ToastyPigeon's picture
Training in progress, step 236, checkpoint
dc14b5c verified
raw
history blame
42.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.251063829787234,
"eval_steps": 189,
"global_step": 236,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010638297872340426,
"grad_norm": 0.15719425678253174,
"learning_rate": 2.5e-05,
"loss": 1.9422,
"step": 1
},
{
"epoch": 0.0010638297872340426,
"eval_loss": 2.3947696685791016,
"eval_runtime": 228.0833,
"eval_samples_per_second": 0.403,
"eval_steps_per_second": 0.403,
"step": 1
},
{
"epoch": 0.002127659574468085,
"grad_norm": 0.12337572872638702,
"learning_rate": 5e-05,
"loss": 1.8454,
"step": 2
},
{
"epoch": 0.0031914893617021275,
"grad_norm": 0.13498862087726593,
"learning_rate": 7.5e-05,
"loss": 2.0205,
"step": 3
},
{
"epoch": 0.00425531914893617,
"grad_norm": 0.14641264081001282,
"learning_rate": 0.0001,
"loss": 2.2241,
"step": 4
},
{
"epoch": 0.005319148936170213,
"grad_norm": 0.221758633852005,
"learning_rate": 0.000125,
"loss": 2.1881,
"step": 5
},
{
"epoch": 0.006382978723404255,
"grad_norm": 0.16080522537231445,
"learning_rate": 0.00015,
"loss": 2.3418,
"step": 6
},
{
"epoch": 0.007446808510638298,
"grad_norm": 0.200699582695961,
"learning_rate": 0.000175,
"loss": 2.2462,
"step": 7
},
{
"epoch": 0.00851063829787234,
"grad_norm": 0.22244133055210114,
"learning_rate": 0.0002,
"loss": 2.1351,
"step": 8
},
{
"epoch": 0.009574468085106383,
"grad_norm": 0.12635783851146698,
"learning_rate": 0.00022500000000000002,
"loss": 2.1829,
"step": 9
},
{
"epoch": 0.010638297872340425,
"grad_norm": 0.23889027535915375,
"learning_rate": 0.00025,
"loss": 2.285,
"step": 10
},
{
"epoch": 0.011702127659574468,
"grad_norm": 0.16700100898742676,
"learning_rate": 0.0002499993636030197,
"loss": 2.0751,
"step": 11
},
{
"epoch": 0.01276595744680851,
"grad_norm": 0.13016349077224731,
"learning_rate": 0.00024999745441927886,
"loss": 2.1398,
"step": 12
},
{
"epoch": 0.013829787234042552,
"grad_norm": 0.22968527674674988,
"learning_rate": 0.00024999427247037733,
"loss": 2.0359,
"step": 13
},
{
"epoch": 0.014893617021276596,
"grad_norm": 0.145517960190773,
"learning_rate": 0.000249989817792315,
"loss": 1.9857,
"step": 14
},
{
"epoch": 0.015957446808510637,
"grad_norm": 0.12325005978345871,
"learning_rate": 0.0002499840904354907,
"loss": 2.1137,
"step": 15
},
{
"epoch": 0.01702127659574468,
"grad_norm": 0.10462953895330429,
"learning_rate": 0.0002499770904647022,
"loss": 2.1306,
"step": 16
},
{
"epoch": 0.018085106382978722,
"grad_norm": 0.10856030881404877,
"learning_rate": 0.0002499688179591453,
"loss": 1.9974,
"step": 17
},
{
"epoch": 0.019148936170212766,
"grad_norm": 0.12662340700626373,
"learning_rate": 0.0002499592730124128,
"loss": 2.3052,
"step": 18
},
{
"epoch": 0.02021276595744681,
"grad_norm": 0.10757914185523987,
"learning_rate": 0.0002499484557324936,
"loss": 2.1465,
"step": 19
},
{
"epoch": 0.02127659574468085,
"grad_norm": 0.1157526895403862,
"learning_rate": 0.0002499363662417714,
"loss": 2.2331,
"step": 20
},
{
"epoch": 0.022340425531914895,
"grad_norm": 0.12368866801261902,
"learning_rate": 0.00024992300467702346,
"loss": 2.1574,
"step": 21
},
{
"epoch": 0.023404255319148935,
"grad_norm": 0.10928671061992645,
"learning_rate": 0.00024990837118941874,
"loss": 2.0207,
"step": 22
},
{
"epoch": 0.02446808510638298,
"grad_norm": 0.1046021580696106,
"learning_rate": 0.00024989246594451646,
"loss": 2.1064,
"step": 23
},
{
"epoch": 0.02553191489361702,
"grad_norm": 0.09606686979532242,
"learning_rate": 0.0002498752891222643,
"loss": 1.9726,
"step": 24
},
{
"epoch": 0.026595744680851064,
"grad_norm": 0.10333864390850067,
"learning_rate": 0.00024985684091699594,
"loss": 1.9889,
"step": 25
},
{
"epoch": 0.027659574468085105,
"grad_norm": 0.09974610805511475,
"learning_rate": 0.00024983712153742936,
"loss": 2.1849,
"step": 26
},
{
"epoch": 0.02872340425531915,
"grad_norm": 0.09508953243494034,
"learning_rate": 0.00024981613120666417,
"loss": 1.8267,
"step": 27
},
{
"epoch": 0.029787234042553193,
"grad_norm": 0.11703687906265259,
"learning_rate": 0.0002497938701621792,
"loss": 2.1924,
"step": 28
},
{
"epoch": 0.030851063829787233,
"grad_norm": 0.10372091084718704,
"learning_rate": 0.0002497703386558297,
"loss": 1.8565,
"step": 29
},
{
"epoch": 0.031914893617021274,
"grad_norm": 0.10386721789836884,
"learning_rate": 0.0002497455369538447,
"loss": 2.0355,
"step": 30
},
{
"epoch": 0.03297872340425532,
"grad_norm": 0.09948979318141937,
"learning_rate": 0.0002497194653368238,
"loss": 2.088,
"step": 31
},
{
"epoch": 0.03404255319148936,
"grad_norm": 0.0912819355726242,
"learning_rate": 0.0002496921240997341,
"loss": 2.1658,
"step": 32
},
{
"epoch": 0.035106382978723406,
"grad_norm": 0.09557418525218964,
"learning_rate": 0.0002496635135519068,
"loss": 2.1933,
"step": 33
},
{
"epoch": 0.036170212765957444,
"grad_norm": 0.10222162306308746,
"learning_rate": 0.0002496336340170337,
"loss": 2.0631,
"step": 34
},
{
"epoch": 0.03723404255319149,
"grad_norm": 0.08941858261823654,
"learning_rate": 0.0002496024858331637,
"loss": 1.9997,
"step": 35
},
{
"epoch": 0.03829787234042553,
"grad_norm": 0.0999622568488121,
"learning_rate": 0.00024957006935269867,
"loss": 2.2196,
"step": 36
},
{
"epoch": 0.039361702127659576,
"grad_norm": 0.10653268545866013,
"learning_rate": 0.0002495363849423898,
"loss": 2.1727,
"step": 37
},
{
"epoch": 0.04042553191489362,
"grad_norm": 0.1327868402004242,
"learning_rate": 0.0002495014329833331,
"loss": 2.0095,
"step": 38
},
{
"epoch": 0.04148936170212766,
"grad_norm": 0.08846122026443481,
"learning_rate": 0.00024946521387096557,
"loss": 1.8497,
"step": 39
},
{
"epoch": 0.0425531914893617,
"grad_norm": 0.1001238003373146,
"learning_rate": 0.0002494277280150601,
"loss": 2.0145,
"step": 40
},
{
"epoch": 0.043617021276595745,
"grad_norm": 0.1113252341747284,
"learning_rate": 0.0002493889758397214,
"loss": 1.7905,
"step": 41
},
{
"epoch": 0.04468085106382979,
"grad_norm": 0.10579642653465271,
"learning_rate": 0.00024934895778338086,
"loss": 1.9684,
"step": 42
},
{
"epoch": 0.045744680851063826,
"grad_norm": 0.09689021110534668,
"learning_rate": 0.0002493076742987917,
"loss": 1.9877,
"step": 43
},
{
"epoch": 0.04680851063829787,
"grad_norm": 0.10904544591903687,
"learning_rate": 0.000249265125853024,
"loss": 1.9456,
"step": 44
},
{
"epoch": 0.047872340425531915,
"grad_norm": 0.08989599347114563,
"learning_rate": 0.000249221312927459,
"loss": 1.9915,
"step": 45
},
{
"epoch": 0.04893617021276596,
"grad_norm": 0.10626763105392456,
"learning_rate": 0.0002491762360177841,
"loss": 2.1049,
"step": 46
},
{
"epoch": 0.05,
"grad_norm": 0.10239193588495255,
"learning_rate": 0.00024912989563398696,
"loss": 2.1835,
"step": 47
},
{
"epoch": 0.05106382978723404,
"grad_norm": 0.09280844777822495,
"learning_rate": 0.00024908229230035,
"loss": 1.9502,
"step": 48
},
{
"epoch": 0.052127659574468084,
"grad_norm": 0.10963878780603409,
"learning_rate": 0.00024903342655544414,
"loss": 1.9337,
"step": 49
},
{
"epoch": 0.05319148936170213,
"grad_norm": 0.10434435307979584,
"learning_rate": 0.00024898329895212297,
"loss": 1.9479,
"step": 50
},
{
"epoch": 0.05425531914893617,
"grad_norm": 0.11127671599388123,
"learning_rate": 0.00024893191005751636,
"loss": 2.1103,
"step": 51
},
{
"epoch": 0.05531914893617021,
"grad_norm": 0.09825640171766281,
"learning_rate": 0.00024887926045302403,
"loss": 1.777,
"step": 52
},
{
"epoch": 0.05638297872340425,
"grad_norm": 0.10062053054571152,
"learning_rate": 0.00024882535073430915,
"loss": 2.0612,
"step": 53
},
{
"epoch": 0.0574468085106383,
"grad_norm": 0.1014753133058548,
"learning_rate": 0.00024877018151129134,
"loss": 2.015,
"step": 54
},
{
"epoch": 0.05851063829787234,
"grad_norm": 0.10736796259880066,
"learning_rate": 0.00024871375340814004,
"loss": 2.1078,
"step": 55
},
{
"epoch": 0.059574468085106386,
"grad_norm": 0.09837566316127777,
"learning_rate": 0.00024865606706326714,
"loss": 2.0138,
"step": 56
},
{
"epoch": 0.06063829787234042,
"grad_norm": 0.10129820555448532,
"learning_rate": 0.00024859712312932014,
"loss": 1.8079,
"step": 57
},
{
"epoch": 0.06170212765957447,
"grad_norm": 0.11590743064880371,
"learning_rate": 0.0002485369222731744,
"loss": 1.8639,
"step": 58
},
{
"epoch": 0.0627659574468085,
"grad_norm": 0.10071361064910889,
"learning_rate": 0.0002484754651759258,
"loss": 1.9809,
"step": 59
},
{
"epoch": 0.06382978723404255,
"grad_norm": 0.16242088377475739,
"learning_rate": 0.0002484127525328829,
"loss": 2.0969,
"step": 60
},
{
"epoch": 0.06489361702127659,
"grad_norm": 0.09952322393655777,
"learning_rate": 0.0002483487850535594,
"loss": 1.7684,
"step": 61
},
{
"epoch": 0.06595744680851064,
"grad_norm": 0.0950712263584137,
"learning_rate": 0.0002482835634616656,
"loss": 1.86,
"step": 62
},
{
"epoch": 0.06702127659574468,
"grad_norm": 0.1205645427107811,
"learning_rate": 0.00024821708849510053,
"loss": 1.9127,
"step": 63
},
{
"epoch": 0.06808510638297872,
"grad_norm": 0.10416848212480545,
"learning_rate": 0.00024814936090594383,
"loss": 2.1245,
"step": 64
},
{
"epoch": 0.06914893617021277,
"grad_norm": 0.10299328714609146,
"learning_rate": 0.00024808038146044664,
"loss": 2.2193,
"step": 65
},
{
"epoch": 0.07021276595744681,
"grad_norm": 0.10638066381216049,
"learning_rate": 0.00024801015093902333,
"loss": 1.8795,
"step": 66
},
{
"epoch": 0.07127659574468086,
"grad_norm": 0.13867318630218506,
"learning_rate": 0.0002479386701362427,
"loss": 2.0245,
"step": 67
},
{
"epoch": 0.07234042553191489,
"grad_norm": 0.09890972822904587,
"learning_rate": 0.00024786593986081884,
"loss": 2.1797,
"step": 68
},
{
"epoch": 0.07340425531914893,
"grad_norm": 0.09402583539485931,
"learning_rate": 0.00024779196093560195,
"loss": 2.0093,
"step": 69
},
{
"epoch": 0.07446808510638298,
"grad_norm": 0.10384728014469147,
"learning_rate": 0.00024771673419756926,
"loss": 1.9576,
"step": 70
},
{
"epoch": 0.07553191489361702,
"grad_norm": 0.11337074637413025,
"learning_rate": 0.0002476402604978153,
"loss": 2.1267,
"step": 71
},
{
"epoch": 0.07659574468085106,
"grad_norm": 0.12024985998868942,
"learning_rate": 0.00024756254070154235,
"loss": 2.1193,
"step": 72
},
{
"epoch": 0.07765957446808511,
"grad_norm": 0.09909618645906448,
"learning_rate": 0.0002474835756880509,
"loss": 2.0732,
"step": 73
},
{
"epoch": 0.07872340425531915,
"grad_norm": 0.10968328267335892,
"learning_rate": 0.00024740336635072915,
"loss": 1.8176,
"step": 74
},
{
"epoch": 0.0797872340425532,
"grad_norm": 0.10667924582958221,
"learning_rate": 0.00024732191359704345,
"loss": 1.7713,
"step": 75
},
{
"epoch": 0.08085106382978724,
"grad_norm": 0.10140973329544067,
"learning_rate": 0.0002472392183485279,
"loss": 1.9644,
"step": 76
},
{
"epoch": 0.08191489361702127,
"grad_norm": 0.1087941825389862,
"learning_rate": 0.0002471552815407736,
"loss": 2.0052,
"step": 77
},
{
"epoch": 0.08297872340425531,
"grad_norm": 0.1062784343957901,
"learning_rate": 0.0002470701041234185,
"loss": 1.9551,
"step": 78
},
{
"epoch": 0.08404255319148936,
"grad_norm": 0.10445404797792435,
"learning_rate": 0.0002469836870601363,
"loss": 2.0273,
"step": 79
},
{
"epoch": 0.0851063829787234,
"grad_norm": 0.09620675444602966,
"learning_rate": 0.000246896031328626,
"loss": 1.837,
"step": 80
},
{
"epoch": 0.08617021276595745,
"grad_norm": 0.09469189494848251,
"learning_rate": 0.00024680713792060016,
"loss": 2.0745,
"step": 81
},
{
"epoch": 0.08723404255319149,
"grad_norm": 0.10994596034288406,
"learning_rate": 0.00024671700784177435,
"loss": 1.8983,
"step": 82
},
{
"epoch": 0.08829787234042553,
"grad_norm": 0.11240627616643906,
"learning_rate": 0.0002466256421118555,
"loss": 2.0791,
"step": 83
},
{
"epoch": 0.08936170212765958,
"grad_norm": 0.11063706874847412,
"learning_rate": 0.0002465330417645301,
"loss": 1.9128,
"step": 84
},
{
"epoch": 0.09042553191489362,
"grad_norm": 0.09807933121919632,
"learning_rate": 0.0002464392078474531,
"loss": 1.9822,
"step": 85
},
{
"epoch": 0.09148936170212765,
"grad_norm": 0.11714861541986465,
"learning_rate": 0.0002463441414222355,
"loss": 2.149,
"step": 86
},
{
"epoch": 0.0925531914893617,
"grad_norm": 0.11007135361433029,
"learning_rate": 0.0002462478435644325,
"loss": 1.7036,
"step": 87
},
{
"epoch": 0.09361702127659574,
"grad_norm": 0.1519717276096344,
"learning_rate": 0.0002461503153635316,
"loss": 2.1358,
"step": 88
},
{
"epoch": 0.09468085106382979,
"grad_norm": 0.10105334222316742,
"learning_rate": 0.00024605155792293995,
"loss": 1.8889,
"step": 89
},
{
"epoch": 0.09574468085106383,
"grad_norm": 0.09844442456960678,
"learning_rate": 0.000245951572359972,
"loss": 2.0052,
"step": 90
},
{
"epoch": 0.09680851063829787,
"grad_norm": 0.1045021116733551,
"learning_rate": 0.0002458503598058367,
"loss": 2.2272,
"step": 91
},
{
"epoch": 0.09787234042553192,
"grad_norm": 0.09748804569244385,
"learning_rate": 0.0002457479214056251,
"loss": 2.2324,
"step": 92
},
{
"epoch": 0.09893617021276596,
"grad_norm": 0.09661906957626343,
"learning_rate": 0.0002456442583182969,
"loss": 2.0503,
"step": 93
},
{
"epoch": 0.1,
"grad_norm": 0.10234526544809341,
"learning_rate": 0.0002455393717166678,
"loss": 2.1088,
"step": 94
},
{
"epoch": 0.10106382978723404,
"grad_norm": 0.10246799141168594,
"learning_rate": 0.00024543326278739566,
"loss": 2.2405,
"step": 95
},
{
"epoch": 0.10212765957446808,
"grad_norm": 0.1000024825334549,
"learning_rate": 0.0002453259327309679,
"loss": 1.86,
"step": 96
},
{
"epoch": 0.10319148936170212,
"grad_norm": 0.10678999125957489,
"learning_rate": 0.0002452173827616869,
"loss": 2.134,
"step": 97
},
{
"epoch": 0.10425531914893617,
"grad_norm": 0.10660276561975479,
"learning_rate": 0.00024510761410765725,
"loss": 1.8102,
"step": 98
},
{
"epoch": 0.10531914893617021,
"grad_norm": 0.10170196741819382,
"learning_rate": 0.00024499662801077114,
"loss": 1.9482,
"step": 99
},
{
"epoch": 0.10638297872340426,
"grad_norm": 0.11082155257463455,
"learning_rate": 0.0002448844257266947,
"loss": 2.2016,
"step": 100
},
{
"epoch": 0.1074468085106383,
"grad_norm": 0.09914924204349518,
"learning_rate": 0.0002447710085248535,
"loss": 1.7777,
"step": 101
},
{
"epoch": 0.10851063829787234,
"grad_norm": 0.0965084433555603,
"learning_rate": 0.00024465637768841857,
"loss": 2.0662,
"step": 102
},
{
"epoch": 0.10957446808510639,
"grad_norm": 0.10745298117399216,
"learning_rate": 0.0002445405345142915,
"loss": 1.8013,
"step": 103
},
{
"epoch": 0.11063829787234042,
"grad_norm": 0.11509711295366287,
"learning_rate": 0.0002444234803130901,
"loss": 1.9372,
"step": 104
},
{
"epoch": 0.11170212765957446,
"grad_norm": 0.09749408811330795,
"learning_rate": 0.00024430521640913323,
"loss": 2.1201,
"step": 105
},
{
"epoch": 0.1127659574468085,
"grad_norm": 0.10483244061470032,
"learning_rate": 0.0002441857441404261,
"loss": 1.9827,
"step": 106
},
{
"epoch": 0.11382978723404255,
"grad_norm": 0.11765095591545105,
"learning_rate": 0.00024406506485864497,
"loss": 1.8852,
"step": 107
},
{
"epoch": 0.1148936170212766,
"grad_norm": 0.09942599385976791,
"learning_rate": 0.00024394317992912194,
"loss": 1.8814,
"step": 108
},
{
"epoch": 0.11595744680851064,
"grad_norm": 0.1128399670124054,
"learning_rate": 0.0002438200907308295,
"loss": 1.9887,
"step": 109
},
{
"epoch": 0.11702127659574468,
"grad_norm": 0.1034490242600441,
"learning_rate": 0.00024369579865636485,
"loss": 2.087,
"step": 110
},
{
"epoch": 0.11808510638297873,
"grad_norm": 0.10408236086368561,
"learning_rate": 0.00024357030511193423,
"loss": 1.4333,
"step": 111
},
{
"epoch": 0.11914893617021277,
"grad_norm": 0.10553466528654099,
"learning_rate": 0.00024344361151733702,
"loss": 2.1482,
"step": 112
},
{
"epoch": 0.1202127659574468,
"grad_norm": 0.10812198370695114,
"learning_rate": 0.00024331571930594954,
"loss": 1.7569,
"step": 113
},
{
"epoch": 0.12127659574468085,
"grad_norm": 0.3904220759868622,
"learning_rate": 0.00024318662992470896,
"loss": 2.0672,
"step": 114
},
{
"epoch": 0.12234042553191489,
"grad_norm": 0.1045014038681984,
"learning_rate": 0.00024305634483409703,
"loss": 1.7733,
"step": 115
},
{
"epoch": 0.12340425531914893,
"grad_norm": 0.11234873533248901,
"learning_rate": 0.00024292486550812323,
"loss": 1.8588,
"step": 116
},
{
"epoch": 0.12446808510638298,
"grad_norm": 0.12042441219091415,
"learning_rate": 0.00024279219343430842,
"loss": 2.3323,
"step": 117
},
{
"epoch": 0.125531914893617,
"grad_norm": 0.13395822048187256,
"learning_rate": 0.00024265833011366777,
"loss": 1.9681,
"step": 118
},
{
"epoch": 0.12659574468085105,
"grad_norm": 0.13613761961460114,
"learning_rate": 0.00024252327706069407,
"loss": 1.8812,
"step": 119
},
{
"epoch": 0.1276595744680851,
"grad_norm": 0.11202660948038101,
"learning_rate": 0.0002423870358033402,
"loss": 2.1017,
"step": 120
},
{
"epoch": 0.12872340425531914,
"grad_norm": 0.10813065618276596,
"learning_rate": 0.00024224960788300217,
"loss": 1.6332,
"step": 121
},
{
"epoch": 0.12978723404255318,
"grad_norm": 0.12841644883155823,
"learning_rate": 0.00024211099485450167,
"loss": 2.0098,
"step": 122
},
{
"epoch": 0.13085106382978723,
"grad_norm": 0.10981354117393494,
"learning_rate": 0.0002419711982860681,
"loss": 2.0437,
"step": 123
},
{
"epoch": 0.13191489361702127,
"grad_norm": 0.10300987213850021,
"learning_rate": 0.0002418302197593213,
"loss": 1.9898,
"step": 124
},
{
"epoch": 0.13297872340425532,
"grad_norm": 0.09915132820606232,
"learning_rate": 0.00024168806086925348,
"loss": 1.7063,
"step": 125
},
{
"epoch": 0.13404255319148936,
"grad_norm": 0.10637573152780533,
"learning_rate": 0.00024154472322421113,
"loss": 1.8626,
"step": 126
},
{
"epoch": 0.1351063829787234,
"grad_norm": 0.10706152766942978,
"learning_rate": 0.00024140020844587667,
"loss": 2.009,
"step": 127
},
{
"epoch": 0.13617021276595745,
"grad_norm": 0.10487835109233856,
"learning_rate": 0.00024125451816925058,
"loss": 2.0771,
"step": 128
},
{
"epoch": 0.1372340425531915,
"grad_norm": 0.11320215463638306,
"learning_rate": 0.0002411076540426324,
"loss": 2.111,
"step": 129
},
{
"epoch": 0.13829787234042554,
"grad_norm": 0.10687907040119171,
"learning_rate": 0.00024095961772760237,
"loss": 1.7782,
"step": 130
},
{
"epoch": 0.13936170212765958,
"grad_norm": 0.10387088358402252,
"learning_rate": 0.0002408104108990024,
"loss": 1.947,
"step": 131
},
{
"epoch": 0.14042553191489363,
"grad_norm": 0.11471838504076004,
"learning_rate": 0.00024066003524491752,
"loss": 2.0569,
"step": 132
},
{
"epoch": 0.14148936170212767,
"grad_norm": 0.10412081331014633,
"learning_rate": 0.00024050849246665628,
"loss": 1.9277,
"step": 133
},
{
"epoch": 0.1425531914893617,
"grad_norm": 0.11945554614067078,
"learning_rate": 0.00024035578427873192,
"loss": 2.0863,
"step": 134
},
{
"epoch": 0.14361702127659576,
"grad_norm": 0.12696759402751923,
"learning_rate": 0.00024020191240884276,
"loss": 2.0757,
"step": 135
},
{
"epoch": 0.14468085106382977,
"grad_norm": 0.11579248309135437,
"learning_rate": 0.00024004687859785265,
"loss": 1.9771,
"step": 136
},
{
"epoch": 0.14574468085106382,
"grad_norm": 0.1291639804840088,
"learning_rate": 0.00023989068459977139,
"loss": 1.9655,
"step": 137
},
{
"epoch": 0.14680851063829786,
"grad_norm": 0.10244561731815338,
"learning_rate": 0.0002397333321817347,
"loss": 2.0573,
"step": 138
},
{
"epoch": 0.1478723404255319,
"grad_norm": 0.10870030522346497,
"learning_rate": 0.00023957482312398452,
"loss": 1.9953,
"step": 139
},
{
"epoch": 0.14893617021276595,
"grad_norm": 0.11521364748477936,
"learning_rate": 0.00023941515921984855,
"loss": 1.7835,
"step": 140
},
{
"epoch": 0.15,
"grad_norm": 0.1189892515540123,
"learning_rate": 0.00023925434227572013,
"loss": 1.8137,
"step": 141
},
{
"epoch": 0.15106382978723404,
"grad_norm": 0.11443563550710678,
"learning_rate": 0.00023909237411103785,
"loss": 2.1109,
"step": 142
},
{
"epoch": 0.15212765957446808,
"grad_norm": 0.1882992833852768,
"learning_rate": 0.00023892925655826476,
"loss": 2.1079,
"step": 143
},
{
"epoch": 0.15319148936170213,
"grad_norm": 0.11956554651260376,
"learning_rate": 0.0002387649914628679,
"loss": 2.0648,
"step": 144
},
{
"epoch": 0.15425531914893617,
"grad_norm": 0.13715718686580658,
"learning_rate": 0.00023859958068329725,
"loss": 2.004,
"step": 145
},
{
"epoch": 0.15531914893617021,
"grad_norm": 0.1169043555855751,
"learning_rate": 0.00023843302609096467,
"loss": 2.1193,
"step": 146
},
{
"epoch": 0.15638297872340426,
"grad_norm": 0.11039727926254272,
"learning_rate": 0.00023826532957022293,
"loss": 1.9419,
"step": 147
},
{
"epoch": 0.1574468085106383,
"grad_norm": 0.11504384130239487,
"learning_rate": 0.00023809649301834415,
"loss": 1.9714,
"step": 148
},
{
"epoch": 0.15851063829787235,
"grad_norm": 0.11435811966657639,
"learning_rate": 0.00023792651834549856,
"loss": 1.7879,
"step": 149
},
{
"epoch": 0.1595744680851064,
"grad_norm": 0.27376243472099304,
"learning_rate": 0.00023775540747473262,
"loss": 2.0011,
"step": 150
},
{
"epoch": 0.16063829787234044,
"grad_norm": 0.12073350697755814,
"learning_rate": 0.0002375831623419476,
"loss": 1.9285,
"step": 151
},
{
"epoch": 0.16170212765957448,
"grad_norm": 0.11144834011793137,
"learning_rate": 0.00023740978489587733,
"loss": 1.9147,
"step": 152
},
{
"epoch": 0.16276595744680852,
"grad_norm": 0.1074347198009491,
"learning_rate": 0.00023723527709806647,
"loss": 2.092,
"step": 153
},
{
"epoch": 0.16382978723404254,
"grad_norm": 0.11253698170185089,
"learning_rate": 0.00023705964092284805,
"loss": 1.9452,
"step": 154
},
{
"epoch": 0.16489361702127658,
"grad_norm": 0.1153697595000267,
"learning_rate": 0.00023688287835732134,
"loss": 2.008,
"step": 155
},
{
"epoch": 0.16595744680851063,
"grad_norm": 0.11541475355625153,
"learning_rate": 0.00023670499140132918,
"loss": 1.5319,
"step": 156
},
{
"epoch": 0.16702127659574467,
"grad_norm": 0.11363336443901062,
"learning_rate": 0.00023652598206743553,
"loss": 2.1214,
"step": 157
},
{
"epoch": 0.16808510638297872,
"grad_norm": 0.10930821299552917,
"learning_rate": 0.00023634585238090265,
"loss": 1.8862,
"step": 158
},
{
"epoch": 0.16914893617021276,
"grad_norm": 0.13756263256072998,
"learning_rate": 0.000236164604379668,
"loss": 2.001,
"step": 159
},
{
"epoch": 0.1702127659574468,
"grad_norm": 0.11600874364376068,
"learning_rate": 0.00023598224011432163,
"loss": 2.0017,
"step": 160
},
{
"epoch": 0.17127659574468085,
"grad_norm": 0.14339403808116913,
"learning_rate": 0.00023579876164808234,
"loss": 1.8875,
"step": 161
},
{
"epoch": 0.1723404255319149,
"grad_norm": 0.11734171211719513,
"learning_rate": 0.000235614171056775,
"loss": 2.025,
"step": 162
},
{
"epoch": 0.17340425531914894,
"grad_norm": 0.16881157457828522,
"learning_rate": 0.00023542847042880662,
"loss": 2.1279,
"step": 163
},
{
"epoch": 0.17446808510638298,
"grad_norm": 0.10519936680793762,
"learning_rate": 0.00023524166186514284,
"loss": 1.8798,
"step": 164
},
{
"epoch": 0.17553191489361702,
"grad_norm": 0.11043398827314377,
"learning_rate": 0.00023505374747928419,
"loss": 1.9368,
"step": 165
},
{
"epoch": 0.17659574468085107,
"grad_norm": 0.11440404504537582,
"learning_rate": 0.00023486472939724217,
"loss": 1.9948,
"step": 166
},
{
"epoch": 0.1776595744680851,
"grad_norm": 0.11574520170688629,
"learning_rate": 0.0002346746097575153,
"loss": 2.1822,
"step": 167
},
{
"epoch": 0.17872340425531916,
"grad_norm": 0.11897675693035126,
"learning_rate": 0.00023448339071106461,
"loss": 1.9755,
"step": 168
},
{
"epoch": 0.1797872340425532,
"grad_norm": 0.116481252014637,
"learning_rate": 0.00023429107442128974,
"loss": 1.751,
"step": 169
},
{
"epoch": 0.18085106382978725,
"grad_norm": 0.11168333142995834,
"learning_rate": 0.0002340976630640041,
"loss": 2.1915,
"step": 170
},
{
"epoch": 0.1819148936170213,
"grad_norm": 0.1481730043888092,
"learning_rate": 0.00023390315882741038,
"loss": 1.9164,
"step": 171
},
{
"epoch": 0.1829787234042553,
"grad_norm": 0.10625225305557251,
"learning_rate": 0.00023370756391207588,
"loss": 1.8064,
"step": 172
},
{
"epoch": 0.18404255319148935,
"grad_norm": 0.11492953449487686,
"learning_rate": 0.0002335108805309075,
"loss": 2.0202,
"step": 173
},
{
"epoch": 0.1851063829787234,
"grad_norm": 0.11886078119277954,
"learning_rate": 0.00023331311090912677,
"loss": 1.994,
"step": 174
},
{
"epoch": 0.18617021276595744,
"grad_norm": 0.12113317847251892,
"learning_rate": 0.0002331142572842446,
"loss": 2.061,
"step": 175
},
{
"epoch": 0.18723404255319148,
"grad_norm": 0.11451803892850876,
"learning_rate": 0.00023291432190603603,
"loss": 2.0846,
"step": 176
},
{
"epoch": 0.18829787234042553,
"grad_norm": 0.13504713773727417,
"learning_rate": 0.00023271330703651482,
"loss": 2.0917,
"step": 177
},
{
"epoch": 0.18936170212765957,
"grad_norm": 0.11458391696214676,
"learning_rate": 0.00023251121494990764,
"loss": 1.704,
"step": 178
},
{
"epoch": 0.19042553191489361,
"grad_norm": 0.13398422300815582,
"learning_rate": 0.00023230804793262873,
"loss": 2.103,
"step": 179
},
{
"epoch": 0.19148936170212766,
"grad_norm": 0.11917758733034134,
"learning_rate": 0.00023210380828325353,
"loss": 1.7718,
"step": 180
},
{
"epoch": 0.1925531914893617,
"grad_norm": 0.1172708049416542,
"learning_rate": 0.0002318984983124932,
"loss": 2.0172,
"step": 181
},
{
"epoch": 0.19361702127659575,
"grad_norm": 0.1266704946756363,
"learning_rate": 0.00023169212034316805,
"loss": 1.9212,
"step": 182
},
{
"epoch": 0.1946808510638298,
"grad_norm": 0.13580508530139923,
"learning_rate": 0.0002314846767101815,
"loss": 2.0556,
"step": 183
},
{
"epoch": 0.19574468085106383,
"grad_norm": 0.1328660249710083,
"learning_rate": 0.00023127616976049357,
"loss": 1.9746,
"step": 184
},
{
"epoch": 0.19680851063829788,
"grad_norm": 0.1272975504398346,
"learning_rate": 0.00023106660185309434,
"loss": 1.9995,
"step": 185
},
{
"epoch": 0.19787234042553192,
"grad_norm": 0.11610808223485947,
"learning_rate": 0.0002308559753589773,
"loss": 1.9755,
"step": 186
},
{
"epoch": 0.19893617021276597,
"grad_norm": 0.11477465182542801,
"learning_rate": 0.0002306442926611125,
"loss": 1.8594,
"step": 187
},
{
"epoch": 0.2,
"grad_norm": 0.11912880837917328,
"learning_rate": 0.00023043155615441963,
"loss": 2.2537,
"step": 188
},
{
"epoch": 0.20106382978723406,
"grad_norm": 0.12370310723781586,
"learning_rate": 0.00023021776824574077,
"loss": 1.8427,
"step": 189
},
{
"epoch": 0.20106382978723406,
"eval_loss": 2.2439846992492676,
"eval_runtime": 228.9331,
"eval_samples_per_second": 0.402,
"eval_steps_per_second": 0.402,
"step": 189
},
{
"epoch": 0.20212765957446807,
"grad_norm": 0.12219749391078949,
"learning_rate": 0.0002300029313538133,
"loss": 1.6372,
"step": 190
},
{
"epoch": 0.20319148936170212,
"grad_norm": 0.12997935712337494,
"learning_rate": 0.00022978704790924264,
"loss": 1.7587,
"step": 191
},
{
"epoch": 0.20425531914893616,
"grad_norm": 0.1191156730055809,
"learning_rate": 0.00022957012035447445,
"loss": 2.1128,
"step": 192
},
{
"epoch": 0.2053191489361702,
"grad_norm": 0.1545037180185318,
"learning_rate": 0.00022935215114376723,
"loss": 1.6692,
"step": 193
},
{
"epoch": 0.20638297872340425,
"grad_norm": 0.1366199105978012,
"learning_rate": 0.00022913314274316455,
"loss": 1.9685,
"step": 194
},
{
"epoch": 0.2074468085106383,
"grad_norm": 0.12138072401285172,
"learning_rate": 0.00022891309763046697,
"loss": 1.8484,
"step": 195
},
{
"epoch": 0.20851063829787234,
"grad_norm": 0.1285848766565323,
"learning_rate": 0.0002286920182952042,
"loss": 1.7935,
"step": 196
},
{
"epoch": 0.20957446808510638,
"grad_norm": 0.11619207262992859,
"learning_rate": 0.00022846990723860686,
"loss": 2.0731,
"step": 197
},
{
"epoch": 0.21063829787234042,
"grad_norm": 0.4214017689228058,
"learning_rate": 0.00022824676697357814,
"loss": 2.0675,
"step": 198
},
{
"epoch": 0.21170212765957447,
"grad_norm": 0.11827094852924347,
"learning_rate": 0.0002280226000246654,
"loss": 1.7509,
"step": 199
},
{
"epoch": 0.2127659574468085,
"grad_norm": 0.132975772023201,
"learning_rate": 0.00022779740892803175,
"loss": 1.6893,
"step": 200
},
{
"epoch": 0.21382978723404256,
"grad_norm": 0.12743262946605682,
"learning_rate": 0.00022757119623142706,
"loss": 1.9338,
"step": 201
},
{
"epoch": 0.2148936170212766,
"grad_norm": 0.13391292095184326,
"learning_rate": 0.00022734396449415934,
"loss": 2.1821,
"step": 202
},
{
"epoch": 0.21595744680851064,
"grad_norm": 0.12177909165620804,
"learning_rate": 0.0002271157162870658,
"loss": 1.8998,
"step": 203
},
{
"epoch": 0.2170212765957447,
"grad_norm": 0.3537590503692627,
"learning_rate": 0.00022688645419248374,
"loss": 1.8342,
"step": 204
},
{
"epoch": 0.21808510638297873,
"grad_norm": 0.14446629583835602,
"learning_rate": 0.00022665618080422114,
"loss": 1.9379,
"step": 205
},
{
"epoch": 0.21914893617021278,
"grad_norm": 0.1220061182975769,
"learning_rate": 0.00022642489872752765,
"loss": 1.8389,
"step": 206
},
{
"epoch": 0.22021276595744682,
"grad_norm": 0.10652719438076019,
"learning_rate": 0.00022619261057906485,
"loss": 1.7434,
"step": 207
},
{
"epoch": 0.22127659574468084,
"grad_norm": 0.1321529746055603,
"learning_rate": 0.00022595931898687673,
"loss": 2.2176,
"step": 208
},
{
"epoch": 0.22234042553191488,
"grad_norm": 0.11512637138366699,
"learning_rate": 0.00022572502659036007,
"loss": 1.8772,
"step": 209
},
{
"epoch": 0.22340425531914893,
"grad_norm": 0.15195037424564362,
"learning_rate": 0.00022548973604023437,
"loss": 2.1445,
"step": 210
},
{
"epoch": 0.22446808510638297,
"grad_norm": 0.1171952560544014,
"learning_rate": 0.00022525344999851197,
"loss": 2.0841,
"step": 211
},
{
"epoch": 0.225531914893617,
"grad_norm": 0.11501558870077133,
"learning_rate": 0.00022501617113846798,
"loss": 1.8845,
"step": 212
},
{
"epoch": 0.22659574468085106,
"grad_norm": 0.14285384118556976,
"learning_rate": 0.00022477790214460994,
"loss": 1.7457,
"step": 213
},
{
"epoch": 0.2276595744680851,
"grad_norm": 0.1312599778175354,
"learning_rate": 0.0002245386457126475,
"loss": 2.12,
"step": 214
},
{
"epoch": 0.22872340425531915,
"grad_norm": 0.12865905463695526,
"learning_rate": 0.00022429840454946196,
"loss": 1.9595,
"step": 215
},
{
"epoch": 0.2297872340425532,
"grad_norm": 0.18248826265335083,
"learning_rate": 0.00022405718137307552,
"loss": 2.0199,
"step": 216
},
{
"epoch": 0.23085106382978723,
"grad_norm": 0.129413902759552,
"learning_rate": 0.00022381497891262066,
"loss": 1.8833,
"step": 217
},
{
"epoch": 0.23191489361702128,
"grad_norm": 0.12320221215486526,
"learning_rate": 0.00022357179990830923,
"loss": 2.0043,
"step": 218
},
{
"epoch": 0.23297872340425532,
"grad_norm": 0.11922425031661987,
"learning_rate": 0.00022332764711140127,
"loss": 1.9641,
"step": 219
},
{
"epoch": 0.23404255319148937,
"grad_norm": 0.1320050060749054,
"learning_rate": 0.00022308252328417426,
"loss": 1.9602,
"step": 220
},
{
"epoch": 0.2351063829787234,
"grad_norm": 0.14773212373256683,
"learning_rate": 0.00022283643119989154,
"loss": 1.8785,
"step": 221
},
{
"epoch": 0.23617021276595745,
"grad_norm": 0.128052219748497,
"learning_rate": 0.00022258937364277105,
"loss": 1.8772,
"step": 222
},
{
"epoch": 0.2372340425531915,
"grad_norm": 0.12113828212022781,
"learning_rate": 0.00022234135340795378,
"loss": 2.0577,
"step": 223
},
{
"epoch": 0.23829787234042554,
"grad_norm": 0.1478564292192459,
"learning_rate": 0.0002220923733014723,
"loss": 1.7237,
"step": 224
},
{
"epoch": 0.2393617021276596,
"grad_norm": 0.12648318707942963,
"learning_rate": 0.0002218424361402188,
"loss": 1.5301,
"step": 225
},
{
"epoch": 0.2404255319148936,
"grad_norm": 0.13919681310653687,
"learning_rate": 0.00022159154475191343,
"loss": 1.8451,
"step": 226
},
{
"epoch": 0.24148936170212765,
"grad_norm": 0.162435844540596,
"learning_rate": 0.00022133970197507199,
"loss": 1.7585,
"step": 227
},
{
"epoch": 0.2425531914893617,
"grad_norm": 0.1612282693386078,
"learning_rate": 0.0002210869106589743,
"loss": 1.9223,
"step": 228
},
{
"epoch": 0.24361702127659574,
"grad_norm": 0.1214359775185585,
"learning_rate": 0.0002208331736636316,
"loss": 1.8637,
"step": 229
},
{
"epoch": 0.24468085106382978,
"grad_norm": 0.1307225078344345,
"learning_rate": 0.0002205784938597541,
"loss": 1.9397,
"step": 230
},
{
"epoch": 0.24574468085106382,
"grad_norm": 0.13562381267547607,
"learning_rate": 0.00022032287412871893,
"loss": 1.9584,
"step": 231
},
{
"epoch": 0.24680851063829787,
"grad_norm": 0.12984585762023926,
"learning_rate": 0.00022006631736253715,
"loss": 1.8084,
"step": 232
},
{
"epoch": 0.2478723404255319,
"grad_norm": 0.11881977319717407,
"learning_rate": 0.00021980882646382128,
"loss": 1.747,
"step": 233
},
{
"epoch": 0.24893617021276596,
"grad_norm": 0.13311228156089783,
"learning_rate": 0.0002195504043457523,
"loss": 1.9873,
"step": 234
},
{
"epoch": 0.25,
"grad_norm": 0.13149425387382507,
"learning_rate": 0.00021929105393204675,
"loss": 2.0715,
"step": 235
},
{
"epoch": 0.251063829787234,
"grad_norm": 0.1460556536912918,
"learning_rate": 0.00021903077815692358,
"loss": 1.7887,
"step": 236
}
],
"logging_steps": 1,
"max_steps": 944,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 236,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.477347754193715e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}