{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004270037149323199,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.270037149323199e-05,
      "grad_norm": 0.5806448459625244,
      "learning_rate": 1e-05,
      "loss": 0.7031,
      "step": 1
    },
    {
      "epoch": 4.270037149323199e-05,
      "eval_loss": 0.6539058685302734,
      "eval_runtime": 1043.647,
      "eval_samples_per_second": 18.897,
      "eval_steps_per_second": 2.363,
      "step": 1
    },
    {
      "epoch": 8.540074298646398e-05,
      "grad_norm": 0.5279636383056641,
      "learning_rate": 2e-05,
      "loss": 0.6652,
      "step": 2
    },
    {
      "epoch": 0.00012810111447969597,
      "grad_norm": 0.5978780388832092,
      "learning_rate": 3e-05,
      "loss": 0.6196,
      "step": 3
    },
    {
      "epoch": 0.00017080148597292796,
      "grad_norm": 0.5513725876808167,
      "learning_rate": 4e-05,
      "loss": 0.6547,
      "step": 4
    },
    {
      "epoch": 0.00021350185746615995,
      "grad_norm": 0.6722200512886047,
      "learning_rate": 5e-05,
      "loss": 0.7237,
      "step": 5
    },
    {
      "epoch": 0.00025620222895939194,
      "grad_norm": 0.5960759520530701,
      "learning_rate": 6e-05,
      "loss": 0.5818,
      "step": 6
    },
    {
      "epoch": 0.00029890260045262396,
      "grad_norm": 0.619697630405426,
      "learning_rate": 7e-05,
      "loss": 0.5735,
      "step": 7
    },
    {
      "epoch": 0.0003416029719458559,
      "grad_norm": 0.5188044309616089,
      "learning_rate": 8e-05,
      "loss": 0.4729,
      "step": 8
    },
    {
      "epoch": 0.00038430334343908794,
      "grad_norm": 0.5667243599891663,
      "learning_rate": 9e-05,
      "loss": 0.4471,
      "step": 9
    },
    {
      "epoch": 0.00038430334343908794,
      "eval_loss": 0.4289737343788147,
      "eval_runtime": 1042.9129,
      "eval_samples_per_second": 18.91,
      "eval_steps_per_second": 2.365,
      "step": 9
    },
    {
      "epoch": 0.0004270037149323199,
      "grad_norm": 0.6490625739097595,
      "learning_rate": 0.0001,
      "loss": 0.4473,
      "step": 10
    },
    {
      "epoch": 0.0004697040864255519,
      "grad_norm": 0.5033735632896423,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4143,
      "step": 11
    },
    {
      "epoch": 0.0005124044579187839,
      "grad_norm": 0.4695536196231842,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3505,
      "step": 12
    },
    {
      "epoch": 0.0005551048294120159,
      "grad_norm": 0.499141126871109,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3492,
      "step": 13
    },
    {
      "epoch": 0.0005978052009052479,
      "grad_norm": 0.5028942823410034,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.282,
      "step": 14
    },
    {
      "epoch": 0.0006405055723984798,
      "grad_norm": 0.5011232495307922,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.3819,
      "step": 15
    },
    {
      "epoch": 0.0006832059438917118,
      "grad_norm": 0.4742172956466675,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3328,
      "step": 16
    },
    {
      "epoch": 0.0007259063153849439,
      "grad_norm": 0.439372181892395,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.3047,
      "step": 17
    },
    {
      "epoch": 0.0007686066868781759,
      "grad_norm": 0.4455060064792633,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.3214,
      "step": 18
    },
    {
      "epoch": 0.0007686066868781759,
      "eval_loss": 0.29088911414146423,
      "eval_runtime": 1042.7152,
      "eval_samples_per_second": 18.914,
      "eval_steps_per_second": 2.365,
      "step": 18
    },
    {
      "epoch": 0.0008113070583714078,
      "grad_norm": 0.393311470746994,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2974,
      "step": 19
    },
    {
      "epoch": 0.0008540074298646398,
      "grad_norm": 0.4025300443172455,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2702,
      "step": 20
    },
    {
      "epoch": 0.0008967078013578718,
      "grad_norm": 0.41801270842552185,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3036,
      "step": 21
    },
    {
      "epoch": 0.0009394081728511038,
      "grad_norm": 0.35936877131462097,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.231,
      "step": 22
    },
    {
      "epoch": 0.0009821085443443359,
      "grad_norm": 0.3666516840457916,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2591,
      "step": 23
    },
    {
      "epoch": 0.0010248089158375678,
      "grad_norm": 0.337710976600647,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2395,
      "step": 24
    },
    {
      "epoch": 0.0010675092873307997,
      "grad_norm": 0.39601168036460876,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.3018,
      "step": 25
    },
    {
      "epoch": 0.0011102096588240318,
      "grad_norm": 0.3834843337535858,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.3222,
      "step": 26
    },
    {
      "epoch": 0.0011529100303172637,
      "grad_norm": 0.41886094212532043,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.239,
      "step": 27
    },
    {
      "epoch": 0.0011529100303172637,
      "eval_loss": 0.2563450336456299,
      "eval_runtime": 1042.8941,
      "eval_samples_per_second": 18.911,
      "eval_steps_per_second": 2.365,
      "step": 27
    },
    {
      "epoch": 0.0011956104018104958,
      "grad_norm": 0.3777792453765869,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3324,
      "step": 28
    },
    {
      "epoch": 0.0012383107733037278,
      "grad_norm": 0.3712221682071686,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2331,
      "step": 29
    },
    {
      "epoch": 0.0012810111447969597,
      "grad_norm": 0.36599892377853394,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.225,
      "step": 30
    },
    {
      "epoch": 0.0013237115162901918,
      "grad_norm": 0.3358147144317627,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2138,
      "step": 31
    },
    {
      "epoch": 0.0013664118877834237,
      "grad_norm": 0.36963242292404175,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2453,
      "step": 32
    },
    {
      "epoch": 0.0014091122592766556,
      "grad_norm": 0.3715946078300476,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2436,
      "step": 33
    },
    {
      "epoch": 0.0014518126307698877,
      "grad_norm": 0.3672356605529785,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2154,
      "step": 34
    },
    {
      "epoch": 0.0014945130022631196,
      "grad_norm": 0.39946144819259644,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.296,
      "step": 35
    },
    {
      "epoch": 0.0015372133737563518,
      "grad_norm": 0.3786686062812805,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2748,
      "step": 36
    },
    {
      "epoch": 0.0015372133737563518,
      "eval_loss": 0.24014145135879517,
      "eval_runtime": 1042.4884,
      "eval_samples_per_second": 18.918,
      "eval_steps_per_second": 2.365,
      "step": 36
    },
    {
      "epoch": 0.0015799137452495837,
      "grad_norm": 0.30576813220977783,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2187,
      "step": 37
    },
    {
      "epoch": 0.0016226141167428156,
      "grad_norm": 0.4365510642528534,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3345,
      "step": 38
    },
    {
      "epoch": 0.0016653144882360477,
      "grad_norm": 0.31430575251579285,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2518,
      "step": 39
    },
    {
      "epoch": 0.0017080148597292796,
      "grad_norm": 0.30722737312316895,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1799,
      "step": 40
    },
    {
      "epoch": 0.0017507152312225115,
      "grad_norm": 0.7996488213539124,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2487,
      "step": 41
    },
    {
      "epoch": 0.0017934156027157437,
      "grad_norm": 0.360711008310318,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2487,
      "step": 42
    },
    {
      "epoch": 0.0018361159742089756,
      "grad_norm": 0.2855508327484131,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2171,
      "step": 43
    },
    {
      "epoch": 0.0018788163457022077,
      "grad_norm": 0.4108193516731262,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.2603,
      "step": 44
    },
    {
      "epoch": 0.0019215167171954396,
      "grad_norm": 0.3485919237136841,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2161,
      "step": 45
    },
    {
      "epoch": 0.0019215167171954396,
      "eval_loss": 0.2321677803993225,
      "eval_runtime": 1043.2455,
      "eval_samples_per_second": 18.904,
      "eval_steps_per_second": 2.364,
      "step": 45
    },
    {
      "epoch": 0.0019642170886886717,
      "grad_norm": 0.3474808931350708,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2196,
      "step": 46
    },
    {
      "epoch": 0.0020069174601819034,
      "grad_norm": 0.3056509792804718,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1926,
      "step": 47
    },
    {
      "epoch": 0.0020496178316751355,
      "grad_norm": 0.3568718731403351,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2306,
      "step": 48
    },
    {
      "epoch": 0.0020923182031683677,
      "grad_norm": 0.3656061589717865,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2755,
      "step": 49
    },
    {
      "epoch": 0.0021350185746615994,
      "grad_norm": 0.34584182500839233,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2099,
      "step": 50
    },
    {
      "epoch": 0.0021777189461548315,
      "grad_norm": 0.30307361483573914,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2349,
      "step": 51
    },
    {
      "epoch": 0.0022204193176480636,
      "grad_norm": 0.39751020073890686,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.201,
      "step": 52
    },
    {
      "epoch": 0.0022631196891412953,
      "grad_norm": 0.33425378799438477,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2524,
      "step": 53
    },
    {
      "epoch": 0.0023058200606345274,
      "grad_norm": 0.3343847990036011,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2174,
      "step": 54
    },
    {
      "epoch": 0.0023058200606345274,
      "eval_loss": 0.22683541476726532,
      "eval_runtime": 1042.3263,
      "eval_samples_per_second": 18.921,
      "eval_steps_per_second": 2.366,
      "step": 54
    },
    {
      "epoch": 0.0023485204321277596,
      "grad_norm": 0.33391427993774414,
      "learning_rate": 5e-05,
      "loss": 0.1933,
      "step": 55
    },
    {
      "epoch": 0.0023912208036209917,
      "grad_norm": 0.35349971055984497,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2256,
      "step": 56
    },
    {
      "epoch": 0.0024339211751142234,
      "grad_norm": 0.38863974809646606,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2714,
      "step": 57
    },
    {
      "epoch": 0.0024766215466074555,
      "grad_norm": 0.42387786507606506,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2432,
      "step": 58
    },
    {
      "epoch": 0.0025193219181006876,
      "grad_norm": 0.31495586037635803,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1821,
      "step": 59
    },
    {
      "epoch": 0.0025620222895939193,
      "grad_norm": 0.30894848704338074,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.199,
      "step": 60
    },
    {
      "epoch": 0.0026047226610871515,
      "grad_norm": 0.25788867473602295,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2037,
      "step": 61
    },
    {
      "epoch": 0.0026474230325803836,
      "grad_norm": 0.33555373549461365,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2012,
      "step": 62
    },
    {
      "epoch": 0.0026901234040736153,
      "grad_norm": 0.3025542199611664,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2233,
      "step": 63
    },
    {
      "epoch": 0.0026901234040736153,
      "eval_loss": 0.2226668745279312,
      "eval_runtime": 1042.8472,
      "eval_samples_per_second": 18.912,
      "eval_steps_per_second": 2.365,
      "step": 63
    },
    {
      "epoch": 0.0027328237755668474,
      "grad_norm": 0.35507652163505554,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2529,
      "step": 64
    },
    {
      "epoch": 0.0027755241470600795,
      "grad_norm": 0.3171915113925934,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2096,
      "step": 65
    },
    {
      "epoch": 0.0028182245185533112,
      "grad_norm": 0.3953452408313751,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2454,
      "step": 66
    },
    {
      "epoch": 0.0028609248900465433,
      "grad_norm": 0.3464995324611664,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2131,
      "step": 67
    },
    {
      "epoch": 0.0029036252615397755,
      "grad_norm": 0.33387652039527893,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2442,
      "step": 68
    },
    {
      "epoch": 0.0029463256330330076,
      "grad_norm": 0.3720588684082031,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2552,
      "step": 69
    },
    {
      "epoch": 0.0029890260045262393,
      "grad_norm": 0.2944726347923279,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1772,
      "step": 70
    },
    {
      "epoch": 0.0030317263760194714,
      "grad_norm": 0.3224077820777893,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1975,
      "step": 71
    },
    {
      "epoch": 0.0030744267475127035,
      "grad_norm": 0.3087961971759796,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1746,
      "step": 72
    },
    {
      "epoch": 0.0030744267475127035,
      "eval_loss": 0.2203490138053894,
      "eval_runtime": 1042.3878,
      "eval_samples_per_second": 18.92,
      "eval_steps_per_second": 2.366,
      "step": 72
    },
    {
      "epoch": 0.0031171271190059352,
      "grad_norm": 0.3237898647785187,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2342,
      "step": 73
    },
    {
      "epoch": 0.0031598274904991674,
      "grad_norm": 0.3525395691394806,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1927,
      "step": 74
    },
    {
      "epoch": 0.0032025278619923995,
      "grad_norm": 0.3019056022167206,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1916,
      "step": 75
    },
    {
      "epoch": 0.003245228233485631,
      "grad_norm": 0.35412412881851196,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1878,
      "step": 76
    },
    {
      "epoch": 0.0032879286049788633,
      "grad_norm": 0.30525103211402893,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1653,
      "step": 77
    },
    {
      "epoch": 0.0033306289764720954,
      "grad_norm": 0.39213159680366516,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.2591,
      "step": 78
    },
    {
      "epoch": 0.003373329347965327,
      "grad_norm": 0.3606932461261749,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2121,
      "step": 79
    },
    {
      "epoch": 0.0034160297194585592,
      "grad_norm": 0.3313511908054352,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.191,
      "step": 80
    },
    {
      "epoch": 0.0034587300909517914,
      "grad_norm": 0.3328807055950165,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2106,
      "step": 81
    },
    {
      "epoch": 0.0034587300909517914,
      "eval_loss": 0.21893253922462463,
      "eval_runtime": 1042.9691,
      "eval_samples_per_second": 18.909,
      "eval_steps_per_second": 2.364,
      "step": 81
    },
    {
      "epoch": 0.003501430462445023,
      "grad_norm": 0.2882632315158844,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2033,
      "step": 82
    },
    {
      "epoch": 0.003544130833938255,
      "grad_norm": 0.29635459184646606,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1779,
      "step": 83
    },
    {
      "epoch": 0.0035868312054314873,
      "grad_norm": 0.33490076661109924,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.2321,
      "step": 84
    },
    {
      "epoch": 0.0036295315769247194,
      "grad_norm": 0.35736796259880066,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2227,
      "step": 85
    },
    {
      "epoch": 0.003672231948417951,
      "grad_norm": 0.27138444781303406,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1776,
      "step": 86
    },
    {
      "epoch": 0.0037149323199111833,
      "grad_norm": 0.3137736916542053,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2174,
      "step": 87
    },
    {
      "epoch": 0.0037576326914044154,
      "grad_norm": 0.3758503496646881,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2291,
      "step": 88
    },
    {
      "epoch": 0.003800333062897647,
      "grad_norm": 0.31046900153160095,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2707,
      "step": 89
    },
    {
      "epoch": 0.003843033434390879,
      "grad_norm": 0.40348750352859497,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2896,
      "step": 90
    },
    {
      "epoch": 0.003843033434390879,
      "eval_loss": 0.2182931900024414,
      "eval_runtime": 1042.6209,
      "eval_samples_per_second": 18.916,
      "eval_steps_per_second": 2.365,
      "step": 90
    },
    {
      "epoch": 0.0038857338058841113,
      "grad_norm": 0.3493230938911438,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2649,
      "step": 91
    },
    {
      "epoch": 0.0039284341773773435,
      "grad_norm": 0.4098386764526367,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2941,
      "step": 92
    },
    {
      "epoch": 0.003971134548870575,
      "grad_norm": 0.37344005703926086,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2413,
      "step": 93
    },
    {
      "epoch": 0.004013834920363807,
      "grad_norm": 0.32273340225219727,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.2232,
      "step": 94
    },
    {
      "epoch": 0.004056535291857039,
      "grad_norm": 0.36059901118278503,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2346,
      "step": 95
    },
    {
      "epoch": 0.004099235663350271,
      "grad_norm": 0.37520527839660645,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2152,
      "step": 96
    },
    {
      "epoch": 0.004141936034843503,
      "grad_norm": 0.30212971568107605,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1743,
      "step": 97
    },
    {
      "epoch": 0.004184636406336735,
      "grad_norm": 0.37452566623687744,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.2375,
      "step": 98
    },
    {
      "epoch": 0.004227336777829967,
      "grad_norm": 0.314308762550354,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1714,
      "step": 99
    },
    {
      "epoch": 0.004227336777829967,
      "eval_loss": 0.21816055476665497,
      "eval_runtime": 1042.752,
      "eval_samples_per_second": 18.913,
      "eval_steps_per_second": 2.365,
      "step": 99
    },
    {
      "epoch": 0.004270037149323199,
      "grad_norm": 0.3065028786659241,
      "learning_rate": 0.0,
      "loss": 0.2229,
      "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": 7.455967199782502e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}