{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003244751614263928,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.244751614263928e-05,
      "grad_norm": 0.699952244758606,
      "learning_rate": 1e-05,
      "loss": 1.0141,
      "step": 1
    },
    {
      "epoch": 3.244751614263928e-05,
      "eval_loss": 1.2364516258239746,
      "eval_runtime": 410.7977,
      "eval_samples_per_second": 63.177,
      "eval_steps_per_second": 7.899,
      "step": 1
    },
    {
      "epoch": 6.489503228527856e-05,
      "grad_norm": 0.5059106945991516,
      "learning_rate": 2e-05,
      "loss": 1.173,
      "step": 2
    },
    {
      "epoch": 9.734254842791784e-05,
      "grad_norm": 0.721911609172821,
      "learning_rate": 3e-05,
      "loss": 1.2592,
      "step": 3
    },
    {
      "epoch": 0.00012979006457055711,
      "grad_norm": 0.7691875696182251,
      "learning_rate": 4e-05,
      "loss": 1.2255,
      "step": 4
    },
    {
      "epoch": 0.00016223758071319641,
      "grad_norm": 0.6363957524299622,
      "learning_rate": 5e-05,
      "loss": 1.2921,
      "step": 5
    },
    {
      "epoch": 0.00019468509685583569,
      "grad_norm": 0.8589330315589905,
      "learning_rate": 6e-05,
      "loss": 1.0931,
      "step": 6
    },
    {
      "epoch": 0.00022713261299847496,
      "grad_norm": 0.7455472350120544,
      "learning_rate": 7e-05,
      "loss": 1.3303,
      "step": 7
    },
    {
      "epoch": 0.00025958012914111423,
      "grad_norm": 0.6809628009796143,
      "learning_rate": 8e-05,
      "loss": 1.1682,
      "step": 8
    },
    {
      "epoch": 0.0002920276452837535,
      "grad_norm": 0.5815722346305847,
      "learning_rate": 9e-05,
      "loss": 1.2131,
      "step": 9
    },
    {
      "epoch": 0.0002920276452837535,
      "eval_loss": 1.2085680961608887,
      "eval_runtime": 409.6889,
      "eval_samples_per_second": 63.348,
      "eval_steps_per_second": 7.921,
      "step": 9
    },
    {
      "epoch": 0.00032447516142639283,
      "grad_norm": 0.48401424288749695,
      "learning_rate": 0.0001,
      "loss": 1.1914,
      "step": 10
    },
    {
      "epoch": 0.0003569226775690321,
      "grad_norm": 0.7972922325134277,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.3705,
      "step": 11
    },
    {
      "epoch": 0.00038937019371167137,
      "grad_norm": 0.7923889756202698,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.187,
      "step": 12
    },
    {
      "epoch": 0.00042181770985431064,
      "grad_norm": 0.7378607988357544,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1752,
      "step": 13
    },
    {
      "epoch": 0.0004542652259969499,
      "grad_norm": 0.6670899987220764,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2382,
      "step": 14
    },
    {
      "epoch": 0.0004867127421395892,
      "grad_norm": 0.5493435859680176,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0741,
      "step": 15
    },
    {
      "epoch": 0.0005191602582822285,
      "grad_norm": 0.6642765402793884,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.273,
      "step": 16
    },
    {
      "epoch": 0.0005516077744248677,
      "grad_norm": 0.7158033847808838,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.0416,
      "step": 17
    },
    {
      "epoch": 0.000584055290567507,
      "grad_norm": 0.6141757965087891,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1888,
      "step": 18
    },
    {
      "epoch": 0.000584055290567507,
      "eval_loss": 1.1528652906417847,
      "eval_runtime": 409.6904,
      "eval_samples_per_second": 63.348,
      "eval_steps_per_second": 7.921,
      "step": 18
    },
    {
      "epoch": 0.0006165028067101464,
      "grad_norm": 0.7109853029251099,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.09,
      "step": 19
    },
    {
      "epoch": 0.0006489503228527857,
      "grad_norm": 0.6954298615455627,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0063,
      "step": 20
    },
    {
      "epoch": 0.0006813978389954249,
      "grad_norm": 0.7887369990348816,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0689,
      "step": 21
    },
    {
      "epoch": 0.0007138453551380642,
      "grad_norm": 0.9078826308250427,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0223,
      "step": 22
    },
    {
      "epoch": 0.0007462928712807035,
      "grad_norm": 0.8368735313415527,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.2175,
      "step": 23
    },
    {
      "epoch": 0.0007787403874233427,
      "grad_norm": 0.6735103726387024,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.2283,
      "step": 24
    },
    {
      "epoch": 0.000811187903565982,
      "grad_norm": 0.6207486391067505,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0345,
      "step": 25
    },
    {
      "epoch": 0.0008436354197086213,
      "grad_norm": 0.6223241090774536,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.0311,
      "step": 26
    },
    {
      "epoch": 0.0008760829358512606,
      "grad_norm": 0.7213761806488037,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.0735,
      "step": 27
    },
    {
      "epoch": 0.0008760829358512606,
      "eval_loss": 1.129144310951233,
      "eval_runtime": 409.5892,
      "eval_samples_per_second": 63.363,
      "eval_steps_per_second": 7.923,
      "step": 27
    },
    {
      "epoch": 0.0009085304519938998,
      "grad_norm": 0.7402194142341614,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0728,
      "step": 28
    },
    {
      "epoch": 0.0009409779681365391,
      "grad_norm": 0.7021007537841797,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1606,
      "step": 29
    },
    {
      "epoch": 0.0009734254842791784,
      "grad_norm": 0.7063369750976562,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1922,
      "step": 30
    },
    {
      "epoch": 0.0010058730004218178,
      "grad_norm": 0.7353460192680359,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.266,
      "step": 31
    },
    {
      "epoch": 0.001038320516564457,
      "grad_norm": 0.6535232067108154,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1358,
      "step": 32
    },
    {
      "epoch": 0.0010707680327070963,
      "grad_norm": 0.7119964957237244,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.193,
      "step": 33
    },
    {
      "epoch": 0.0011032155488497355,
      "grad_norm": 0.7616000175476074,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.225,
      "step": 34
    },
    {
      "epoch": 0.0011356630649923748,
      "grad_norm": 0.6312659382820129,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0475,
      "step": 35
    },
    {
      "epoch": 0.001168110581135014,
      "grad_norm": 0.9175184369087219,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.0903,
      "step": 36
    },
    {
      "epoch": 0.001168110581135014,
      "eval_loss": 1.1155873537063599,
      "eval_runtime": 410.7403,
      "eval_samples_per_second": 63.186,
      "eval_steps_per_second": 7.9,
      "step": 36
    },
    {
      "epoch": 0.0012005580972776534,
      "grad_norm": 0.41725394129753113,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0517,
      "step": 37
    },
    {
      "epoch": 0.0012330056134202928,
      "grad_norm": 0.6825345158576965,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.134,
      "step": 38
    },
    {
      "epoch": 0.001265453129562932,
      "grad_norm": 0.641930878162384,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.4195,
      "step": 39
    },
    {
      "epoch": 0.0012979006457055713,
      "grad_norm": 0.7435463070869446,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.195,
      "step": 40
    },
    {
      "epoch": 0.0013303481618482105,
      "grad_norm": 0.5704800486564636,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.0218,
      "step": 41
    },
    {
      "epoch": 0.0013627956779908499,
      "grad_norm": 0.6911413669586182,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.2863,
      "step": 42
    },
    {
      "epoch": 0.001395243194133489,
      "grad_norm": 0.9549648761749268,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.2395,
      "step": 43
    },
    {
      "epoch": 0.0014276907102761284,
      "grad_norm": 0.8420898914337158,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0508,
      "step": 44
    },
    {
      "epoch": 0.0014601382264187676,
      "grad_norm": 0.8447883129119873,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.0626,
      "step": 45
    },
    {
      "epoch": 0.0014601382264187676,
      "eval_loss": 1.1072334051132202,
      "eval_runtime": 410.1574,
      "eval_samples_per_second": 63.276,
      "eval_steps_per_second": 7.912,
      "step": 45
    },
    {
      "epoch": 0.001492585742561407,
      "grad_norm": 0.7884063124656677,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1144,
      "step": 46
    },
    {
      "epoch": 0.001525033258704046,
      "grad_norm": 0.6031967401504517,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.2737,
      "step": 47
    },
    {
      "epoch": 0.0015574807748466855,
      "grad_norm": 1.1018924713134766,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0928,
      "step": 48
    },
    {
      "epoch": 0.0015899282909893249,
      "grad_norm": 0.6400368213653564,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.0312,
      "step": 49
    },
    {
      "epoch": 0.001622375807131964,
      "grad_norm": 0.5094920992851257,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.951,
      "step": 50
    },
    {
      "epoch": 0.0016548233232746034,
      "grad_norm": 0.5639609694480896,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.1328,
      "step": 51
    },
    {
      "epoch": 0.0016872708394172426,
      "grad_norm": 0.9295167922973633,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.0703,
      "step": 52
    },
    {
      "epoch": 0.001719718355559882,
      "grad_norm": 0.681804358959198,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8775,
      "step": 53
    },
    {
      "epoch": 0.0017521658717025211,
      "grad_norm": 0.9615750312805176,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.134,
      "step": 54
    },
    {
      "epoch": 0.0017521658717025211,
      "eval_loss": 1.100877046585083,
      "eval_runtime": 410.0074,
      "eval_samples_per_second": 63.299,
      "eval_steps_per_second": 7.914,
      "step": 54
    },
    {
      "epoch": 0.0017846133878451605,
      "grad_norm": 0.656295657157898,
      "learning_rate": 5e-05,
      "loss": 0.975,
      "step": 55
    },
    {
      "epoch": 0.0018170609039877997,
      "grad_norm": 0.7529284954071045,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.1466,
      "step": 56
    },
    {
      "epoch": 0.001849508420130439,
      "grad_norm": 0.729901909828186,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.9293,
      "step": 57
    },
    {
      "epoch": 0.0018819559362730782,
      "grad_norm": 0.6308677196502686,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.0554,
      "step": 58
    },
    {
      "epoch": 0.0019144034524157176,
      "grad_norm": 0.7009322643280029,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.2438,
      "step": 59
    },
    {
      "epoch": 0.0019468509685583568,
      "grad_norm": 0.5819316506385803,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.078,
      "step": 60
    },
    {
      "epoch": 0.0019792984847009963,
      "grad_norm": 0.7872710824012756,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.1027,
      "step": 61
    },
    {
      "epoch": 0.0020117460008436355,
      "grad_norm": 0.7103775143623352,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.137,
      "step": 62
    },
    {
      "epoch": 0.0020441935169862747,
      "grad_norm": 0.6074665188789368,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.1263,
      "step": 63
    },
    {
      "epoch": 0.0020441935169862747,
      "eval_loss": 1.096551775932312,
      "eval_runtime": 410.1243,
      "eval_samples_per_second": 63.281,
      "eval_steps_per_second": 7.912,
      "step": 63
    },
    {
      "epoch": 0.002076641033128914,
      "grad_norm": 0.7665818333625793,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.953,
      "step": 64
    },
    {
      "epoch": 0.0021090885492715534,
      "grad_norm": 0.7354022860527039,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.1649,
      "step": 65
    },
    {
      "epoch": 0.0021415360654141926,
      "grad_norm": 0.8466889262199402,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.1085,
      "step": 66
    },
    {
      "epoch": 0.0021739835815568318,
      "grad_norm": 0.6907970905303955,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.1462,
      "step": 67
    },
    {
      "epoch": 0.002206431097699471,
      "grad_norm": 0.7935671210289001,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8663,
      "step": 68
    },
    {
      "epoch": 0.0022388786138421105,
      "grad_norm": 0.6784248948097229,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.1117,
      "step": 69
    },
    {
      "epoch": 0.0022713261299847497,
      "grad_norm": 0.6219685673713684,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.1149,
      "step": 70
    },
    {
      "epoch": 0.002303773646127389,
      "grad_norm": 0.7263062000274658,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7273,
      "step": 71
    },
    {
      "epoch": 0.002336221162270028,
      "grad_norm": 0.6051014065742493,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.1056,
      "step": 72
    },
    {
      "epoch": 0.002336221162270028,
      "eval_loss": 1.0936394929885864,
      "eval_runtime": 409.7581,
      "eval_samples_per_second": 63.337,
      "eval_steps_per_second": 7.919,
      "step": 72
    },
    {
      "epoch": 0.0023686686784126676,
      "grad_norm": 0.5516490340232849,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0039,
      "step": 73
    },
    {
      "epoch": 0.0024011161945553068,
      "grad_norm": 0.9471641182899475,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.1249,
      "step": 74
    },
    {
      "epoch": 0.002433563710697946,
      "grad_norm": 0.6294670104980469,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.9388,
      "step": 75
    },
    {
      "epoch": 0.0024660112268405855,
      "grad_norm": 0.6627998948097229,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.1794,
      "step": 76
    },
    {
      "epoch": 0.0024984587429832247,
      "grad_norm": 0.5571295022964478,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.2429,
      "step": 77
    },
    {
      "epoch": 0.002530906259125864,
      "grad_norm": 0.7011799216270447,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0675,
      "step": 78
    },
    {
      "epoch": 0.002563353775268503,
      "grad_norm": 0.7084078192710876,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.0732,
      "step": 79
    },
    {
      "epoch": 0.0025958012914111426,
      "grad_norm": 0.728354275226593,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.1039,
      "step": 80
    },
    {
      "epoch": 0.002628248807553782,
      "grad_norm": 0.7055922746658325,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.0463,
      "step": 81
    },
    {
      "epoch": 0.002628248807553782,
      "eval_loss": 1.0919792652130127,
      "eval_runtime": 410.0116,
      "eval_samples_per_second": 63.298,
      "eval_steps_per_second": 7.914,
      "step": 81
    },
    {
      "epoch": 0.002660696323696421,
      "grad_norm": 0.6339782476425171,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1567,
      "step": 82
    },
    {
      "epoch": 0.00269314383983906,
      "grad_norm": 0.8945773839950562,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.1069,
      "step": 83
    },
    {
      "epoch": 0.0027255913559816997,
      "grad_norm": 0.7640128135681152,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.0045,
      "step": 84
    },
    {
      "epoch": 0.002758038872124339,
      "grad_norm": 0.7280663847923279,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.056,
      "step": 85
    },
    {
      "epoch": 0.002790486388266978,
      "grad_norm": 0.5676079988479614,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0548,
      "step": 86
    },
    {
      "epoch": 0.0028229339044096176,
      "grad_norm": 0.5649421215057373,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.026,
      "step": 87
    },
    {
      "epoch": 0.002855381420552257,
      "grad_norm": 0.534390389919281,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.0154,
      "step": 88
    },
    {
      "epoch": 0.002887828936694896,
      "grad_norm": 0.6375171542167664,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0314,
      "step": 89
    },
    {
      "epoch": 0.002920276452837535,
      "grad_norm": 0.8114333748817444,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.2451,
      "step": 90
    },
    {
      "epoch": 0.002920276452837535,
      "eval_loss": 1.0911792516708374,
      "eval_runtime": 410.057,
      "eval_samples_per_second": 63.291,
      "eval_steps_per_second": 7.914,
      "step": 90
    },
    {
      "epoch": 0.0029527239689801747,
      "grad_norm": 0.7806537747383118,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2908,
      "step": 91
    },
    {
      "epoch": 0.002985171485122814,
      "grad_norm": 0.7690258622169495,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0371,
      "step": 92
    },
    {
      "epoch": 0.003017619001265453,
      "grad_norm": 0.6484013199806213,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.0125,
      "step": 93
    },
    {
      "epoch": 0.003050066517408092,
      "grad_norm": 0.7861148715019226,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.1867,
      "step": 94
    },
    {
      "epoch": 0.003082514033550732,
      "grad_norm": 0.5767760872840881,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.9655,
      "step": 95
    },
    {
      "epoch": 0.003114961549693371,
      "grad_norm": 0.6316145658493042,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.1651,
      "step": 96
    },
    {
      "epoch": 0.00314740906583601,
      "grad_norm": 0.621796190738678,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0775,
      "step": 97
    },
    {
      "epoch": 0.0031798565819786497,
      "grad_norm": 0.6306882500648499,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.1397,
      "step": 98
    },
    {
      "epoch": 0.003212304098121289,
      "grad_norm": 0.5787349343299866,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0839,
      "step": 99
    },
    {
      "epoch": 0.003212304098121289,
      "eval_loss": 1.0910366773605347,
      "eval_runtime": 409.9187,
      "eval_samples_per_second": 63.313,
      "eval_steps_per_second": 7.916,
      "step": 99
    },
    {
      "epoch": 0.003244751614263928,
      "grad_norm": 0.7515978813171387,
      "learning_rate": 0.0,
      "loss": 1.1321,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0705435229159424e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}