{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4140786749482402,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004140786749482402,
      "grad_norm": 0.9301577806472778,
      "learning_rate": 1e-05,
      "loss": 3.1126,
      "step": 1
    },
    {
      "epoch": 0.004140786749482402,
      "eval_loss": 1.5828256607055664,
      "eval_runtime": 86.4747,
      "eval_samples_per_second": 2.359,
      "eval_steps_per_second": 0.301,
      "step": 1
    },
    {
      "epoch": 0.008281573498964804,
      "grad_norm": 0.8852660655975342,
      "learning_rate": 2e-05,
      "loss": 3.2312,
      "step": 2
    },
    {
      "epoch": 0.012422360248447204,
      "grad_norm": 0.9227669835090637,
      "learning_rate": 3e-05,
      "loss": 2.8183,
      "step": 3
    },
    {
      "epoch": 0.016563146997929608,
      "grad_norm": 1.096196174621582,
      "learning_rate": 4e-05,
      "loss": 3.433,
      "step": 4
    },
    {
      "epoch": 0.020703933747412008,
      "grad_norm": 1.1805181503295898,
      "learning_rate": 5e-05,
      "loss": 2.9417,
      "step": 5
    },
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 1.0887078046798706,
      "learning_rate": 6e-05,
      "loss": 2.7484,
      "step": 6
    },
    {
      "epoch": 0.028985507246376812,
      "grad_norm": 1.1074923276901245,
      "learning_rate": 7e-05,
      "loss": 2.8224,
      "step": 7
    },
    {
      "epoch": 0.033126293995859216,
      "grad_norm": 1.1030354499816895,
      "learning_rate": 8e-05,
      "loss": 2.7812,
      "step": 8
    },
    {
      "epoch": 0.037267080745341616,
      "grad_norm": 1.2491376399993896,
      "learning_rate": 9e-05,
      "loss": 2.6374,
      "step": 9
    },
    {
      "epoch": 0.037267080745341616,
      "eval_loss": 1.3686977624893188,
      "eval_runtime": 86.6236,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 9
    },
    {
      "epoch": 0.041407867494824016,
      "grad_norm": 1.2215477228164673,
      "learning_rate": 0.0001,
      "loss": 2.9145,
      "step": 10
    },
    {
      "epoch": 0.045548654244306416,
      "grad_norm": 1.2886161804199219,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.2524,
      "step": 11
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 1.200274109840393,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.3977,
      "step": 12
    },
    {
      "epoch": 0.053830227743271224,
      "grad_norm": 1.059577465057373,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.1013,
      "step": 13
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 1.544952154159546,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.3457,
      "step": 14
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 1.3836092948913574,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.7073,
      "step": 15
    },
    {
      "epoch": 0.06625258799171843,
      "grad_norm": 1.410312533378601,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.8543,
      "step": 16
    },
    {
      "epoch": 0.07039337474120083,
      "grad_norm": 1.2303005456924438,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.3382,
      "step": 17
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 1.4924076795578003,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.2618,
      "step": 18
    },
    {
      "epoch": 0.07453416149068323,
      "eval_loss": 1.0939579010009766,
      "eval_runtime": 86.594,
      "eval_samples_per_second": 2.356,
      "eval_steps_per_second": 0.3,
      "step": 18
    },
    {
      "epoch": 0.07867494824016563,
      "grad_norm": 1.4655351638793945,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.5699,
      "step": 19
    },
    {
      "epoch": 0.08281573498964803,
      "grad_norm": 1.2195974588394165,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8441,
      "step": 20
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 1.2934242486953735,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2081,
      "step": 21
    },
    {
      "epoch": 0.09109730848861283,
      "grad_norm": 1.0533246994018555,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.0406,
      "step": 22
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.3303511142730713,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.3889,
      "step": 23
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 1.2019553184509277,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6975,
      "step": 24
    },
    {
      "epoch": 0.10351966873706005,
      "grad_norm": 1.1562660932540894,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.0118,
      "step": 25
    },
    {
      "epoch": 0.10766045548654245,
      "grad_norm": 1.2384679317474365,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.8618,
      "step": 26
    },
    {
      "epoch": 0.11180124223602485,
      "grad_norm": 1.2058842182159424,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.8744,
      "step": 27
    },
    {
      "epoch": 0.11180124223602485,
      "eval_loss": 1.000207543373108,
      "eval_runtime": 86.613,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 27
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 1.3206522464752197,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4724,
      "step": 28
    },
    {
      "epoch": 0.12008281573498965,
      "grad_norm": 1.1769299507141113,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.2312,
      "step": 29
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 1.1039841175079346,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.8363,
      "step": 30
    },
    {
      "epoch": 0.12836438923395446,
      "grad_norm": 1.1677961349487305,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.0295,
      "step": 31
    },
    {
      "epoch": 0.13250517598343686,
      "grad_norm": 1.136795163154602,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.7927,
      "step": 32
    },
    {
      "epoch": 0.13664596273291926,
      "grad_norm": 1.1699427366256714,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.1008,
      "step": 33
    },
    {
      "epoch": 0.14078674948240166,
      "grad_norm": 1.0956039428710938,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8778,
      "step": 34
    },
    {
      "epoch": 0.14492753623188406,
      "grad_norm": 1.106882929801941,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8638,
      "step": 35
    },
    {
      "epoch": 0.14906832298136646,
      "grad_norm": 1.176102638244629,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0063,
      "step": 36
    },
    {
      "epoch": 0.14906832298136646,
      "eval_loss": 0.9627537727355957,
      "eval_runtime": 86.6445,
      "eval_samples_per_second": 2.354,
      "eval_steps_per_second": 0.3,
      "step": 36
    },
    {
      "epoch": 0.15320910973084886,
      "grad_norm": 1.2707808017730713,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0563,
      "step": 37
    },
    {
      "epoch": 0.15734989648033126,
      "grad_norm": 1.1810678243637085,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.7766,
      "step": 38
    },
    {
      "epoch": 0.16149068322981366,
      "grad_norm": 1.2528388500213623,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.2023,
      "step": 39
    },
    {
      "epoch": 0.16563146997929606,
      "grad_norm": 1.1106541156768799,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9607,
      "step": 40
    },
    {
      "epoch": 0.16977225672877846,
      "grad_norm": 1.3797121047973633,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.2966,
      "step": 41
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 1.0759304761886597,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9743,
      "step": 42
    },
    {
      "epoch": 0.17805383022774326,
      "grad_norm": 1.485608696937561,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.1251,
      "step": 43
    },
    {
      "epoch": 0.18219461697722567,
      "grad_norm": 1.1569021940231323,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.9108,
      "step": 44
    },
    {
      "epoch": 0.18633540372670807,
      "grad_norm": 1.4364919662475586,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.561,
      "step": 45
    },
    {
      "epoch": 0.18633540372670807,
      "eval_loss": 0.9237259030342102,
      "eval_runtime": 86.6431,
      "eval_samples_per_second": 2.354,
      "eval_steps_per_second": 0.3,
      "step": 45
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.126060128211975,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.8225,
      "step": 46
    },
    {
      "epoch": 0.19461697722567287,
      "grad_norm": 1.137122392654419,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.8008,
      "step": 47
    },
    {
      "epoch": 0.19875776397515527,
      "grad_norm": 1.1307929754257202,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8732,
      "step": 48
    },
    {
      "epoch": 0.2028985507246377,
      "grad_norm": 1.3419166803359985,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.782,
      "step": 49
    },
    {
      "epoch": 0.2070393374741201,
      "grad_norm": 1.3455865383148193,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4769,
      "step": 50
    },
    {
      "epoch": 0.2111801242236025,
      "grad_norm": 1.3331935405731201,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.8375,
      "step": 51
    },
    {
      "epoch": 0.2153209109730849,
      "grad_norm": 1.3784667253494263,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.825,
      "step": 52
    },
    {
      "epoch": 0.2194616977225673,
      "grad_norm": 1.5882664918899536,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.7993,
      "step": 53
    },
    {
      "epoch": 0.2236024844720497,
      "grad_norm": 1.4123127460479736,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.0265,
      "step": 54
    },
    {
      "epoch": 0.2236024844720497,
      "eval_loss": 0.9083660840988159,
      "eval_runtime": 86.6141,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 54
    },
    {
      "epoch": 0.2277432712215321,
      "grad_norm": 1.447785496711731,
      "learning_rate": 5e-05,
      "loss": 2.1512,
      "step": 55
    },
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 1.2638105154037476,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.846,
      "step": 56
    },
    {
      "epoch": 0.2360248447204969,
      "grad_norm": 1.3584290742874146,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.8303,
      "step": 57
    },
    {
      "epoch": 0.2401656314699793,
      "grad_norm": 1.3381396532058716,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.8396,
      "step": 58
    },
    {
      "epoch": 0.2443064182194617,
      "grad_norm": 1.3689265251159668,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.0676,
      "step": 59
    },
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 1.4174652099609375,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.9523,
      "step": 60
    },
    {
      "epoch": 0.2525879917184265,
      "grad_norm": 1.3407961130142212,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.012,
      "step": 61
    },
    {
      "epoch": 0.2567287784679089,
      "grad_norm": 1.2478750944137573,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.7861,
      "step": 62
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 1.5503246784210205,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.9632,
      "step": 63
    },
    {
      "epoch": 0.2608695652173913,
      "eval_loss": 0.8929786682128906,
      "eval_runtime": 86.6107,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 63
    },
    {
      "epoch": 0.2650103519668737,
      "grad_norm": 1.4950432777404785,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.8385,
      "step": 64
    },
    {
      "epoch": 0.2691511387163561,
      "grad_norm": 1.512736201286316,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.7907,
      "step": 65
    },
    {
      "epoch": 0.2732919254658385,
      "grad_norm": 1.3820559978485107,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8472,
      "step": 66
    },
    {
      "epoch": 0.2774327122153209,
      "grad_norm": 1.4131429195404053,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4766,
      "step": 67
    },
    {
      "epoch": 0.2815734989648033,
      "grad_norm": 1.5196677446365356,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1048,
      "step": 68
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.3883243799209595,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8889,
      "step": 69
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 1.5153822898864746,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.039,
      "step": 70
    },
    {
      "epoch": 0.2939958592132505,
      "grad_norm": 1.3976097106933594,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.0947,
      "step": 71
    },
    {
      "epoch": 0.2981366459627329,
      "grad_norm": 1.1849572658538818,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.8548,
      "step": 72
    },
    {
      "epoch": 0.2981366459627329,
      "eval_loss": 0.8833903074264526,
      "eval_runtime": 86.6246,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 72
    },
    {
      "epoch": 0.3022774327122153,
      "grad_norm": 1.4871492385864258,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.4162,
      "step": 73
    },
    {
      "epoch": 0.3064182194616977,
      "grad_norm": 1.3210978507995605,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6831,
      "step": 74
    },
    {
      "epoch": 0.3105590062111801,
      "grad_norm": 1.3456048965454102,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8442,
      "step": 75
    },
    {
      "epoch": 0.3146997929606625,
      "grad_norm": 1.361826777458191,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.8078,
      "step": 76
    },
    {
      "epoch": 0.3188405797101449,
      "grad_norm": 1.30433189868927,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.6288,
      "step": 77
    },
    {
      "epoch": 0.32298136645962733,
      "grad_norm": 1.61412513256073,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.8112,
      "step": 78
    },
    {
      "epoch": 0.32712215320910976,
      "grad_norm": 1.463856816291809,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.0371,
      "step": 79
    },
    {
      "epoch": 0.33126293995859213,
      "grad_norm": 1.370507836341858,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7918,
      "step": 80
    },
    {
      "epoch": 0.33540372670807456,
      "grad_norm": 1.5622191429138184,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.1189,
      "step": 81
    },
    {
      "epoch": 0.33540372670807456,
      "eval_loss": 0.8779899477958679,
      "eval_runtime": 86.6409,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 81
    },
    {
      "epoch": 0.33954451345755693,
      "grad_norm": 1.1751959323883057,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.7123,
      "step": 82
    },
    {
      "epoch": 0.34368530020703936,
      "grad_norm": 1.3203461170196533,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.9642,
      "step": 83
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.4285207986831665,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.0058,
      "step": 84
    },
    {
      "epoch": 0.35196687370600416,
      "grad_norm": 1.5354092121124268,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.2293,
      "step": 85
    },
    {
      "epoch": 0.35610766045548653,
      "grad_norm": 1.2501472234725952,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.6873,
      "step": 86
    },
    {
      "epoch": 0.36024844720496896,
      "grad_norm": 1.2382432222366333,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.6576,
      "step": 87
    },
    {
      "epoch": 0.36438923395445133,
      "grad_norm": 1.519044041633606,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.9783,
      "step": 88
    },
    {
      "epoch": 0.36853002070393376,
      "grad_norm": 1.3468337059020996,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.7055,
      "step": 89
    },
    {
      "epoch": 0.37267080745341613,
      "grad_norm": 1.450764775276184,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.2036,
      "step": 90
    },
    {
      "epoch": 0.37267080745341613,
      "eval_loss": 0.8755683302879333,
      "eval_runtime": 86.6141,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 90
    },
    {
      "epoch": 0.37681159420289856,
      "grad_norm": 1.2986805438995361,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5392,
      "step": 91
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.204742431640625,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.8787,
      "step": 92
    },
    {
      "epoch": 0.38509316770186336,
      "grad_norm": 1.4381076097488403,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.0241,
      "step": 93
    },
    {
      "epoch": 0.38923395445134573,
      "grad_norm": 1.3065365552902222,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.8894,
      "step": 94
    },
    {
      "epoch": 0.39337474120082816,
      "grad_norm": 1.4354333877563477,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.9965,
      "step": 95
    },
    {
      "epoch": 0.39751552795031053,
      "grad_norm": 1.419108510017395,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.7321,
      "step": 96
    },
    {
      "epoch": 0.40165631469979296,
      "grad_norm": 1.3358365297317505,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.7262,
      "step": 97
    },
    {
      "epoch": 0.4057971014492754,
      "grad_norm": 1.2788820266723633,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.9486,
      "step": 98
    },
    {
      "epoch": 0.40993788819875776,
      "grad_norm": 1.3755329847335815,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.8636,
      "step": 99
    },
    {
      "epoch": 0.40993788819875776,
      "eval_loss": 0.874519944190979,
      "eval_runtime": 86.6203,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 0.3,
      "step": 99
    },
    {
      "epoch": 0.4140786749482402,
      "grad_norm": 1.3155301809310913,
      "learning_rate": 0.0,
      "loss": 1.6806,
      "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": 2.2344361467445248e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}