{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5011185682326622,
  "eval_steps": 45,
  "global_step": 112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0044742729306487695,
      "grad_norm": 0.056262753903865814,
      "learning_rate": 2.5e-06,
      "loss": 2.2246,
      "step": 1
    },
    {
      "epoch": 0.0044742729306487695,
      "eval_loss": 2.4987943172454834,
      "eval_runtime": 289.9018,
      "eval_samples_per_second": 0.635,
      "eval_steps_per_second": 0.635,
      "step": 1
    },
    {
      "epoch": 0.008948545861297539,
      "grad_norm": 0.05820031091570854,
      "learning_rate": 5e-06,
      "loss": 2.2253,
      "step": 2
    },
    {
      "epoch": 0.013422818791946308,
      "grad_norm": 0.05092893913388252,
      "learning_rate": 7.5e-06,
      "loss": 2.2124,
      "step": 3
    },
    {
      "epoch": 0.017897091722595078,
      "grad_norm": 0.06304118037223816,
      "learning_rate": 1e-05,
      "loss": 2.2923,
      "step": 4
    },
    {
      "epoch": 0.02237136465324385,
      "grad_norm": 0.05285007879137993,
      "learning_rate": 1.25e-05,
      "loss": 2.2454,
      "step": 5
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": 0.05117042735219002,
      "learning_rate": 1.5e-05,
      "loss": 2.2598,
      "step": 6
    },
    {
      "epoch": 0.03131991051454139,
      "grad_norm": 0.05469581112265587,
      "learning_rate": 1.75e-05,
      "loss": 2.2928,
      "step": 7
    },
    {
      "epoch": 0.035794183445190156,
      "grad_norm": 0.060069695115089417,
      "learning_rate": 2e-05,
      "loss": 2.0551,
      "step": 8
    },
    {
      "epoch": 0.040268456375838924,
      "grad_norm": 0.06096857041120529,
      "learning_rate": 2.25e-05,
      "loss": 2.3018,
      "step": 9
    },
    {
      "epoch": 0.0447427293064877,
      "grad_norm": 0.06183759495615959,
      "learning_rate": 2.5e-05,
      "loss": 2.1434,
      "step": 10
    },
    {
      "epoch": 0.049217002237136466,
      "grad_norm": 0.05740294232964516,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 2.2667,
      "step": 11
    },
    {
      "epoch": 0.053691275167785234,
      "grad_norm": 0.05711159110069275,
      "learning_rate": 3e-05,
      "loss": 2.0616,
      "step": 12
    },
    {
      "epoch": 0.058165548098434,
      "grad_norm": 0.05979042127728462,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 2.2919,
      "step": 13
    },
    {
      "epoch": 0.06263982102908278,
      "grad_norm": 0.06278480589389801,
      "learning_rate": 3.5e-05,
      "loss": 2.1027,
      "step": 14
    },
    {
      "epoch": 0.06711409395973154,
      "grad_norm": 0.05609359219670296,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.2461,
      "step": 15
    },
    {
      "epoch": 0.07158836689038031,
      "grad_norm": 0.0614086352288723,
      "learning_rate": 4e-05,
      "loss": 2.2855,
      "step": 16
    },
    {
      "epoch": 0.07606263982102908,
      "grad_norm": 0.06281686574220657,
      "learning_rate": 4.25e-05,
      "loss": 2.2511,
      "step": 17
    },
    {
      "epoch": 0.08053691275167785,
      "grad_norm": 0.06691695749759674,
      "learning_rate": 4.5e-05,
      "loss": 2.1579,
      "step": 18
    },
    {
      "epoch": 0.08501118568232663,
      "grad_norm": 0.06627006828784943,
      "learning_rate": 4.75e-05,
      "loss": 2.194,
      "step": 19
    },
    {
      "epoch": 0.0894854586129754,
      "grad_norm": 0.07224016636610031,
      "learning_rate": 5e-05,
      "loss": 2.3305,
      "step": 20
    },
    {
      "epoch": 0.09395973154362416,
      "grad_norm": 0.060522738844156265,
      "learning_rate": 4.9997305665425414e-05,
      "loss": 2.2927,
      "step": 21
    },
    {
      "epoch": 0.09843400447427293,
      "grad_norm": 0.05773790180683136,
      "learning_rate": 4.9989223306985084e-05,
      "loss": 2.2183,
      "step": 22
    },
    {
      "epoch": 0.1029082774049217,
      "grad_norm": 0.05926959961652756,
      "learning_rate": 4.9975754860374825e-05,
      "loss": 2.1042,
      "step": 23
    },
    {
      "epoch": 0.10738255033557047,
      "grad_norm": 0.06636251509189606,
      "learning_rate": 4.99569035512392e-05,
      "loss": 2.245,
      "step": 24
    },
    {
      "epoch": 0.11185682326621924,
      "grad_norm": 0.055921752005815506,
      "learning_rate": 4.993267389439901e-05,
      "loss": 2.1514,
      "step": 25
    },
    {
      "epoch": 0.116331096196868,
      "grad_norm": 0.05159250274300575,
      "learning_rate": 4.9903071692770007e-05,
      "loss": 2.3138,
      "step": 26
    },
    {
      "epoch": 0.12080536912751678,
      "grad_norm": 0.05444907769560814,
      "learning_rate": 4.98681040359731e-05,
      "loss": 2.177,
      "step": 27
    },
    {
      "epoch": 0.12527964205816555,
      "grad_norm": 0.053689103573560715,
      "learning_rate": 4.982777929863643e-05,
      "loss": 2.1221,
      "step": 28
    },
    {
      "epoch": 0.1297539149888143,
      "grad_norm": 0.052982673048973083,
      "learning_rate": 4.978210713838971e-05,
      "loss": 2.1504,
      "step": 29
    },
    {
      "epoch": 0.1342281879194631,
      "grad_norm": 0.05092277005314827,
      "learning_rate": 4.9731098493551194e-05,
      "loss": 2.2196,
      "step": 30
    },
    {
      "epoch": 0.13870246085011187,
      "grad_norm": 0.05224297195672989,
      "learning_rate": 4.9674765580508025e-05,
      "loss": 2.1602,
      "step": 31
    },
    {
      "epoch": 0.14317673378076062,
      "grad_norm": 0.05033150315284729,
      "learning_rate": 4.961312189079045e-05,
      "loss": 2.057,
      "step": 32
    },
    {
      "epoch": 0.1476510067114094,
      "grad_norm": 0.052374593913555145,
      "learning_rate": 4.9546182187840656e-05,
      "loss": 2.0742,
      "step": 33
    },
    {
      "epoch": 0.15212527964205816,
      "grad_norm": 0.050675470381975174,
      "learning_rate": 4.947396250347695e-05,
      "loss": 2.2151,
      "step": 34
    },
    {
      "epoch": 0.15659955257270694,
      "grad_norm": 0.05398967117071152,
      "learning_rate": 4.939648013405423e-05,
      "loss": 2.1598,
      "step": 35
    },
    {
      "epoch": 0.1610738255033557,
      "grad_norm": 0.051805514842271805,
      "learning_rate": 4.9313753636321555e-05,
      "loss": 2.169,
      "step": 36
    },
    {
      "epoch": 0.16554809843400448,
      "grad_norm": 0.04822838678956032,
      "learning_rate": 4.9225802822977866e-05,
      "loss": 2.1082,
      "step": 37
    },
    {
      "epoch": 0.17002237136465326,
      "grad_norm": 0.05128757655620575,
      "learning_rate": 4.9132648757926907e-05,
      "loss": 2.2767,
      "step": 38
    },
    {
      "epoch": 0.174496644295302,
      "grad_norm": 0.050592970103025436,
      "learning_rate": 4.9034313751232526e-05,
      "loss": 2.2146,
      "step": 39
    },
    {
      "epoch": 0.1789709172259508,
      "grad_norm": 0.052525170147418976,
      "learning_rate": 4.8930821353775474e-05,
      "loss": 2.2353,
      "step": 40
    },
    {
      "epoch": 0.18344519015659955,
      "grad_norm": 0.050297219306230545,
      "learning_rate": 4.882219635161306e-05,
      "loss": 2.1571,
      "step": 41
    },
    {
      "epoch": 0.18791946308724833,
      "grad_norm": 0.05148237198591232,
      "learning_rate": 4.870846476004296e-05,
      "loss": 2.2254,
      "step": 42
    },
    {
      "epoch": 0.19239373601789708,
      "grad_norm": 0.052405666559934616,
      "learning_rate": 4.8589653817372684e-05,
      "loss": 2.2464,
      "step": 43
    },
    {
      "epoch": 0.19686800894854586,
      "grad_norm": 0.051612552255392075,
      "learning_rate": 4.8465791978396077e-05,
      "loss": 2.2005,
      "step": 44
    },
    {
      "epoch": 0.20134228187919462,
      "grad_norm": 0.054552752524614334,
      "learning_rate": 4.833690890757847e-05,
      "loss": 2.1034,
      "step": 45
    },
    {
      "epoch": 0.20134228187919462,
      "eval_loss": 2.4256694316864014,
      "eval_runtime": 289.4928,
      "eval_samples_per_second": 0.636,
      "eval_steps_per_second": 0.636,
      "step": 45
    },
    {
      "epoch": 0.2058165548098434,
      "grad_norm": 0.05522807687520981,
      "learning_rate": 4.8203035471952225e-05,
      "loss": 2.2148,
      "step": 46
    },
    {
      "epoch": 0.21029082774049218,
      "grad_norm": 0.05309893563389778,
      "learning_rate": 4.80642037337241e-05,
      "loss": 2.2054,
      "step": 47
    },
    {
      "epoch": 0.21476510067114093,
      "grad_norm": 0.05665770173072815,
      "learning_rate": 4.7920446942596535e-05,
      "loss": 2.1856,
      "step": 48
    },
    {
      "epoch": 0.21923937360178972,
      "grad_norm": 0.051858678460121155,
      "learning_rate": 4.777179952780443e-05,
      "loss": 2.1558,
      "step": 49
    },
    {
      "epoch": 0.22371364653243847,
      "grad_norm": 0.05269116908311844,
      "learning_rate": 4.761829708986949e-05,
      "loss": 2.1143,
      "step": 50
    },
    {
      "epoch": 0.22818791946308725,
      "grad_norm": 0.05275040119886398,
      "learning_rate": 4.7459976392074e-05,
      "loss": 2.1701,
      "step": 51
    },
    {
      "epoch": 0.232662192393736,
      "grad_norm": 0.051428090780973434,
      "learning_rate": 4.729687535165618e-05,
      "loss": 2.1786,
      "step": 52
    },
    {
      "epoch": 0.2371364653243848,
      "grad_norm": 0.05071357637643814,
      "learning_rate": 4.712903303072913e-05,
      "loss": 1.9975,
      "step": 53
    },
    {
      "epoch": 0.24161073825503357,
      "grad_norm": 0.05553808808326721,
      "learning_rate": 4.695648962692559e-05,
      "loss": 2.086,
      "step": 54
    },
    {
      "epoch": 0.24608501118568232,
      "grad_norm": 0.056803636252880096,
      "learning_rate": 4.677928646377076e-05,
      "loss": 2.0821,
      "step": 55
    },
    {
      "epoch": 0.2505592841163311,
      "grad_norm": 0.056700658053159714,
      "learning_rate": 4.659746598078546e-05,
      "loss": 2.2197,
      "step": 56
    },
    {
      "epoch": 0.2550335570469799,
      "grad_norm": 0.061487387865781784,
      "learning_rate": 4.641107172332202e-05,
      "loss": 2.2045,
      "step": 57
    },
    {
      "epoch": 0.2595078299776286,
      "grad_norm": 0.055603038519620895,
      "learning_rate": 4.6220148332135306e-05,
      "loss": 2.1375,
      "step": 58
    },
    {
      "epoch": 0.2639821029082774,
      "grad_norm": 0.060784775763750076,
      "learning_rate": 4.6024741532691464e-05,
      "loss": 2.1271,
      "step": 59
    },
    {
      "epoch": 0.2684563758389262,
      "grad_norm": 0.06078394129872322,
      "learning_rate": 4.582489812421679e-05,
      "loss": 2.1142,
      "step": 60
    },
    {
      "epoch": 0.27293064876957496,
      "grad_norm": 0.05928591638803482,
      "learning_rate": 4.562066596848949e-05,
      "loss": 2.2558,
      "step": 61
    },
    {
      "epoch": 0.27740492170022374,
      "grad_norm": 0.05784851685166359,
      "learning_rate": 4.5412093978376986e-05,
      "loss": 2.1869,
      "step": 62
    },
    {
      "epoch": 0.28187919463087246,
      "grad_norm": 0.0587453693151474,
      "learning_rate": 4.519923210612144e-05,
      "loss": 2.1112,
      "step": 63
    },
    {
      "epoch": 0.28635346756152125,
      "grad_norm": 0.05652754753828049,
      "learning_rate": 4.4982131331376354e-05,
      "loss": 2.0209,
      "step": 64
    },
    {
      "epoch": 0.29082774049217003,
      "grad_norm": 0.05855140462517738,
      "learning_rate": 4.476084364899718e-05,
      "loss": 2.0628,
      "step": 65
    },
    {
      "epoch": 0.2953020134228188,
      "grad_norm": 0.059751931577920914,
      "learning_rate": 4.453542205658865e-05,
      "loss": 2.1839,
      "step": 66
    },
    {
      "epoch": 0.29977628635346754,
      "grad_norm": 0.057392723858356476,
      "learning_rate": 4.4305920541812126e-05,
      "loss": 2.0437,
      "step": 67
    },
    {
      "epoch": 0.3042505592841163,
      "grad_norm": 0.05976765975356102,
      "learning_rate": 4.407239406945574e-05,
      "loss": 2.2058,
      "step": 68
    },
    {
      "epoch": 0.3087248322147651,
      "grad_norm": 0.06070901080965996,
      "learning_rate": 4.3834898568270444e-05,
      "loss": 2.1448,
      "step": 69
    },
    {
      "epoch": 0.3131991051454139,
      "grad_norm": 0.057694025337696075,
      "learning_rate": 4.3593490917575384e-05,
      "loss": 2.0374,
      "step": 70
    },
    {
      "epoch": 0.31767337807606266,
      "grad_norm": 0.057838428765535355,
      "learning_rate": 4.3348228933635415e-05,
      "loss": 2.1571,
      "step": 71
    },
    {
      "epoch": 0.3221476510067114,
      "grad_norm": 0.058909159153699875,
      "learning_rate": 4.3099171355814394e-05,
      "loss": 2.2299,
      "step": 72
    },
    {
      "epoch": 0.32662192393736017,
      "grad_norm": 0.061468496918678284,
      "learning_rate": 4.284637783250725e-05,
      "loss": 2.2524,
      "step": 73
    },
    {
      "epoch": 0.33109619686800895,
      "grad_norm": 0.06305054575204849,
      "learning_rate": 4.258990890685442e-05,
      "loss": 2.2769,
      "step": 74
    },
    {
      "epoch": 0.33557046979865773,
      "grad_norm": 0.06071413308382034,
      "learning_rate": 4.2329826002242015e-05,
      "loss": 2.1923,
      "step": 75
    },
    {
      "epoch": 0.3400447427293065,
      "grad_norm": 0.059323471039533615,
      "learning_rate": 4.2066191407591125e-05,
      "loss": 2.1689,
      "step": 76
    },
    {
      "epoch": 0.34451901565995524,
      "grad_norm": 0.06283161044120789,
      "learning_rate": 4.179906826243982e-05,
      "loss": 2.0665,
      "step": 77
    },
    {
      "epoch": 0.348993288590604,
      "grad_norm": 0.06119167432188988,
      "learning_rate": 4.1528520541821506e-05,
      "loss": 2.168,
      "step": 78
    },
    {
      "epoch": 0.3534675615212528,
      "grad_norm": 0.05631568655371666,
      "learning_rate": 4.1254613040943084e-05,
      "loss": 2.1633,
      "step": 79
    },
    {
      "epoch": 0.3579418344519016,
      "grad_norm": 0.06311590224504471,
      "learning_rate": 4.097741135966676e-05,
      "loss": 2.2448,
      "step": 80
    },
    {
      "epoch": 0.3624161073825503,
      "grad_norm": 0.06038917228579521,
      "learning_rate": 4.069698188679912e-05,
      "loss": 2.1406,
      "step": 81
    },
    {
      "epoch": 0.3668903803131991,
      "grad_norm": 0.06018317863345146,
      "learning_rate": 4.0413391784191224e-05,
      "loss": 2.0145,
      "step": 82
    },
    {
      "epoch": 0.3713646532438479,
      "grad_norm": 0.06453920155763626,
      "learning_rate": 4.012670897065361e-05,
      "loss": 2.0058,
      "step": 83
    },
    {
      "epoch": 0.37583892617449666,
      "grad_norm": 0.06324189156293869,
      "learning_rate": 3.983700210568995e-05,
      "loss": 2.1545,
      "step": 84
    },
    {
      "epoch": 0.38031319910514544,
      "grad_norm": 0.06280701607465744,
      "learning_rate": 3.954434057305339e-05,
      "loss": 2.1706,
      "step": 85
    },
    {
      "epoch": 0.38478747203579416,
      "grad_norm": 0.06356626003980637,
      "learning_rate": 3.924879446412934e-05,
      "loss": 2.141,
      "step": 86
    },
    {
      "epoch": 0.38926174496644295,
      "grad_norm": 0.061704233288764954,
      "learning_rate": 3.8950434561148904e-05,
      "loss": 2.0535,
      "step": 87
    },
    {
      "epoch": 0.39373601789709173,
      "grad_norm": 0.06186094880104065,
      "learning_rate": 3.864933232023671e-05,
      "loss": 2.1291,
      "step": 88
    },
    {
      "epoch": 0.3982102908277405,
      "grad_norm": 0.062092263251543045,
      "learning_rate": 3.83455598542975e-05,
      "loss": 2.0795,
      "step": 89
    },
    {
      "epoch": 0.40268456375838924,
      "grad_norm": 0.06686920672655106,
      "learning_rate": 3.803918991574528e-05,
      "loss": 2.2138,
      "step": 90
    },
    {
      "epoch": 0.40268456375838924,
      "eval_loss": 2.4077019691467285,
      "eval_runtime": 289.5088,
      "eval_samples_per_second": 0.636,
      "eval_steps_per_second": 0.636,
      "step": 90
    },
    {
      "epoch": 0.407158836689038,
      "grad_norm": 0.06389721482992172,
      "learning_rate": 3.773029587907945e-05,
      "loss": 2.201,
      "step": 91
    },
    {
      "epoch": 0.4116331096196868,
      "grad_norm": 0.06094789505004883,
      "learning_rate": 3.741895172331181e-05,
      "loss": 2.0209,
      "step": 92
    },
    {
      "epoch": 0.4161073825503356,
      "grad_norm": 0.06485461443662643,
      "learning_rate": 3.71052320142489e-05,
      "loss": 2.2049,
      "step": 93
    },
    {
      "epoch": 0.42058165548098436,
      "grad_norm": 0.06497982889413834,
      "learning_rate": 3.678921188663374e-05,
      "loss": 2.1933,
      "step": 94
    },
    {
      "epoch": 0.4250559284116331,
      "grad_norm": 0.06549432873725891,
      "learning_rate": 3.6470967026151275e-05,
      "loss": 2.1491,
      "step": 95
    },
    {
      "epoch": 0.42953020134228187,
      "grad_norm": 0.06468207389116287,
      "learning_rate": 3.615057365130206e-05,
      "loss": 2.0306,
      "step": 96
    },
    {
      "epoch": 0.43400447427293065,
      "grad_norm": 0.06705638021230698,
      "learning_rate": 3.582810849514808e-05,
      "loss": 2.2625,
      "step": 97
    },
    {
      "epoch": 0.43847874720357943,
      "grad_norm": 0.06647801399230957,
      "learning_rate": 3.5503648786935466e-05,
      "loss": 2.1676,
      "step": 98
    },
    {
      "epoch": 0.4429530201342282,
      "grad_norm": 0.06524338573217392,
      "learning_rate": 3.517727223359845e-05,
      "loss": 2.1717,
      "step": 99
    },
    {
      "epoch": 0.44742729306487694,
      "grad_norm": 0.06328637152910233,
      "learning_rate": 3.484905700114878e-05,
      "loss": 2.1748,
      "step": 100
    },
    {
      "epoch": 0.4519015659955257,
      "grad_norm": 0.0714753046631813,
      "learning_rate": 3.45190816959552e-05,
      "loss": 2.1021,
      "step": 101
    },
    {
      "epoch": 0.4563758389261745,
      "grad_norm": 0.06487017869949341,
      "learning_rate": 3.4187425345917596e-05,
      "loss": 2.0921,
      "step": 102
    },
    {
      "epoch": 0.4608501118568233,
      "grad_norm": 0.07029467821121216,
      "learning_rate": 3.3854167381540036e-05,
      "loss": 2.1023,
      "step": 103
    },
    {
      "epoch": 0.465324384787472,
      "grad_norm": 0.06549900770187378,
      "learning_rate": 3.351938761690748e-05,
      "loss": 2.2034,
      "step": 104
    },
    {
      "epoch": 0.4697986577181208,
      "grad_norm": 0.06699974834918976,
      "learning_rate": 3.318316623057054e-05,
      "loss": 2.1688,
      "step": 105
    },
    {
      "epoch": 0.4742729306487696,
      "grad_norm": 0.06636672466993332,
      "learning_rate": 3.284558374634311e-05,
      "loss": 2.3472,
      "step": 106
    },
    {
      "epoch": 0.47874720357941836,
      "grad_norm": 0.06550615280866623,
      "learning_rate": 3.250672101401707e-05,
      "loss": 2.0626,
      "step": 107
    },
    {
      "epoch": 0.48322147651006714,
      "grad_norm": 0.06411173939704895,
      "learning_rate": 3.2166659189999186e-05,
      "loss": 2.0398,
      "step": 108
    },
    {
      "epoch": 0.48769574944071586,
      "grad_norm": 0.06714348495006561,
      "learning_rate": 3.182547971787433e-05,
      "loss": 2.1168,
      "step": 109
    },
    {
      "epoch": 0.49217002237136465,
      "grad_norm": 0.06583981961011887,
      "learning_rate": 3.148326430890009e-05,
      "loss": 2.246,
      "step": 110
    },
    {
      "epoch": 0.4966442953020134,
      "grad_norm": 0.06999325752258301,
      "learning_rate": 3.114009492243721e-05,
      "loss": 2.0567,
      "step": 111
    },
    {
      "epoch": 0.5011185682326622,
      "grad_norm": 0.06488411128520966,
      "learning_rate": 3.079605374632061e-05,
      "loss": 2.1187,
      "step": 112
    }
  ],
  "logging_steps": 1,
  "max_steps": 223,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 56,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.758140832781435e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}