nttx's picture
Training in progress, step 200, checkpoint
a3929ba verified
{
"best_metric": 2.167288064956665,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.0672777731057102,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00033638886552855103,
"grad_norm": 0.07795742154121399,
"learning_rate": 3.3333333333333333e-06,
"loss": 2.7769,
"step": 1
},
{
"epoch": 0.00033638886552855103,
"eval_loss": 2.455552101135254,
"eval_runtime": 133.5909,
"eval_samples_per_second": 37.48,
"eval_steps_per_second": 18.744,
"step": 1
},
{
"epoch": 0.0006727777310571021,
"grad_norm": 0.091961570084095,
"learning_rate": 6.666666666666667e-06,
"loss": 2.615,
"step": 2
},
{
"epoch": 0.001009166596585653,
"grad_norm": 0.09707869589328766,
"learning_rate": 1e-05,
"loss": 2.4234,
"step": 3
},
{
"epoch": 0.0013455554621142041,
"grad_norm": 0.09777762740850449,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.4821,
"step": 4
},
{
"epoch": 0.001681944327642755,
"grad_norm": 0.16171760857105255,
"learning_rate": 1.6666666666666667e-05,
"loss": 2.4558,
"step": 5
},
{
"epoch": 0.002018333193171306,
"grad_norm": 0.10559370368719101,
"learning_rate": 2e-05,
"loss": 2.4765,
"step": 6
},
{
"epoch": 0.002354722058699857,
"grad_norm": 0.11369410157203674,
"learning_rate": 2.3333333333333336e-05,
"loss": 2.585,
"step": 7
},
{
"epoch": 0.0026911109242284082,
"grad_norm": 0.1158774346113205,
"learning_rate": 2.6666666666666667e-05,
"loss": 2.4602,
"step": 8
},
{
"epoch": 0.003027499789756959,
"grad_norm": 0.12309759110212326,
"learning_rate": 3e-05,
"loss": 2.4651,
"step": 9
},
{
"epoch": 0.00336388865528551,
"grad_norm": 0.13319513201713562,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.309,
"step": 10
},
{
"epoch": 0.0037002775208140612,
"grad_norm": 0.12856201827526093,
"learning_rate": 3.6666666666666666e-05,
"loss": 2.4663,
"step": 11
},
{
"epoch": 0.004036666386342612,
"grad_norm": 0.12185679376125336,
"learning_rate": 4e-05,
"loss": 2.4488,
"step": 12
},
{
"epoch": 0.004373055251871163,
"grad_norm": 0.12302099913358688,
"learning_rate": 4.3333333333333334e-05,
"loss": 2.3317,
"step": 13
},
{
"epoch": 0.004709444117399714,
"grad_norm": 0.1280185580253601,
"learning_rate": 4.666666666666667e-05,
"loss": 2.3823,
"step": 14
},
{
"epoch": 0.005045832982928265,
"grad_norm": 0.13406257331371307,
"learning_rate": 5e-05,
"loss": 2.3536,
"step": 15
},
{
"epoch": 0.0053822218484568165,
"grad_norm": 0.1333453357219696,
"learning_rate": 5.333333333333333e-05,
"loss": 2.4247,
"step": 16
},
{
"epoch": 0.005718610713985367,
"grad_norm": 0.12794539332389832,
"learning_rate": 5.666666666666667e-05,
"loss": 2.4933,
"step": 17
},
{
"epoch": 0.006054999579513918,
"grad_norm": 0.12640050053596497,
"learning_rate": 6e-05,
"loss": 2.4592,
"step": 18
},
{
"epoch": 0.0063913884450424695,
"grad_norm": 0.1311822533607483,
"learning_rate": 6.333333333333333e-05,
"loss": 2.2846,
"step": 19
},
{
"epoch": 0.00672777731057102,
"grad_norm": 0.13246804475784302,
"learning_rate": 6.666666666666667e-05,
"loss": 2.4061,
"step": 20
},
{
"epoch": 0.007064166176099571,
"grad_norm": 0.15557919442653656,
"learning_rate": 7e-05,
"loss": 2.2899,
"step": 21
},
{
"epoch": 0.0074005550416281225,
"grad_norm": 0.13837924599647522,
"learning_rate": 7.333333333333333e-05,
"loss": 2.5681,
"step": 22
},
{
"epoch": 0.007736943907156673,
"grad_norm": 0.1440717875957489,
"learning_rate": 7.666666666666667e-05,
"loss": 2.3665,
"step": 23
},
{
"epoch": 0.008073332772685224,
"grad_norm": 0.15145528316497803,
"learning_rate": 8e-05,
"loss": 2.2948,
"step": 24
},
{
"epoch": 0.008409721638213775,
"grad_norm": 0.1539720594882965,
"learning_rate": 8.333333333333334e-05,
"loss": 2.3214,
"step": 25
},
{
"epoch": 0.008746110503742325,
"grad_norm": 0.14122752845287323,
"learning_rate": 8.666666666666667e-05,
"loss": 2.2708,
"step": 26
},
{
"epoch": 0.009082499369270877,
"grad_norm": 0.15089313685894012,
"learning_rate": 9e-05,
"loss": 2.3226,
"step": 27
},
{
"epoch": 0.009418888234799428,
"grad_norm": 0.200881689786911,
"learning_rate": 9.333333333333334e-05,
"loss": 2.3429,
"step": 28
},
{
"epoch": 0.00975527710032798,
"grad_norm": 0.1588452160358429,
"learning_rate": 9.666666666666667e-05,
"loss": 2.2316,
"step": 29
},
{
"epoch": 0.01009166596585653,
"grad_norm": 0.18878738582134247,
"learning_rate": 0.0001,
"loss": 2.249,
"step": 30
},
{
"epoch": 0.010428054831385081,
"grad_norm": 0.19466233253479004,
"learning_rate": 9.999146252290264e-05,
"loss": 2.2815,
"step": 31
},
{
"epoch": 0.010764443696913633,
"grad_norm": 0.23344077169895172,
"learning_rate": 9.996585300715116e-05,
"loss": 2.2785,
"step": 32
},
{
"epoch": 0.011100832562442183,
"grad_norm": 0.23798418045043945,
"learning_rate": 9.99231801983717e-05,
"loss": 2.0524,
"step": 33
},
{
"epoch": 0.011437221427970734,
"grad_norm": 0.19358737766742706,
"learning_rate": 9.986345866928941e-05,
"loss": 2.0744,
"step": 34
},
{
"epoch": 0.011773610293499286,
"grad_norm": 0.19671595096588135,
"learning_rate": 9.978670881475172e-05,
"loss": 2.1176,
"step": 35
},
{
"epoch": 0.012109999159027836,
"grad_norm": 0.20317138731479645,
"learning_rate": 9.96929568447637e-05,
"loss": 2.2187,
"step": 36
},
{
"epoch": 0.012446388024556387,
"grad_norm": 0.19243532419204712,
"learning_rate": 9.958223477553714e-05,
"loss": 1.9553,
"step": 37
},
{
"epoch": 0.012782776890084939,
"grad_norm": 0.17963586747646332,
"learning_rate": 9.94545804185573e-05,
"loss": 2.0921,
"step": 38
},
{
"epoch": 0.013119165755613489,
"grad_norm": 0.20728521049022675,
"learning_rate": 9.931003736767013e-05,
"loss": 2.3093,
"step": 39
},
{
"epoch": 0.01345555462114204,
"grad_norm": 0.2048047035932541,
"learning_rate": 9.91486549841951e-05,
"loss": 2.2137,
"step": 40
},
{
"epoch": 0.013791943486670592,
"grad_norm": 0.199965700507164,
"learning_rate": 9.89704883800683e-05,
"loss": 2.1698,
"step": 41
},
{
"epoch": 0.014128332352199142,
"grad_norm": 0.2382458597421646,
"learning_rate": 9.877559839902184e-05,
"loss": 2.1951,
"step": 42
},
{
"epoch": 0.014464721217727693,
"grad_norm": 0.19734260439872742,
"learning_rate": 9.85640515958057e-05,
"loss": 2.118,
"step": 43
},
{
"epoch": 0.014801110083256245,
"grad_norm": 0.23887623846530914,
"learning_rate": 9.833592021345937e-05,
"loss": 2.133,
"step": 44
},
{
"epoch": 0.015137498948784795,
"grad_norm": 0.21855773031711578,
"learning_rate": 9.809128215864097e-05,
"loss": 2.182,
"step": 45
},
{
"epoch": 0.015473887814313346,
"grad_norm": 0.24946734309196472,
"learning_rate": 9.783022097502204e-05,
"loss": 2.2907,
"step": 46
},
{
"epoch": 0.015810276679841896,
"grad_norm": 0.23966045677661896,
"learning_rate": 9.755282581475769e-05,
"loss": 2.1424,
"step": 47
},
{
"epoch": 0.016146665545370448,
"grad_norm": 0.29373985528945923,
"learning_rate": 9.725919140804099e-05,
"loss": 2.2907,
"step": 48
},
{
"epoch": 0.016483054410899,
"grad_norm": 0.2858251631259918,
"learning_rate": 9.694941803075283e-05,
"loss": 1.9196,
"step": 49
},
{
"epoch": 0.01681944327642755,
"grad_norm": 0.44232481718063354,
"learning_rate": 9.662361147021779e-05,
"loss": 2.2586,
"step": 50
},
{
"epoch": 0.01681944327642755,
"eval_loss": 2.229457378387451,
"eval_runtime": 133.8125,
"eval_samples_per_second": 37.418,
"eval_steps_per_second": 18.713,
"step": 50
},
{
"epoch": 0.017155832141956102,
"grad_norm": 0.2517932653427124,
"learning_rate": 9.628188298907782e-05,
"loss": 2.5462,
"step": 51
},
{
"epoch": 0.01749222100748465,
"grad_norm": 0.2670835554599762,
"learning_rate": 9.592434928729616e-05,
"loss": 2.5628,
"step": 52
},
{
"epoch": 0.017828609873013202,
"grad_norm": 0.25449806451797485,
"learning_rate": 9.555113246230442e-05,
"loss": 2.3425,
"step": 53
},
{
"epoch": 0.018164998738541754,
"grad_norm": 0.2293660193681717,
"learning_rate": 9.516235996730645e-05,
"loss": 2.525,
"step": 54
},
{
"epoch": 0.018501387604070305,
"grad_norm": 0.20520225167274475,
"learning_rate": 9.475816456775313e-05,
"loss": 2.3914,
"step": 55
},
{
"epoch": 0.018837776469598857,
"grad_norm": 0.1786617934703827,
"learning_rate": 9.43386842960031e-05,
"loss": 2.4665,
"step": 56
},
{
"epoch": 0.01917416533512741,
"grad_norm": 0.160075381398201,
"learning_rate": 9.39040624041849e-05,
"loss": 2.2621,
"step": 57
},
{
"epoch": 0.01951055420065596,
"grad_norm": 0.1475311666727066,
"learning_rate": 9.345444731527642e-05,
"loss": 2.2723,
"step": 58
},
{
"epoch": 0.019846943066184508,
"grad_norm": 0.1324007511138916,
"learning_rate": 9.298999257241863e-05,
"loss": 2.4622,
"step": 59
},
{
"epoch": 0.02018333193171306,
"grad_norm": 0.12696845829486847,
"learning_rate": 9.251085678648072e-05,
"loss": 2.3154,
"step": 60
},
{
"epoch": 0.02051972079724161,
"grad_norm": 0.12675370275974274,
"learning_rate": 9.201720358189464e-05,
"loss": 2.179,
"step": 61
},
{
"epoch": 0.020856109662770163,
"grad_norm": 0.11854014545679092,
"learning_rate": 9.150920154077754e-05,
"loss": 2.4794,
"step": 62
},
{
"epoch": 0.021192498528298714,
"grad_norm": 0.134128600358963,
"learning_rate": 9.098702414536107e-05,
"loss": 2.0619,
"step": 63
},
{
"epoch": 0.021528887393827266,
"grad_norm": 0.1273840367794037,
"learning_rate": 9.045084971874738e-05,
"loss": 2.1111,
"step": 64
},
{
"epoch": 0.021865276259355814,
"grad_norm": 0.11819684505462646,
"learning_rate": 8.9900861364012e-05,
"loss": 2.3178,
"step": 65
},
{
"epoch": 0.022201665124884366,
"grad_norm": 0.12865498661994934,
"learning_rate": 8.933724690167417e-05,
"loss": 2.3396,
"step": 66
},
{
"epoch": 0.022538053990412917,
"grad_norm": 0.13002778589725494,
"learning_rate": 8.876019880555649e-05,
"loss": 2.1979,
"step": 67
},
{
"epoch": 0.02287444285594147,
"grad_norm": 0.12023420631885529,
"learning_rate": 8.816991413705516e-05,
"loss": 2.2783,
"step": 68
},
{
"epoch": 0.02321083172147002,
"grad_norm": 0.1349371373653412,
"learning_rate": 8.756659447784368e-05,
"loss": 2.257,
"step": 69
},
{
"epoch": 0.023547220586998572,
"grad_norm": 0.13931462168693542,
"learning_rate": 8.695044586103296e-05,
"loss": 2.058,
"step": 70
},
{
"epoch": 0.02388360945252712,
"grad_norm": 0.12889568507671356,
"learning_rate": 8.632167870081121e-05,
"loss": 2.1331,
"step": 71
},
{
"epoch": 0.02421999831805567,
"grad_norm": 0.13493181765079498,
"learning_rate": 8.568050772058762e-05,
"loss": 2.1518,
"step": 72
},
{
"epoch": 0.024556387183584223,
"grad_norm": 0.12535114586353302,
"learning_rate": 8.502715187966455e-05,
"loss": 2.3403,
"step": 73
},
{
"epoch": 0.024892776049112775,
"grad_norm": 0.14284498989582062,
"learning_rate": 8.436183429846313e-05,
"loss": 2.2651,
"step": 74
},
{
"epoch": 0.025229164914641326,
"grad_norm": 0.1374937891960144,
"learning_rate": 8.368478218232787e-05,
"loss": 2.2428,
"step": 75
},
{
"epoch": 0.025565553780169878,
"grad_norm": 0.14151272177696228,
"learning_rate": 8.299622674393614e-05,
"loss": 2.1402,
"step": 76
},
{
"epoch": 0.025901942645698426,
"grad_norm": 0.14077945053577423,
"learning_rate": 8.229640312433937e-05,
"loss": 2.2438,
"step": 77
},
{
"epoch": 0.026238331511226978,
"grad_norm": 0.14996446669101715,
"learning_rate": 8.158555031266254e-05,
"loss": 2.0749,
"step": 78
},
{
"epoch": 0.02657472037675553,
"grad_norm": 0.14320829510688782,
"learning_rate": 8.086391106448965e-05,
"loss": 2.1752,
"step": 79
},
{
"epoch": 0.02691110924228408,
"grad_norm": 0.1642449051141739,
"learning_rate": 8.013173181896283e-05,
"loss": 2.2197,
"step": 80
},
{
"epoch": 0.027247498107812632,
"grad_norm": 0.14916405081748962,
"learning_rate": 7.938926261462366e-05,
"loss": 2.0808,
"step": 81
},
{
"epoch": 0.027583886973341184,
"grad_norm": 0.14916309714317322,
"learning_rate": 7.863675700402526e-05,
"loss": 2.1206,
"step": 82
},
{
"epoch": 0.027920275838869732,
"grad_norm": 0.15080957114696503,
"learning_rate": 7.787447196714427e-05,
"loss": 2.2949,
"step": 83
},
{
"epoch": 0.028256664704398284,
"grad_norm": 0.14866329729557037,
"learning_rate": 7.710266782362247e-05,
"loss": 1.9822,
"step": 84
},
{
"epoch": 0.028593053569926835,
"grad_norm": 0.15501651167869568,
"learning_rate": 7.63216081438678e-05,
"loss": 2.2537,
"step": 85
},
{
"epoch": 0.028929442435455387,
"grad_norm": 0.15602312982082367,
"learning_rate": 7.553155965904535e-05,
"loss": 2.0236,
"step": 86
},
{
"epoch": 0.029265831300983938,
"grad_norm": 0.14871007204055786,
"learning_rate": 7.473279216998895e-05,
"loss": 2.1303,
"step": 87
},
{
"epoch": 0.02960222016651249,
"grad_norm": 0.16841718554496765,
"learning_rate": 7.392557845506432e-05,
"loss": 2.2095,
"step": 88
},
{
"epoch": 0.029938609032041038,
"grad_norm": 0.18683014810085297,
"learning_rate": 7.311019417701566e-05,
"loss": 2.1266,
"step": 89
},
{
"epoch": 0.03027499789756959,
"grad_norm": 0.16032518446445465,
"learning_rate": 7.228691778882693e-05,
"loss": 2.2099,
"step": 90
},
{
"epoch": 0.03061138676309814,
"grad_norm": 0.1630275994539261,
"learning_rate": 7.145603043863045e-05,
"loss": 2.0045,
"step": 91
},
{
"epoch": 0.030947775628626693,
"grad_norm": 0.18670861423015594,
"learning_rate": 7.061781587369519e-05,
"loss": 1.941,
"step": 92
},
{
"epoch": 0.03128416449415524,
"grad_norm": 0.17295370995998383,
"learning_rate": 6.977256034352712e-05,
"loss": 2.0762,
"step": 93
},
{
"epoch": 0.03162055335968379,
"grad_norm": 0.17951808869838715,
"learning_rate": 6.892055250211552e-05,
"loss": 2.0782,
"step": 94
},
{
"epoch": 0.031956942225212344,
"grad_norm": 0.19968754053115845,
"learning_rate": 6.806208330935766e-05,
"loss": 2.0776,
"step": 95
},
{
"epoch": 0.032293331090740895,
"grad_norm": 0.20060695707798004,
"learning_rate": 6.719744593169641e-05,
"loss": 2.0879,
"step": 96
},
{
"epoch": 0.03262971995626945,
"grad_norm": 0.22675327956676483,
"learning_rate": 6.632693564200416e-05,
"loss": 2.1727,
"step": 97
},
{
"epoch": 0.032966108821798,
"grad_norm": 0.2281123250722885,
"learning_rate": 6.545084971874738e-05,
"loss": 2.1492,
"step": 98
},
{
"epoch": 0.03330249768732655,
"grad_norm": 0.27324235439300537,
"learning_rate": 6.456948734446624e-05,
"loss": 2.0096,
"step": 99
},
{
"epoch": 0.0336388865528551,
"grad_norm": 0.3571203052997589,
"learning_rate": 6.368314950360415e-05,
"loss": 2.0528,
"step": 100
},
{
"epoch": 0.0336388865528551,
"eval_loss": 2.184495449066162,
"eval_runtime": 134.0079,
"eval_samples_per_second": 37.363,
"eval_steps_per_second": 18.685,
"step": 100
},
{
"epoch": 0.03397527541838365,
"grad_norm": 0.1273975670337677,
"learning_rate": 6.279213887972179e-05,
"loss": 2.5001,
"step": 101
},
{
"epoch": 0.034311664283912205,
"grad_norm": 0.1580890268087387,
"learning_rate": 6.189675975213094e-05,
"loss": 2.6171,
"step": 102
},
{
"epoch": 0.034648053149440756,
"grad_norm": 0.14681027829647064,
"learning_rate": 6.099731789198344e-05,
"loss": 2.3392,
"step": 103
},
{
"epoch": 0.0349844420149693,
"grad_norm": 0.16795434057712555,
"learning_rate": 6.009412045785051e-05,
"loss": 2.3509,
"step": 104
},
{
"epoch": 0.03532083088049785,
"grad_norm": 0.15639738738536835,
"learning_rate": 5.918747589082853e-05,
"loss": 2.2799,
"step": 105
},
{
"epoch": 0.035657219746026404,
"grad_norm": 0.1573394536972046,
"learning_rate": 5.82776938092065e-05,
"loss": 2.5607,
"step": 106
},
{
"epoch": 0.035993608611554956,
"grad_norm": 0.1536206305027008,
"learning_rate": 5.736508490273188e-05,
"loss": 2.222,
"step": 107
},
{
"epoch": 0.03632999747708351,
"grad_norm": 0.15485522150993347,
"learning_rate": 5.644996082651017e-05,
"loss": 2.3612,
"step": 108
},
{
"epoch": 0.03666638634261206,
"grad_norm": 0.14206035435199738,
"learning_rate": 5.553263409457504e-05,
"loss": 2.3203,
"step": 109
},
{
"epoch": 0.03700277520814061,
"grad_norm": 0.1353464424610138,
"learning_rate": 5.4613417973165106e-05,
"loss": 2.2831,
"step": 110
},
{
"epoch": 0.03733916407366916,
"grad_norm": 0.12393804639577866,
"learning_rate": 5.3692626373743706e-05,
"loss": 2.2349,
"step": 111
},
{
"epoch": 0.037675552939197714,
"grad_norm": 0.13074256479740143,
"learning_rate": 5.27705737457985e-05,
"loss": 2.1481,
"step": 112
},
{
"epoch": 0.038011941804726265,
"grad_norm": 0.1324545294046402,
"learning_rate": 5.184757496945726e-05,
"loss": 2.2031,
"step": 113
},
{
"epoch": 0.03834833067025482,
"grad_norm": 0.14374986290931702,
"learning_rate": 5.092394524795649e-05,
"loss": 2.2458,
"step": 114
},
{
"epoch": 0.03868471953578337,
"grad_norm": 0.12872225046157837,
"learning_rate": 5e-05,
"loss": 2.1645,
"step": 115
},
{
"epoch": 0.03902110840131192,
"grad_norm": 0.12324129045009613,
"learning_rate": 4.907605475204352e-05,
"loss": 2.2346,
"step": 116
},
{
"epoch": 0.039357497266840465,
"grad_norm": 0.12691381573677063,
"learning_rate": 4.8152425030542766e-05,
"loss": 2.1249,
"step": 117
},
{
"epoch": 0.039693886132369016,
"grad_norm": 0.11859089136123657,
"learning_rate": 4.72294262542015e-05,
"loss": 2.0766,
"step": 118
},
{
"epoch": 0.04003027499789757,
"grad_norm": 0.12147951871156693,
"learning_rate": 4.6307373626256306e-05,
"loss": 2.3106,
"step": 119
},
{
"epoch": 0.04036666386342612,
"grad_norm": 0.12418749928474426,
"learning_rate": 4.5386582026834906e-05,
"loss": 2.0982,
"step": 120
},
{
"epoch": 0.04070305272895467,
"grad_norm": 0.12721975147724152,
"learning_rate": 4.446736590542497e-05,
"loss": 2.2366,
"step": 121
},
{
"epoch": 0.04103944159448322,
"grad_norm": 0.13671071827411652,
"learning_rate": 4.3550039173489845e-05,
"loss": 2.1654,
"step": 122
},
{
"epoch": 0.041375830460011774,
"grad_norm": 0.13127440214157104,
"learning_rate": 4.2634915097268115e-05,
"loss": 2.2255,
"step": 123
},
{
"epoch": 0.041712219325540326,
"grad_norm": 0.14041757583618164,
"learning_rate": 4.1722306190793495e-05,
"loss": 2.3629,
"step": 124
},
{
"epoch": 0.04204860819106888,
"grad_norm": 0.12985271215438843,
"learning_rate": 4.0812524109171476e-05,
"loss": 2.2141,
"step": 125
},
{
"epoch": 0.04238499705659743,
"grad_norm": 0.14057950675487518,
"learning_rate": 3.99058795421495e-05,
"loss": 2.0291,
"step": 126
},
{
"epoch": 0.04272138592212598,
"grad_norm": 0.1375603973865509,
"learning_rate": 3.9002682108016585e-05,
"loss": 2.0766,
"step": 127
},
{
"epoch": 0.04305777478765453,
"grad_norm": 0.15876489877700806,
"learning_rate": 3.8103240247869075e-05,
"loss": 2.2225,
"step": 128
},
{
"epoch": 0.04339416365318308,
"grad_norm": 0.1333220899105072,
"learning_rate": 3.720786112027822e-05,
"loss": 2.0972,
"step": 129
},
{
"epoch": 0.04373055251871163,
"grad_norm": 0.14338713884353638,
"learning_rate": 3.631685049639586e-05,
"loss": 1.9242,
"step": 130
},
{
"epoch": 0.04406694138424018,
"grad_norm": 0.14646734297275543,
"learning_rate": 3.543051265553377e-05,
"loss": 2.1472,
"step": 131
},
{
"epoch": 0.04440333024976873,
"grad_norm": 0.14863519370555878,
"learning_rate": 3.4549150281252636e-05,
"loss": 2.1101,
"step": 132
},
{
"epoch": 0.04473971911529728,
"grad_norm": 0.14415816962718964,
"learning_rate": 3.367306435799584e-05,
"loss": 1.9563,
"step": 133
},
{
"epoch": 0.045076107980825834,
"grad_norm": 0.1510019600391388,
"learning_rate": 3.2802554068303596e-05,
"loss": 2.344,
"step": 134
},
{
"epoch": 0.045412496846354386,
"grad_norm": 0.15380419790744781,
"learning_rate": 3.1937916690642356e-05,
"loss": 2.0964,
"step": 135
},
{
"epoch": 0.04574888571188294,
"grad_norm": 0.15402600169181824,
"learning_rate": 3.107944749788449e-05,
"loss": 2.1511,
"step": 136
},
{
"epoch": 0.04608527457741149,
"grad_norm": 0.1569417119026184,
"learning_rate": 3.0227439656472877e-05,
"loss": 2.2019,
"step": 137
},
{
"epoch": 0.04642166344294004,
"grad_norm": 0.15563955903053284,
"learning_rate": 2.9382184126304834e-05,
"loss": 2.1347,
"step": 138
},
{
"epoch": 0.04675805230846859,
"grad_norm": 0.16049978137016296,
"learning_rate": 2.8543969561369556e-05,
"loss": 2.0268,
"step": 139
},
{
"epoch": 0.047094441173997144,
"grad_norm": 0.1715925931930542,
"learning_rate": 2.771308221117309e-05,
"loss": 1.9335,
"step": 140
},
{
"epoch": 0.04743083003952569,
"grad_norm": 0.1669202297925949,
"learning_rate": 2.688980582298435e-05,
"loss": 1.9606,
"step": 141
},
{
"epoch": 0.04776721890505424,
"grad_norm": 0.1874368041753769,
"learning_rate": 2.607442154493568e-05,
"loss": 2.1294,
"step": 142
},
{
"epoch": 0.04810360777058279,
"grad_norm": 0.19604210555553436,
"learning_rate": 2.5267207830011068e-05,
"loss": 2.2134,
"step": 143
},
{
"epoch": 0.04843999663611134,
"grad_norm": 0.2135860174894333,
"learning_rate": 2.446844034095466e-05,
"loss": 1.9938,
"step": 144
},
{
"epoch": 0.048776385501639895,
"grad_norm": 0.21586836874485016,
"learning_rate": 2.3678391856132204e-05,
"loss": 2.1866,
"step": 145
},
{
"epoch": 0.049112774367168446,
"grad_norm": 0.21214084327220917,
"learning_rate": 2.2897332176377528e-05,
"loss": 2.1615,
"step": 146
},
{
"epoch": 0.049449163232697,
"grad_norm": 0.2273048311471939,
"learning_rate": 2.2125528032855724e-05,
"loss": 2.049,
"step": 147
},
{
"epoch": 0.04978555209822555,
"grad_norm": 0.2707260251045227,
"learning_rate": 2.136324299597474e-05,
"loss": 2.0469,
"step": 148
},
{
"epoch": 0.0501219409637541,
"grad_norm": 0.3056899309158325,
"learning_rate": 2.061073738537635e-05,
"loss": 2.0308,
"step": 149
},
{
"epoch": 0.05045832982928265,
"grad_norm": 0.4177829921245575,
"learning_rate": 1.9868268181037185e-05,
"loss": 2.1673,
"step": 150
},
{
"epoch": 0.05045832982928265,
"eval_loss": 2.1688923835754395,
"eval_runtime": 135.2349,
"eval_samples_per_second": 37.024,
"eval_steps_per_second": 18.516,
"step": 150
},
{
"epoch": 0.050794718694811204,
"grad_norm": 0.08879049122333527,
"learning_rate": 1.9136088935510362e-05,
"loss": 2.5541,
"step": 151
},
{
"epoch": 0.051131107560339756,
"grad_norm": 0.09826517105102539,
"learning_rate": 1.8414449687337464e-05,
"loss": 2.3588,
"step": 152
},
{
"epoch": 0.0514674964258683,
"grad_norm": 0.09574924409389496,
"learning_rate": 1.7703596875660645e-05,
"loss": 2.3422,
"step": 153
},
{
"epoch": 0.05180388529139685,
"grad_norm": 0.10143424570560455,
"learning_rate": 1.700377325606388e-05,
"loss": 2.4938,
"step": 154
},
{
"epoch": 0.052140274156925404,
"grad_norm": 0.10083989053964615,
"learning_rate": 1.631521781767214e-05,
"loss": 2.3884,
"step": 155
},
{
"epoch": 0.052476663022453955,
"grad_norm": 0.1043684333562851,
"learning_rate": 1.5638165701536868e-05,
"loss": 2.2918,
"step": 156
},
{
"epoch": 0.05281305188798251,
"grad_norm": 0.11348860710859299,
"learning_rate": 1.4972848120335453e-05,
"loss": 2.2411,
"step": 157
},
{
"epoch": 0.05314944075351106,
"grad_norm": 0.13526681065559387,
"learning_rate": 1.4319492279412388e-05,
"loss": 2.3494,
"step": 158
},
{
"epoch": 0.05348582961903961,
"grad_norm": 0.10417280346155167,
"learning_rate": 1.3678321299188801e-05,
"loss": 2.3384,
"step": 159
},
{
"epoch": 0.05382221848456816,
"grad_norm": 0.11089330166578293,
"learning_rate": 1.3049554138967051e-05,
"loss": 2.3226,
"step": 160
},
{
"epoch": 0.05415860735009671,
"grad_norm": 0.11724156141281128,
"learning_rate": 1.2433405522156332e-05,
"loss": 2.2407,
"step": 161
},
{
"epoch": 0.054494996215625265,
"grad_norm": 0.1157764121890068,
"learning_rate": 1.183008586294485e-05,
"loss": 2.1198,
"step": 162
},
{
"epoch": 0.054831385081153816,
"grad_norm": 0.119741290807724,
"learning_rate": 1.1239801194443506e-05,
"loss": 2.0437,
"step": 163
},
{
"epoch": 0.05516777394668237,
"grad_norm": 0.11613930761814117,
"learning_rate": 1.066275309832584e-05,
"loss": 2.0914,
"step": 164
},
{
"epoch": 0.05550416281221091,
"grad_norm": 0.12045928835868835,
"learning_rate": 1.0099138635988026e-05,
"loss": 2.3228,
"step": 165
},
{
"epoch": 0.055840551677739464,
"grad_norm": 0.12162400037050247,
"learning_rate": 9.549150281252633e-06,
"loss": 2.163,
"step": 166
},
{
"epoch": 0.056176940543268016,
"grad_norm": 0.12336426973342896,
"learning_rate": 9.012975854638949e-06,
"loss": 2.2464,
"step": 167
},
{
"epoch": 0.05651332940879657,
"grad_norm": 0.12101393938064575,
"learning_rate": 8.490798459222476e-06,
"loss": 2.1465,
"step": 168
},
{
"epoch": 0.05684971827432512,
"grad_norm": 0.2126462608575821,
"learning_rate": 7.982796418105371e-06,
"loss": 2.2171,
"step": 169
},
{
"epoch": 0.05718610713985367,
"grad_norm": 0.12185154110193253,
"learning_rate": 7.489143213519301e-06,
"loss": 2.1763,
"step": 170
},
{
"epoch": 0.05752249600538222,
"grad_norm": 0.11774197220802307,
"learning_rate": 7.010007427581378e-06,
"loss": 2.1448,
"step": 171
},
{
"epoch": 0.05785888487091077,
"grad_norm": 0.12424536049365997,
"learning_rate": 6.5455526847235825e-06,
"loss": 2.1086,
"step": 172
},
{
"epoch": 0.058195273736439325,
"grad_norm": 0.12645591795444489,
"learning_rate": 6.0959375958151045e-06,
"loss": 2.0354,
"step": 173
},
{
"epoch": 0.058531662601967877,
"grad_norm": 0.12034987658262253,
"learning_rate": 5.6613157039969055e-06,
"loss": 2.1267,
"step": 174
},
{
"epoch": 0.05886805146749643,
"grad_norm": 0.13363537192344666,
"learning_rate": 5.241835432246889e-06,
"loss": 2.2255,
"step": 175
},
{
"epoch": 0.05920444033302498,
"grad_norm": 0.14202825725078583,
"learning_rate": 4.837640032693558e-06,
"loss": 2.3348,
"step": 176
},
{
"epoch": 0.05954082919855353,
"grad_norm": 0.13769714534282684,
"learning_rate": 4.448867537695578e-06,
"loss": 2.1034,
"step": 177
},
{
"epoch": 0.059877218064082076,
"grad_norm": 0.1326625496149063,
"learning_rate": 4.075650712703849e-06,
"loss": 2.1942,
"step": 178
},
{
"epoch": 0.06021360692961063,
"grad_norm": 0.13974831998348236,
"learning_rate": 3.71811701092219e-06,
"loss": 2.3027,
"step": 179
},
{
"epoch": 0.06054999579513918,
"grad_norm": 0.13422763347625732,
"learning_rate": 3.376388529782215e-06,
"loss": 2.2325,
"step": 180
},
{
"epoch": 0.06088638466066773,
"grad_norm": 0.14441807568073273,
"learning_rate": 3.0505819692471792e-06,
"loss": 2.0871,
"step": 181
},
{
"epoch": 0.06122277352619628,
"grad_norm": 0.13802383840084076,
"learning_rate": 2.7408085919590264e-06,
"loss": 2.0057,
"step": 182
},
{
"epoch": 0.061559162391724834,
"grad_norm": 0.13615332543849945,
"learning_rate": 2.4471741852423237e-06,
"loss": 2.1748,
"step": 183
},
{
"epoch": 0.061895551257253385,
"grad_norm": 0.13655613362789154,
"learning_rate": 2.1697790249779636e-06,
"loss": 2.0697,
"step": 184
},
{
"epoch": 0.06223194012278194,
"grad_norm": 0.1467704176902771,
"learning_rate": 1.908717841359048e-06,
"loss": 2.0321,
"step": 185
},
{
"epoch": 0.06256832898831048,
"grad_norm": 0.16436661779880524,
"learning_rate": 1.6640797865406288e-06,
"loss": 2.1359,
"step": 186
},
{
"epoch": 0.06290471785383904,
"grad_norm": 0.1564408838748932,
"learning_rate": 1.4359484041943038e-06,
"loss": 1.9555,
"step": 187
},
{
"epoch": 0.06324110671936758,
"grad_norm": 0.15665636956691742,
"learning_rate": 1.2244016009781701e-06,
"loss": 2.0872,
"step": 188
},
{
"epoch": 0.06357749558489614,
"grad_norm": 0.15910153090953827,
"learning_rate": 1.0295116199317057e-06,
"loss": 2.0794,
"step": 189
},
{
"epoch": 0.06391388445042469,
"grad_norm": 0.1592608243227005,
"learning_rate": 8.513450158049108e-07,
"loss": 2.0614,
"step": 190
},
{
"epoch": 0.06425027331595325,
"grad_norm": 0.15927056968212128,
"learning_rate": 6.899626323298713e-07,
"loss": 2.0995,
"step": 191
},
{
"epoch": 0.06458666218148179,
"grad_norm": 0.17379838228225708,
"learning_rate": 5.454195814427021e-07,
"loss": 2.1072,
"step": 192
},
{
"epoch": 0.06492305104701035,
"grad_norm": 0.17387740314006805,
"learning_rate": 4.177652244628627e-07,
"loss": 2.1153,
"step": 193
},
{
"epoch": 0.0652594399125389,
"grad_norm": 0.20028245449066162,
"learning_rate": 3.0704315523631953e-07,
"loss": 1.8804,
"step": 194
},
{
"epoch": 0.06559582877806745,
"grad_norm": 0.1880960315465927,
"learning_rate": 2.1329118524827662e-07,
"loss": 2.0238,
"step": 195
},
{
"epoch": 0.065932217643596,
"grad_norm": 0.19367286562919617,
"learning_rate": 1.3654133071059893e-07,
"loss": 1.9132,
"step": 196
},
{
"epoch": 0.06626860650912454,
"grad_norm": 0.2094404697418213,
"learning_rate": 7.681980162830282e-08,
"loss": 2.2367,
"step": 197
},
{
"epoch": 0.0666049953746531,
"grad_norm": 0.2485300451517105,
"learning_rate": 3.4146992848854695e-08,
"loss": 1.8876,
"step": 198
},
{
"epoch": 0.06694138424018165,
"grad_norm": 0.2835511863231659,
"learning_rate": 8.537477097364522e-09,
"loss": 2.0729,
"step": 199
},
{
"epoch": 0.0672777731057102,
"grad_norm": 0.4069346487522125,
"learning_rate": 0.0,
"loss": 2.0807,
"step": 200
},
{
"epoch": 0.0672777731057102,
"eval_loss": 2.167288064956665,
"eval_runtime": 134.6197,
"eval_samples_per_second": 37.194,
"eval_steps_per_second": 18.601,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.375493127929856e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}