875405075e-05,
      "loss": 0.737,
      "step": 70
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.30916616320610046,
      "learning_rate": 8.617043665736249e-05,
      "loss": 0.7879,
      "step": 72
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 0.35312747955322266,
      "learning_rate": 8.507934199923884e-05,
      "loss": 0.7707,
      "step": 74
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.36939722299575806,
      "learning_rate": 8.39543103432943e-05,
      "loss": 0.727,
      "step": 76
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 0.3665863871574402,
      "learning_rate": 8.2796430084997e-05,
      "loss": 0.7193,
      "step": 78
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.34428849816322327,
      "learning_rate": 8.160682139871633e-05,
      "loss": 0.7573,
      "step": 80
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 0.3433472216129303,
      "learning_rate": 8.03866351540266e-05,
      "loss": 0.7711,
      "step": 82
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.3693158030509949,
      "learning_rate": 7.913705180231505e-05,
      "loss": 0.7741,
      "step": 84
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 0.4667452573776245,
      "learning_rate": 7.785928023477142e-05,
      "loss": 0.812,
      "step": 86
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.36592212319374084,
      "learning_rate": 7.655455661286376e-05,
      "loss": 0.7561,
      "step": 88
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4149788022041321,
      "learning_rate": 7.5224143172432e-05,
      "loss": 0.7797,
      "step": 90
    },
    {
      "epoch": 2.0444444444444443,
      "grad_norm": 0.39174893498420715,
      "learning_rate": 7.386932700255636e-05,
      "loss": 0.7651,
      "step": 92
    },
    {
      "epoch": 2.088888888888889,
      "grad_norm": 0.4016912877559662,
      "learning_rate": 7.24914188003818e-05,
      "loss": 0.741,
      "step": 94
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.46315836906433105,
      "learning_rate": 7.109175160310312e-05,
      "loss": 0.695,
      "step": 96
    },
    {
      "epoch": 2.1777777777777776,
      "grad_norm": 0.48870378732681274,
      "learning_rate": 6.967167949833763e-05,
      "loss": 0.7259,
      "step": 98
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.43603938817977905,
      "learning_rate": 6.823257631413276e-05,
      "loss": 0.7574,
      "step": 100
    },
    {
      "epoch": 2.2666666666666666,
      "grad_norm": 0.46362167596817017,
      "learning_rate": 6.677583428987625e-05,
      "loss": 0.6457,
      "step": 102
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 0.5170242786407471,
      "learning_rate": 6.530286272939437e-05,
      "loss": 0.6498,
      "step": 104
    },
    {
      "epoch": 2.3555555555555556,
      "grad_norm": 0.4572562575340271,
      "learning_rate": 6.381508663754153e-05,
      "loss": 0.6389,
      "step": 106
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.5652968287467957,
      "learning_rate": 6.231394534160008e-05,
      "loss": 0.7215,
      "step": 108
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.5415116548538208,
      "learning_rate": 6.0800891098824186e-05,
      "loss": 0.7096,
      "step": 110
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.493282675743103,
      "learning_rate": 5.9277387691474676e-05,
      "loss": 0.6736,
      "step": 112
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 0.6388583183288574,
      "learning_rate": 5.774490901070424e-05,
      "loss": 0.6875,
      "step": 114
    },
    {
      "epoch": 2.5777777777777775,
      "grad_norm": 0.4991196393966675,
      "learning_rate": 5.620493763066297e-05,
      "loss": 0.6023,
      "step": 116
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.5749160051345825,
      "learning_rate": 5.465896337420359e-05,
      "loss": 0.6356,
      "step": 118
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.6559845209121704,
      "learning_rate": 5.3108481871574036e-05,
      "loss": 0.6939,
      "step": 120
    },
    {
      "epoch": 2.7111111111111112,
      "grad_norm": 0.6793063879013062,
      "learning_rate": 5.155499311349185e-05,
      "loss": 0.6981,
      "step": 122
    },
    {
      "epoch": 2.7555555555555555,
      "grad_norm": 0.6073561310768127,
      "learning_rate": 5e-05,
      "loss": 0.6733,
      "step": 124
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.6620696187019348,
      "learning_rate": 4.844500688650816e-05,
      "loss": 0.6851,
      "step": 126
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.626446545124054,
      "learning_rate": 4.6891518128425976e-05,
      "loss": 0.654,
      "step": 128
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.6012407541275024,
      "learning_rate": 4.534103662579642e-05,
      "loss": 0.6303,
      "step": 130
    },
    {
      "epoch": 2.9333333333333336,
      "grad_norm": 0.6335547566413879,
      "learning_rate": 4.3795062369337034e-05,
      "loss": 0.5819,
      "step": 132
    },
    {
      "epoch": 2.977777777777778,
      "grad_norm": 0.6275166273117065,
      "learning_rate": 4.2255090989295764e-05,
      "loss": 0.6726,
      "step": 134
    },
    {
      "epoch": 3.022222222222222,
      "grad_norm": 0.545259416103363,
      "learning_rate": 4.0722612308525335e-05,
      "loss": 0.6621,
      "step": 136
    },
    {
      "epoch": 3.066666666666667,
      "grad_norm": 0.6598561406135559,
      "learning_rate": 3.919910890117584e-05,
      "loss": 0.5295,
      "step": 138
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.6240947842597961,
      "learning_rate": 3.7686054658399935e-05,
      "loss": 0.5466,
      "step": 140
    },
    {
      "epoch": 3.1555555555555554,
      "grad_norm": 0.682789146900177,
      "learning_rate": 3.618491336245849e-05,
      "loss": 0.5419,
      "step": 142
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.7448738217353821,
      "learning_rate": 3.469713727060564e-05,
      "loss": 0.6171,
      "step": 144
    },
    {
      "epoch": 3.2444444444444445,
      "grad_norm": 0.7555476427078247,
      "learning_rate": 3.3224165710123756e-05,
      "loss": 0.5628,
      "step": 146
    },
    {
      "epoch": 3.2888888888888888,
      "grad_norm": 0.7862750887870789,
      "learning_rate": 3.176742368586725e-05,
      "loss": 0.5923,
      "step": 148
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.7729607224464417,
      "learning_rate": 3.032832050166239e-05,
      "loss": 0.5308,
      "step": 150
    },
    {
      "epoch": 3.3777777777777778,
      "grad_norm": 0.7676399350166321,
      "learning_rate": 2.890824839689689e-05,
      "loss": 0.6444,
      "step": 152
    },
    {
      "epoch": 3.422222222222222,
      "grad_norm": 0.8251731991767883,
      "learning_rate": 2.750858119961821e-05,
      "loss": 0.6573,
      "step": 154
    },
    {
      "epoch": 3.466666666666667,
      "grad_norm": 0.8169701099395752,
      "learning_rate": 2.613067299744364e-05,
      "loss": 0.582,
      "step": 156
    },
    {
      "epoch": 3.511111111111111,
      "grad_norm": 0.7788083553314209,
      "learning_rate": 2.4775856827568016e-05,
      "loss": 0.6335,
      "step": 158
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.8565711379051208,
      "learning_rate": 2.3445443387136244e-05,
      "loss": 0.508,
      "step": 160
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.8271569609642029,
      "learning_rate": 2.2140719765228584e-05,
      "loss": 0.5991,
      "step": 162
    },
    {
      "epoch": 3.6444444444444444,
      "grad_norm": 0.812567412853241,
      "learning_rate": 2.0862948197684955e-05,
      "loss": 0.5808,
      "step": 164
    },
    {
      "epoch": 3.688888888888889,
      "grad_norm": 0.7940819263458252,
      "learning_rate": 1.961336484597343e-05,
      "loss": 0.5703,
      "step": 166
    },
    {
      "epoch": 3.7333333333333334,
      "grad_norm": 0.9031268358230591,
      "learning_rate": 1.8393178601283683e-05,
      "loss": 0.5002,
      "step": 168
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.8260697722434998,
      "learning_rate": 1.7203569915003005e-05,
      "loss": 0.5269,
      "step": 170
    },
    {
      "epoch": 3.822222222222222,
      "grad_norm": 0.9412121772766113,
      "learning_rate": 1.6045689656705716e-05,
      "loss": 0.4902,
      "step": 172
    },
    {
      "epoch": 3.8666666666666667,
      "grad_norm": 0.9131683707237244,
      "learning_rate": 1.4920658000761174e-05,
      "loss": 0.6185,
      "step": 174
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.7923269271850586,
      "learning_rate": 1.3829563342637513e-05,
      "loss": 0.537,
      "step": 176
    },
    {
      "epoch": 3.9555555555555557,
      "grad_norm": 0.8013989329338074,
      "learning_rate": 1.2773461245949247e-05,
      "loss": 0.5637,
      "step": 178
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7401474118232727,
      "learning_rate": 1.1753373421267621e-05,
      "loss": 0.5124,
      "step": 180
    },
    {
      "epoch": 4.044444444444444,
      "grad_norm": 0.8890312910079956,
      "learning_rate": 1.0770286737681701e-05,
      "loss": 0.5488,
      "step": 182
    },
    {
      "epoch": 4.088888888888889,
      "grad_norm": 0.858996570110321,
      "learning_rate": 9.825152268066213e-06,
      "loss": 0.4998,
      "step": 184
    },
    {
      "epoch": 4.133333333333334,
      "grad_norm": 0.755382239818573,
      "learning_rate": 8.91888436897997e-06,
      "loss": 0.4892,
      "step": 186
    },
    {
      "epoch": 4.177777777777778,
      "grad_norm": 0.8359836935997009,
      "learning_rate": 8.052359796084951e-06,
      "loss": 0.5365,
      "step": 188
    },
    {
      "epoch": 4.222222222222222,
      "grad_norm": 0.8235160112380981,
      "learning_rate": 7.226416855941814e-06,
      "loss": 0.4963,
      "step": 190
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.9951562881469727,
      "learning_rate": 6.441854595002477e-06,
      "loss": 0.5367,
      "step": 192
    },
    {
      "epoch": 4.311111111111111,
      "grad_norm": 0.907408595085144,
      "learning_rate": 5.699432026584267e-06,
      "loss": 0.5051,
      "step": 194
    },
    {
      "epoch": 4.355555555555555,
      "grad_norm": 0.9453915357589722,
      "learning_rate": 4.999867396573499e-06,
      "loss": 0.5326,
      "step": 196
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.8306211829185486,
      "learning_rate": 4.343837488569058e-06,
      "loss": 0.4549,
      "step": 198
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.9665538668632507,
      "learning_rate": 3.731976969137929e-06,
      "loss": 0.4968,
      "step": 200
    },
    {
      "epoch": 4.488888888888889,
      "grad_norm": 0.9233301281929016,
      "learning_rate": 3.1648777738162494e-06,
      "loss": 0.4623,
      "step": 202
    },
    {
      "epoch": 4.533333333333333,
      "grad_norm": 0.8156710267066956,
      "learning_rate": 2.6430885344499946e-06,
      "loss": 0.4445,
      "step": 204
    },
    {
      "epoch": 4.5777777777777775,
      "grad_norm": 0.8379063010215759,
      "learning_rate": 2.1671140484290142e-06,
      "loss": 0.4678,
      "step": 206
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.8422232866287231,
      "learning_rate": 1.7374147903282178e-06,
      "loss": 0.5377,
      "step": 208
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.9653432965278625,
      "learning_rate": 1.3544064664281265e-06,
      "loss": 0.5819,
      "step": 210
    },
    {
      "epoch": 4.711111111111111,
      "grad_norm": 0.8152110576629639,
      "learning_rate": 1.0184596125459135e-06,
      "loss": 0.494,
      "step": 212
    },
    {
      "epoch": 4.7555555555555555,
      "grad_norm": 0.9850694537162781,
      "learning_rate": 7.29899235565934e-07,
      "loss": 0.4983,
      "step": 214
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.9584403038024902,
      "learning_rate": 4.890044990165321e-07,
      "loss": 0.5186,
      "step": 216
    },
    {
      "epoch": 4.844444444444444,
      "grad_norm": 0.948579728603363,
      "learning_rate": 2.9600845299737056e-07,
      "loss": 0.5044,
      "step": 218
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 0.8661581873893738,
      "learning_rate": 1.5109780871853663e-07,
      "loss": 0.5062,
      "step": 220
    },
    {
      "epoch": 4.933333333333334,
      "grad_norm": 0.9714407324790955,
      "learning_rate": 5.4412757869459763e-08,
      "loss": 0.5391,
      "step": 222
    },
    {
      "epoch": 4.977777777777778,
      "grad_norm": 0.7409553527832031,
      "learning_rate": 6.04683699252373e-09,
      "loss": 0.5243,
      "step": 224
    },
    {
      "epoch": 5.0,
      "step": 225,
      "total_flos": 8.831352737326694e+16,
      "train_loss": 0.6794352424144745,
      "train_runtime": 806.654,
      "train_samples_per_second": 8.926,
      "train_steps_per_second": 0.279
    }
  ],
  "logging_steps": 2,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.831352737326694e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}