{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022462067184042945,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.246206718404295e-05,
      "grad_norm": 2.7750818729400635,
      "learning_rate": 1e-05,
      "loss": 4.586,
      "step": 1
    },
    {
      "epoch": 2.246206718404295e-05,
      "eval_loss": 2.2075488567352295,
      "eval_runtime": 1630.869,
      "eval_samples_per_second": 22.988,
      "eval_steps_per_second": 2.874,
      "step": 1
    },
    {
      "epoch": 4.49241343680859e-05,
      "grad_norm": 1.9289658069610596,
      "learning_rate": 2e-05,
      "loss": 3.7755,
      "step": 2
    },
    {
      "epoch": 6.738620155212884e-05,
      "grad_norm": 2.192617654800415,
      "learning_rate": 3e-05,
      "loss": 4.2251,
      "step": 3
    },
    {
      "epoch": 8.98482687361718e-05,
      "grad_norm": 2.3574883937835693,
      "learning_rate": 4e-05,
      "loss": 4.9035,
      "step": 4
    },
    {
      "epoch": 0.00011231033592021474,
      "grad_norm": 2.7869656085968018,
      "learning_rate": 5e-05,
      "loss": 4.7603,
      "step": 5
    },
    {
      "epoch": 0.00013477240310425767,
      "grad_norm": 3.171642541885376,
      "learning_rate": 6e-05,
      "loss": 4.1502,
      "step": 6
    },
    {
      "epoch": 0.00015723447028830065,
      "grad_norm": 3.7151501178741455,
      "learning_rate": 7e-05,
      "loss": 4.5112,
      "step": 7
    },
    {
      "epoch": 0.0001796965374723436,
      "grad_norm": 3.1683778762817383,
      "learning_rate": 8e-05,
      "loss": 3.4748,
      "step": 8
    },
    {
      "epoch": 0.00020215860465638654,
      "grad_norm": 5.810944080352783,
      "learning_rate": 9e-05,
      "loss": 4.2722,
      "step": 9
    },
    {
      "epoch": 0.00020215860465638654,
      "eval_loss": 2.0206046104431152,
      "eval_runtime": 1631.9238,
      "eval_samples_per_second": 22.973,
      "eval_steps_per_second": 2.872,
      "step": 9
    },
    {
      "epoch": 0.00022462067184042948,
      "grad_norm": 5.076383113861084,
      "learning_rate": 0.0001,
      "loss": 4.7174,
      "step": 10
    },
    {
      "epoch": 0.0002470827390244724,
      "grad_norm": 3.3657078742980957,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.2967,
      "step": 11
    },
    {
      "epoch": 0.00026954480620851535,
      "grad_norm": 2.2659411430358887,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.7389,
      "step": 12
    },
    {
      "epoch": 0.0002920068733925583,
      "grad_norm": 1.7639695405960083,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.8581,
      "step": 13
    },
    {
      "epoch": 0.0003144689405766013,
      "grad_norm": 5.5207929611206055,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.9921,
      "step": 14
    },
    {
      "epoch": 0.00033693100776064424,
      "grad_norm": 3.114842176437378,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.1103,
      "step": 15
    },
    {
      "epoch": 0.0003593930749446872,
      "grad_norm": 2.190366744995117,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.363,
      "step": 16
    },
    {
      "epoch": 0.0003818551421287301,
      "grad_norm": 3.0523877143859863,
      "learning_rate": 9.851478631379982e-05,
      "loss": 4.1345,
      "step": 17
    },
    {
      "epoch": 0.00040431720931277307,
      "grad_norm": 3.813314437866211,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.8035,
      "step": 18
    },
    {
      "epoch": 0.00040431720931277307,
      "eval_loss": 1.826113224029541,
      "eval_runtime": 1632.2786,
      "eval_samples_per_second": 22.968,
      "eval_steps_per_second": 2.871,
      "step": 18
    },
    {
      "epoch": 0.000426779276496816,
      "grad_norm": 2.902435302734375,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1622,
      "step": 19
    },
    {
      "epoch": 0.00044924134368085896,
      "grad_norm": 3.186333417892456,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.1721,
      "step": 20
    },
    {
      "epoch": 0.0004717034108649019,
      "grad_norm": 3.263099193572998,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.933,
      "step": 21
    },
    {
      "epoch": 0.0004941654780489448,
      "grad_norm": 3.072693109512329,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.0188,
      "step": 22
    },
    {
      "epoch": 0.0005166275452329877,
      "grad_norm": 2.9341752529144287,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.1627,
      "step": 23
    },
    {
      "epoch": 0.0005390896124170307,
      "grad_norm": 2.0156662464141846,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.7665,
      "step": 24
    },
    {
      "epoch": 0.0005615516796010736,
      "grad_norm": 4.773046016693115,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.0075,
      "step": 25
    },
    {
      "epoch": 0.0005840137467851166,
      "grad_norm": 2.525400400161743,
      "learning_rate": 9.24024048078213e-05,
      "loss": 3.4141,
      "step": 26
    },
    {
      "epoch": 0.0006064758139691596,
      "grad_norm": 3.1710431575775146,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.5087,
      "step": 27
    },
    {
      "epoch": 0.0006064758139691596,
      "eval_loss": 1.780084252357483,
      "eval_runtime": 1632.5434,
      "eval_samples_per_second": 22.964,
      "eval_steps_per_second": 2.871,
      "step": 27
    },
    {
      "epoch": 0.0006289378811532026,
      "grad_norm": 2.813370704650879,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.8044,
      "step": 28
    },
    {
      "epoch": 0.0006513999483372455,
      "grad_norm": 2.058415174484253,
      "learning_rate": 8.940053768033609e-05,
      "loss": 3.2233,
      "step": 29
    },
    {
      "epoch": 0.0006738620155212885,
      "grad_norm": 1.962506890296936,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.5407,
      "step": 30
    },
    {
      "epoch": 0.0006963240827053314,
      "grad_norm": 2.352518320083618,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.8538,
      "step": 31
    },
    {
      "epoch": 0.0007187861498893744,
      "grad_norm": 2.3428025245666504,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.6797,
      "step": 32
    },
    {
      "epoch": 0.0007412482170734173,
      "grad_norm": 1.7835075855255127,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.832,
      "step": 33
    },
    {
      "epoch": 0.0007637102842574603,
      "grad_norm": 1.6647694110870361,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.4723,
      "step": 34
    },
    {
      "epoch": 0.0007861723514415032,
      "grad_norm": 2.274492025375366,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.0918,
      "step": 35
    },
    {
      "epoch": 0.0008086344186255461,
      "grad_norm": 3.1563773155212402,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.5549,
      "step": 36
    },
    {
      "epoch": 0.0008086344186255461,
      "eval_loss": 1.7567815780639648,
      "eval_runtime": 1632.074,
      "eval_samples_per_second": 22.971,
      "eval_steps_per_second": 2.872,
      "step": 36
    },
    {
      "epoch": 0.0008310964858095891,
      "grad_norm": 2.0984981060028076,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.4193,
      "step": 37
    },
    {
      "epoch": 0.000853558552993632,
      "grad_norm": 1.842602252960205,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.5343,
      "step": 38
    },
    {
      "epoch": 0.000876020620177675,
      "grad_norm": 1.6959556341171265,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.3391,
      "step": 39
    },
    {
      "epoch": 0.0008984826873617179,
      "grad_norm": 1.5816162824630737,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.8507,
      "step": 40
    },
    {
      "epoch": 0.0009209447545457609,
      "grad_norm": 1.8995237350463867,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.7906,
      "step": 41
    },
    {
      "epoch": 0.0009434068217298038,
      "grad_norm": 1.9689886569976807,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.1076,
      "step": 42
    },
    {
      "epoch": 0.0009658688889138468,
      "grad_norm": 2.290149450302124,
      "learning_rate": 7.033683215379002e-05,
      "loss": 3.3636,
      "step": 43
    },
    {
      "epoch": 0.0009883309560978896,
      "grad_norm": 2.0681443214416504,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.7999,
      "step": 44
    },
    {
      "epoch": 0.0010107930232819327,
      "grad_norm": 1.7715750932693481,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.1144,
      "step": 45
    },
    {
      "epoch": 0.0010107930232819327,
      "eval_loss": 1.7513365745544434,
      "eval_runtime": 1632.0626,
      "eval_samples_per_second": 22.971,
      "eval_steps_per_second": 2.872,
      "step": 45
    },
    {
      "epoch": 0.0010332550904659755,
      "grad_norm": 1.7227574586868286,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.4745,
      "step": 46
    },
    {
      "epoch": 0.0010557171576500185,
      "grad_norm": 1.5659047365188599,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.3294,
      "step": 47
    },
    {
      "epoch": 0.0010781792248340614,
      "grad_norm": 1.7313659191131592,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.6789,
      "step": 48
    },
    {
      "epoch": 0.0011006412920181044,
      "grad_norm": 1.6729196310043335,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.0046,
      "step": 49
    },
    {
      "epoch": 0.0011231033592021473,
      "grad_norm": 1.5939840078353882,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.185,
      "step": 50
    },
    {
      "epoch": 0.0011455654263861903,
      "grad_norm": 2.4340100288391113,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.9648,
      "step": 51
    },
    {
      "epoch": 0.0011680274935702332,
      "grad_norm": 2.181459903717041,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.8834,
      "step": 52
    },
    {
      "epoch": 0.0011904895607542762,
      "grad_norm": 1.8149747848510742,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.6703,
      "step": 53
    },
    {
      "epoch": 0.0012129516279383193,
      "grad_norm": 1.6692755222320557,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.6665,
      "step": 54
    },
    {
      "epoch": 0.0012129516279383193,
      "eval_loss": 1.7456862926483154,
      "eval_runtime": 1632.4662,
      "eval_samples_per_second": 22.965,
      "eval_steps_per_second": 2.871,
      "step": 54
    },
    {
      "epoch": 0.001235413695122362,
      "grad_norm": 2.4753801822662354,
      "learning_rate": 5e-05,
      "loss": 3.4893,
      "step": 55
    },
    {
      "epoch": 0.0012578757623064052,
      "grad_norm": 2.4215543270111084,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.5557,
      "step": 56
    },
    {
      "epoch": 0.001280337829490448,
      "grad_norm": 2.677598476409912,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.9957,
      "step": 57
    },
    {
      "epoch": 0.001302799896674491,
      "grad_norm": 1.6023344993591309,
      "learning_rate": 4.477357683661734e-05,
      "loss": 4.1756,
      "step": 58
    },
    {
      "epoch": 0.0013252619638585339,
      "grad_norm": 1.8356449604034424,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.8109,
      "step": 59
    },
    {
      "epoch": 0.001347724031042577,
      "grad_norm": 1.8622589111328125,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.7408,
      "step": 60
    },
    {
      "epoch": 0.0013701860982266198,
      "grad_norm": 1.797446846961975,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.7321,
      "step": 61
    },
    {
      "epoch": 0.0013926481654106628,
      "grad_norm": 1.903319239616394,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.697,
      "step": 62
    },
    {
      "epoch": 0.0014151102325947057,
      "grad_norm": 1.7271318435668945,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.7319,
      "step": 63
    },
    {
      "epoch": 0.0014151102325947057,
      "eval_loss": 1.7400661706924438,
      "eval_runtime": 1632.0443,
      "eval_samples_per_second": 22.971,
      "eval_steps_per_second": 2.872,
      "step": 63
    },
    {
      "epoch": 0.0014375722997787487,
      "grad_norm": 1.791338324546814,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.0344,
      "step": 64
    },
    {
      "epoch": 0.0014600343669627916,
      "grad_norm": 1.845373511314392,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.6643,
      "step": 65
    },
    {
      "epoch": 0.0014824964341468346,
      "grad_norm": 1.535976767539978,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.8485,
      "step": 66
    },
    {
      "epoch": 0.0015049585013308775,
      "grad_norm": 1.7403994798660278,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.1442,
      "step": 67
    },
    {
      "epoch": 0.0015274205685149205,
      "grad_norm": 1.6058380603790283,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.4109,
      "step": 68
    },
    {
      "epoch": 0.0015498826356989633,
      "grad_norm": 1.738742709159851,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.1998,
      "step": 69
    },
    {
      "epoch": 0.0015723447028830064,
      "grad_norm": 1.8473705053329468,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.399,
      "step": 70
    },
    {
      "epoch": 0.0015948067700670492,
      "grad_norm": 1.9509713649749756,
      "learning_rate": 2.350403678833976e-05,
      "loss": 3.4907,
      "step": 71
    },
    {
      "epoch": 0.0016172688372510923,
      "grad_norm": 1.8196882009506226,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.8142,
      "step": 72
    },
    {
      "epoch": 0.0016172688372510923,
      "eval_loss": 1.7379201650619507,
      "eval_runtime": 1632.391,
      "eval_samples_per_second": 22.966,
      "eval_steps_per_second": 2.871,
      "step": 72
    },
    {
      "epoch": 0.0016397309044351351,
      "grad_norm": 1.8369139432907104,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.736,
      "step": 73
    },
    {
      "epoch": 0.0016621929716191782,
      "grad_norm": 1.637620210647583,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.7325,
      "step": 74
    },
    {
      "epoch": 0.001684655038803221,
      "grad_norm": 1.5396091938018799,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.349,
      "step": 75
    },
    {
      "epoch": 0.001707117105987264,
      "grad_norm": 1.6613136529922485,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 4.1282,
      "step": 76
    },
    {
      "epoch": 0.001729579173171307,
      "grad_norm": 1.7891541719436646,
      "learning_rate": 1.526708147705013e-05,
      "loss": 3.4591,
      "step": 77
    },
    {
      "epoch": 0.00175204124035535,
      "grad_norm": 1.6895219087600708,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.639,
      "step": 78
    },
    {
      "epoch": 0.0017745033075393928,
      "grad_norm": 1.7939364910125732,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 3.7528,
      "step": 79
    },
    {
      "epoch": 0.0017969653747234359,
      "grad_norm": 1.9432029724121094,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.4584,
      "step": 80
    },
    {
      "epoch": 0.0018194274419074787,
      "grad_norm": 1.8174926042556763,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.3959,
      "step": 81
    },
    {
      "epoch": 0.0018194274419074787,
      "eval_loss": 1.736003041267395,
      "eval_runtime": 1632.5563,
      "eval_samples_per_second": 22.964,
      "eval_steps_per_second": 2.871,
      "step": 81
    },
    {
      "epoch": 0.0018418895090915217,
      "grad_norm": 1.5173909664154053,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.8656,
      "step": 82
    },
    {
      "epoch": 0.0018643515762755646,
      "grad_norm": 1.859105110168457,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.914,
      "step": 83
    },
    {
      "epoch": 0.0018868136434596076,
      "grad_norm": 2.0400619506835938,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.5052,
      "step": 84
    },
    {
      "epoch": 0.0019092757106436505,
      "grad_norm": 1.5139789581298828,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.9755,
      "step": 85
    },
    {
      "epoch": 0.0019317377778276935,
      "grad_norm": 1.9782215356826782,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.3867,
      "step": 86
    },
    {
      "epoch": 0.0019541998450117366,
      "grad_norm": 2.021449327468872,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.6848,
      "step": 87
    },
    {
      "epoch": 0.001976661912195779,
      "grad_norm": 1.7191298007965088,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.8803,
      "step": 88
    },
    {
      "epoch": 0.0019991239793798223,
      "grad_norm": 2.1756093502044678,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 3.6223,
      "step": 89
    },
    {
      "epoch": 0.0020215860465638653,
      "grad_norm": 1.4715290069580078,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.3865,
      "step": 90
    },
    {
      "epoch": 0.0020215860465638653,
      "eval_loss": 1.7353254556655884,
      "eval_runtime": 1632.2234,
      "eval_samples_per_second": 22.969,
      "eval_steps_per_second": 2.872,
      "step": 90
    },
    {
      "epoch": 0.0020440481137479084,
      "grad_norm": 1.6335053443908691,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.797,
      "step": 91
    },
    {
      "epoch": 0.002066510180931951,
      "grad_norm": 1.8039343357086182,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.244,
      "step": 92
    },
    {
      "epoch": 0.002088972248115994,
      "grad_norm": 1.8326294422149658,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.6564,
      "step": 93
    },
    {
      "epoch": 0.002111434315300037,
      "grad_norm": 1.3844493627548218,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.5496,
      "step": 94
    },
    {
      "epoch": 0.00213389638248408,
      "grad_norm": 1.5978397130966187,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.5101,
      "step": 95
    },
    {
      "epoch": 0.0021563584496681228,
      "grad_norm": 1.7243602275848389,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.5035,
      "step": 96
    },
    {
      "epoch": 0.002178820516852166,
      "grad_norm": 2.2073657512664795,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 3.2104,
      "step": 97
    },
    {
      "epoch": 0.002201282584036209,
      "grad_norm": 1.385772943496704,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.7669,
      "step": 98
    },
    {
      "epoch": 0.002223744651220252,
      "grad_norm": 1.9135991334915161,
      "learning_rate": 3.04586490452119e-08,
      "loss": 3.1943,
      "step": 99
    },
    {
      "epoch": 0.002223744651220252,
      "eval_loss": 1.7351237535476685,
      "eval_runtime": 1632.3963,
      "eval_samples_per_second": 22.966,
      "eval_steps_per_second": 2.871,
      "step": 99
    },
    {
      "epoch": 0.0022462067184042945,
      "grad_norm": 2.1019656658172607,
      "learning_rate": 0.0,
      "loss": 3.8132,
      "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": 6.53458201903104e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}