adammandic87's picture
Training in progress, step 200, checkpoint
3e2050a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.037801823938005005,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00018900911969002505,
"grad_norm": 0.012686253525316715,
"learning_rate": 2e-05,
"loss": 10.378,
"step": 1
},
{
"epoch": 0.00018900911969002505,
"eval_loss": 10.380497932434082,
"eval_runtime": 7.795,
"eval_samples_per_second": 285.824,
"eval_steps_per_second": 142.912,
"step": 1
},
{
"epoch": 0.0003780182393800501,
"grad_norm": 0.014491567388176918,
"learning_rate": 4e-05,
"loss": 10.3803,
"step": 2
},
{
"epoch": 0.0005670273590700751,
"grad_norm": 0.012410955503582954,
"learning_rate": 6e-05,
"loss": 10.3807,
"step": 3
},
{
"epoch": 0.0007560364787601002,
"grad_norm": 0.01625671051442623,
"learning_rate": 8e-05,
"loss": 10.381,
"step": 4
},
{
"epoch": 0.0009450455984501252,
"grad_norm": 0.01246438268572092,
"learning_rate": 0.0001,
"loss": 10.3789,
"step": 5
},
{
"epoch": 0.0011340547181401502,
"grad_norm": 0.012397886253893375,
"learning_rate": 0.00012,
"loss": 10.3793,
"step": 6
},
{
"epoch": 0.0013230638378301752,
"grad_norm": 0.012805677950382233,
"learning_rate": 0.00014,
"loss": 10.3823,
"step": 7
},
{
"epoch": 0.0015120729575202004,
"grad_norm": 0.015158340334892273,
"learning_rate": 0.00016,
"loss": 10.3804,
"step": 8
},
{
"epoch": 0.0017010820772102254,
"grad_norm": 0.01396258920431137,
"learning_rate": 0.00018,
"loss": 10.38,
"step": 9
},
{
"epoch": 0.0018900911969002504,
"grad_norm": 0.01365083921700716,
"learning_rate": 0.0002,
"loss": 10.3809,
"step": 10
},
{
"epoch": 0.0020791003165902757,
"grad_norm": 0.014954385347664356,
"learning_rate": 0.0001999863304992469,
"loss": 10.378,
"step": 11
},
{
"epoch": 0.0022681094362803004,
"grad_norm": 0.01471993513405323,
"learning_rate": 0.00019994532573409262,
"loss": 10.3826,
"step": 12
},
{
"epoch": 0.0024571185559703257,
"grad_norm": 0.013966689817607403,
"learning_rate": 0.00019987699691483048,
"loss": 10.381,
"step": 13
},
{
"epoch": 0.0026461276756603504,
"grad_norm": 0.012581618502736092,
"learning_rate": 0.00019978136272187747,
"loss": 10.3835,
"step": 14
},
{
"epoch": 0.0028351367953503757,
"grad_norm": 0.01435596588999033,
"learning_rate": 0.000199658449300667,
"loss": 10.3825,
"step": 15
},
{
"epoch": 0.003024145915040401,
"grad_norm": 0.01442666631191969,
"learning_rate": 0.00019950829025450114,
"loss": 10.3798,
"step": 16
},
{
"epoch": 0.0032131550347304257,
"grad_norm": 0.011960881762206554,
"learning_rate": 0.00019933092663536382,
"loss": 10.3795,
"step": 17
},
{
"epoch": 0.003402164154420451,
"grad_norm": 0.017339341342449188,
"learning_rate": 0.00019912640693269752,
"loss": 10.3815,
"step": 18
},
{
"epoch": 0.0035911732741104757,
"grad_norm": 0.014264927245676517,
"learning_rate": 0.00019889478706014687,
"loss": 10.3823,
"step": 19
},
{
"epoch": 0.003780182393800501,
"grad_norm": 0.013290469534695148,
"learning_rate": 0.00019863613034027224,
"loss": 10.3805,
"step": 20
},
{
"epoch": 0.003969191513490526,
"grad_norm": 0.012597162276506424,
"learning_rate": 0.00019835050748723824,
"loss": 10.3767,
"step": 21
},
{
"epoch": 0.004158200633180551,
"grad_norm": 0.014128554612398148,
"learning_rate": 0.00019803799658748094,
"loss": 10.3819,
"step": 22
},
{
"epoch": 0.004347209752870576,
"grad_norm": 0.011865226551890373,
"learning_rate": 0.00019769868307835994,
"loss": 10.3771,
"step": 23
},
{
"epoch": 0.004536218872560601,
"grad_norm": 0.013639312237501144,
"learning_rate": 0.0001973326597248006,
"loss": 10.3778,
"step": 24
},
{
"epoch": 0.004725227992250626,
"grad_norm": 0.0164469163864851,
"learning_rate": 0.00019694002659393305,
"loss": 10.3829,
"step": 25
},
{
"epoch": 0.004914237111940651,
"grad_norm": 0.01444909255951643,
"learning_rate": 0.00019652089102773488,
"loss": 10.3794,
"step": 26
},
{
"epoch": 0.005103246231630676,
"grad_norm": 0.014745713211596012,
"learning_rate": 0.00019607536761368484,
"loss": 10.3777,
"step": 27
},
{
"epoch": 0.005292255351320701,
"grad_norm": 0.011052118614315987,
"learning_rate": 0.00019560357815343577,
"loss": 10.3803,
"step": 28
},
{
"epoch": 0.0054812644710107265,
"grad_norm": 0.013586455024778843,
"learning_rate": 0.00019510565162951537,
"loss": 10.3795,
"step": 29
},
{
"epoch": 0.005670273590700751,
"grad_norm": 0.012791085056960583,
"learning_rate": 0.00019458172417006347,
"loss": 10.3785,
"step": 30
},
{
"epoch": 0.005859282710390776,
"grad_norm": 0.016092879697680473,
"learning_rate": 0.00019403193901161613,
"loss": 10.3789,
"step": 31
},
{
"epoch": 0.006048291830080802,
"grad_norm": 0.016704507172107697,
"learning_rate": 0.0001934564464599461,
"loss": 10.3781,
"step": 32
},
{
"epoch": 0.0062373009497708265,
"grad_norm": 0.014680329710245132,
"learning_rate": 0.00019285540384897073,
"loss": 10.3804,
"step": 33
},
{
"epoch": 0.006426310069460851,
"grad_norm": 0.01731293648481369,
"learning_rate": 0.00019222897549773848,
"loss": 10.3789,
"step": 34
},
{
"epoch": 0.006615319189150876,
"grad_norm": 0.015626097097992897,
"learning_rate": 0.00019157733266550575,
"loss": 10.3798,
"step": 35
},
{
"epoch": 0.006804328308840902,
"grad_norm": 0.014310219325125217,
"learning_rate": 0.00019090065350491626,
"loss": 10.3773,
"step": 36
},
{
"epoch": 0.0069933374285309265,
"grad_norm": 0.015803059563040733,
"learning_rate": 0.00019019912301329592,
"loss": 10.3796,
"step": 37
},
{
"epoch": 0.007182346548220951,
"grad_norm": 0.015785884112119675,
"learning_rate": 0.00018947293298207635,
"loss": 10.3788,
"step": 38
},
{
"epoch": 0.007371355667910977,
"grad_norm": 0.015653641894459724,
"learning_rate": 0.0001887222819443612,
"loss": 10.3798,
"step": 39
},
{
"epoch": 0.007560364787601002,
"grad_norm": 0.01727336086332798,
"learning_rate": 0.0001879473751206489,
"loss": 10.3811,
"step": 40
},
{
"epoch": 0.0077493739072910265,
"grad_norm": 0.01792372763156891,
"learning_rate": 0.00018714842436272773,
"loss": 10.3778,
"step": 41
},
{
"epoch": 0.007938383026981051,
"grad_norm": 0.013475922867655754,
"learning_rate": 0.00018632564809575742,
"loss": 10.3802,
"step": 42
},
{
"epoch": 0.008127392146671077,
"grad_norm": 0.014228393323719501,
"learning_rate": 0.0001854792712585539,
"loss": 10.3804,
"step": 43
},
{
"epoch": 0.008316401266361103,
"grad_norm": 0.022298606112599373,
"learning_rate": 0.00018460952524209355,
"loss": 10.3762,
"step": 44
},
{
"epoch": 0.008505410386051127,
"grad_norm": 0.015143272466957569,
"learning_rate": 0.00018371664782625287,
"loss": 10.3791,
"step": 45
},
{
"epoch": 0.008694419505741152,
"grad_norm": 0.017378278076648712,
"learning_rate": 0.00018280088311480201,
"loss": 10.3784,
"step": 46
},
{
"epoch": 0.008883428625431178,
"grad_norm": 0.01839020662009716,
"learning_rate": 0.00018186248146866927,
"loss": 10.378,
"step": 47
},
{
"epoch": 0.009072437745121202,
"grad_norm": 0.0227019265294075,
"learning_rate": 0.00018090169943749476,
"loss": 10.3784,
"step": 48
},
{
"epoch": 0.009261446864811227,
"grad_norm": 0.01824440062046051,
"learning_rate": 0.0001799187996894925,
"loss": 10.3779,
"step": 49
},
{
"epoch": 0.009450455984501251,
"grad_norm": 0.021518880501389503,
"learning_rate": 0.00017891405093963938,
"loss": 10.3767,
"step": 50
},
{
"epoch": 0.009450455984501251,
"eval_loss": 10.377639770507812,
"eval_runtime": 7.9159,
"eval_samples_per_second": 281.459,
"eval_steps_per_second": 140.729,
"step": 50
},
{
"epoch": 0.009639465104191277,
"grad_norm": 0.019554248079657555,
"learning_rate": 0.00017788772787621126,
"loss": 10.3756,
"step": 51
},
{
"epoch": 0.009828474223881303,
"grad_norm": 0.018241645768284798,
"learning_rate": 0.00017684011108568592,
"loss": 10.3744,
"step": 52
},
{
"epoch": 0.010017483343571327,
"grad_norm": 0.018672486767172813,
"learning_rate": 0.0001757714869760335,
"loss": 10.379,
"step": 53
},
{
"epoch": 0.010206492463261352,
"grad_norm": 0.02010202221572399,
"learning_rate": 0.0001746821476984154,
"loss": 10.3781,
"step": 54
},
{
"epoch": 0.010395501582951378,
"grad_norm": 0.024531200528144836,
"learning_rate": 0.00017357239106731317,
"loss": 10.3781,
"step": 55
},
{
"epoch": 0.010584510702641402,
"grad_norm": 0.019959786906838417,
"learning_rate": 0.00017244252047910892,
"loss": 10.377,
"step": 56
},
{
"epoch": 0.010773519822331427,
"grad_norm": 0.024574976414442062,
"learning_rate": 0.00017129284482913972,
"loss": 10.3771,
"step": 57
},
{
"epoch": 0.010962528942021453,
"grad_norm": 0.02337220311164856,
"learning_rate": 0.00017012367842724887,
"loss": 10.3783,
"step": 58
},
{
"epoch": 0.011151538061711477,
"grad_norm": 0.024848444387316704,
"learning_rate": 0.0001689353409118566,
"loss": 10.3754,
"step": 59
},
{
"epoch": 0.011340547181401503,
"grad_norm": 0.02240614965558052,
"learning_rate": 0.00016772815716257412,
"loss": 10.376,
"step": 60
},
{
"epoch": 0.011529556301091528,
"grad_norm": 0.029676686972379684,
"learning_rate": 0.0001665024572113848,
"loss": 10.3771,
"step": 61
},
{
"epoch": 0.011718565420781552,
"grad_norm": 0.029000744223594666,
"learning_rate": 0.00016525857615241687,
"loss": 10.3737,
"step": 62
},
{
"epoch": 0.011907574540471578,
"grad_norm": 0.029285695403814316,
"learning_rate": 0.00016399685405033167,
"loss": 10.376,
"step": 63
},
{
"epoch": 0.012096583660161603,
"grad_norm": 0.023476559668779373,
"learning_rate": 0.0001627176358473537,
"loss": 10.3757,
"step": 64
},
{
"epoch": 0.012285592779851627,
"grad_norm": 0.024431871250271797,
"learning_rate": 0.0001614212712689668,
"loss": 10.3758,
"step": 65
},
{
"epoch": 0.012474601899541653,
"grad_norm": 0.024970779195427895,
"learning_rate": 0.00016010811472830252,
"loss": 10.3764,
"step": 66
},
{
"epoch": 0.012663611019231679,
"grad_norm": 0.03543892130255699,
"learning_rate": 0.00015877852522924732,
"loss": 10.3729,
"step": 67
},
{
"epoch": 0.012852620138921703,
"grad_norm": 0.031035298481583595,
"learning_rate": 0.00015743286626829437,
"loss": 10.3762,
"step": 68
},
{
"epoch": 0.013041629258611728,
"grad_norm": 0.030213864520192146,
"learning_rate": 0.0001560715057351673,
"loss": 10.3742,
"step": 69
},
{
"epoch": 0.013230638378301752,
"grad_norm": 0.03963561728596687,
"learning_rate": 0.00015469481581224272,
"loss": 10.3749,
"step": 70
},
{
"epoch": 0.013419647497991778,
"grad_norm": 0.029410356655716896,
"learning_rate": 0.0001533031728727994,
"loss": 10.3749,
"step": 71
},
{
"epoch": 0.013608656617681803,
"grad_norm": 0.03572849556803703,
"learning_rate": 0.00015189695737812152,
"loss": 10.3748,
"step": 72
},
{
"epoch": 0.013797665737371827,
"grad_norm": 0.036424197256565094,
"learning_rate": 0.0001504765537734844,
"loss": 10.3722,
"step": 73
},
{
"epoch": 0.013986674857061853,
"grad_norm": 0.03506350517272949,
"learning_rate": 0.00014904235038305083,
"loss": 10.3775,
"step": 74
},
{
"epoch": 0.014175683976751879,
"grad_norm": 0.02972862310707569,
"learning_rate": 0.00014759473930370736,
"loss": 10.3755,
"step": 75
},
{
"epoch": 0.014364693096441903,
"grad_norm": 0.033316999673843384,
"learning_rate": 0.0001461341162978688,
"loss": 10.3737,
"step": 76
},
{
"epoch": 0.014553702216131928,
"grad_norm": 0.04248441383242607,
"learning_rate": 0.00014466088068528068,
"loss": 10.3734,
"step": 77
},
{
"epoch": 0.014742711335821954,
"grad_norm": 0.05600935220718384,
"learning_rate": 0.00014317543523384928,
"loss": 10.371,
"step": 78
},
{
"epoch": 0.014931720455511978,
"grad_norm": 0.04100443795323372,
"learning_rate": 0.00014167818604952906,
"loss": 10.371,
"step": 79
},
{
"epoch": 0.015120729575202004,
"grad_norm": 0.03395973518490791,
"learning_rate": 0.00014016954246529696,
"loss": 10.3753,
"step": 80
},
{
"epoch": 0.01530973869489203,
"grad_norm": 0.059643857181072235,
"learning_rate": 0.00013864991692924523,
"loss": 10.3731,
"step": 81
},
{
"epoch": 0.015498747814582053,
"grad_norm": 0.05056724324822426,
"learning_rate": 0.00013711972489182208,
"loss": 10.3712,
"step": 82
},
{
"epoch": 0.015687756934272077,
"grad_norm": 0.042414236813783646,
"learning_rate": 0.00013557938469225167,
"loss": 10.3717,
"step": 83
},
{
"epoch": 0.015876766053962103,
"grad_norm": 0.054200392216444016,
"learning_rate": 0.00013402931744416433,
"loss": 10.3728,
"step": 84
},
{
"epoch": 0.01606577517365213,
"grad_norm": 0.07007519900798798,
"learning_rate": 0.00013246994692046836,
"loss": 10.3683,
"step": 85
},
{
"epoch": 0.016254784293342154,
"grad_norm": 0.054717712104320526,
"learning_rate": 0.00013090169943749476,
"loss": 10.3694,
"step": 86
},
{
"epoch": 0.01644379341303218,
"grad_norm": 0.05400513857603073,
"learning_rate": 0.0001293250037384465,
"loss": 10.3693,
"step": 87
},
{
"epoch": 0.016632802532722205,
"grad_norm": 0.059751372784376144,
"learning_rate": 0.00012774029087618446,
"loss": 10.3706,
"step": 88
},
{
"epoch": 0.016821811652412227,
"grad_norm": 0.04886062070727348,
"learning_rate": 0.00012614799409538198,
"loss": 10.3715,
"step": 89
},
{
"epoch": 0.017010820772102253,
"grad_norm": 0.06151995435357094,
"learning_rate": 0.00012454854871407994,
"loss": 10.3682,
"step": 90
},
{
"epoch": 0.01719982989179228,
"grad_norm": 0.06826233118772507,
"learning_rate": 0.00012294239200467516,
"loss": 10.3725,
"step": 91
},
{
"epoch": 0.017388839011482304,
"grad_norm": 0.05669957771897316,
"learning_rate": 0.0001213299630743747,
"loss": 10.3681,
"step": 92
},
{
"epoch": 0.01757784813117233,
"grad_norm": 0.06860942393541336,
"learning_rate": 0.00011971170274514802,
"loss": 10.3671,
"step": 93
},
{
"epoch": 0.017766857250862356,
"grad_norm": 0.06745350360870361,
"learning_rate": 0.000118088053433211,
"loss": 10.3681,
"step": 94
},
{
"epoch": 0.017955866370552378,
"grad_norm": 0.059718843549489975,
"learning_rate": 0.00011645945902807341,
"loss": 10.3688,
"step": 95
},
{
"epoch": 0.018144875490242404,
"grad_norm": 0.07292637974023819,
"learning_rate": 0.0001148263647711842,
"loss": 10.367,
"step": 96
},
{
"epoch": 0.01833388460993243,
"grad_norm": 0.055075109004974365,
"learning_rate": 0.00011318921713420691,
"loss": 10.3684,
"step": 97
},
{
"epoch": 0.018522893729622455,
"grad_norm": 0.057356979697942734,
"learning_rate": 0.00011154846369695863,
"loss": 10.367,
"step": 98
},
{
"epoch": 0.01871190284931248,
"grad_norm": 0.08173134177923203,
"learning_rate": 0.0001099045530250463,
"loss": 10.3678,
"step": 99
},
{
"epoch": 0.018900911969002503,
"grad_norm": 0.05882032588124275,
"learning_rate": 0.00010825793454723325,
"loss": 10.3677,
"step": 100
},
{
"epoch": 0.018900911969002503,
"eval_loss": 10.365761756896973,
"eval_runtime": 7.959,
"eval_samples_per_second": 279.935,
"eval_steps_per_second": 139.967,
"step": 100
},
{
"epoch": 0.01908992108869253,
"grad_norm": 0.08496179431676865,
"learning_rate": 0.00010660905843256994,
"loss": 10.3629,
"step": 101
},
{
"epoch": 0.019278930208382554,
"grad_norm": 0.06867600232362747,
"learning_rate": 0.00010495837546732224,
"loss": 10.3636,
"step": 102
},
{
"epoch": 0.01946793932807258,
"grad_norm": 0.07961437106132507,
"learning_rate": 0.00010330633693173082,
"loss": 10.3635,
"step": 103
},
{
"epoch": 0.019656948447762605,
"grad_norm": 0.08998848497867584,
"learning_rate": 0.00010165339447663587,
"loss": 10.3633,
"step": 104
},
{
"epoch": 0.01984595756745263,
"grad_norm": 0.06109720841050148,
"learning_rate": 0.0001,
"loss": 10.3643,
"step": 105
},
{
"epoch": 0.020034966687142653,
"grad_norm": 0.07281994819641113,
"learning_rate": 9.834660552336415e-05,
"loss": 10.3632,
"step": 106
},
{
"epoch": 0.02022397580683268,
"grad_norm": 0.06789088249206543,
"learning_rate": 9.669366306826919e-05,
"loss": 10.3608,
"step": 107
},
{
"epoch": 0.020412984926522704,
"grad_norm": 0.06652762740850449,
"learning_rate": 9.504162453267777e-05,
"loss": 10.3611,
"step": 108
},
{
"epoch": 0.02060199404621273,
"grad_norm": 0.060695480555295944,
"learning_rate": 9.339094156743007e-05,
"loss": 10.3631,
"step": 109
},
{
"epoch": 0.020791003165902756,
"grad_norm": 0.07064124196767807,
"learning_rate": 9.174206545276677e-05,
"loss": 10.3618,
"step": 110
},
{
"epoch": 0.02098001228559278,
"grad_norm": 0.06326396763324738,
"learning_rate": 9.009544697495374e-05,
"loss": 10.364,
"step": 111
},
{
"epoch": 0.021169021405282804,
"grad_norm": 0.0698811262845993,
"learning_rate": 8.845153630304139e-05,
"loss": 10.3626,
"step": 112
},
{
"epoch": 0.02135803052497283,
"grad_norm": 0.08220046013593674,
"learning_rate": 8.681078286579311e-05,
"loss": 10.3631,
"step": 113
},
{
"epoch": 0.021547039644662855,
"grad_norm": 0.060157131403684616,
"learning_rate": 8.517363522881579e-05,
"loss": 10.3617,
"step": 114
},
{
"epoch": 0.02173604876435288,
"grad_norm": 0.07724905014038086,
"learning_rate": 8.35405409719266e-05,
"loss": 10.3604,
"step": 115
},
{
"epoch": 0.021925057884042906,
"grad_norm": 0.0626760870218277,
"learning_rate": 8.191194656678904e-05,
"loss": 10.3616,
"step": 116
},
{
"epoch": 0.022114067003732932,
"grad_norm": 0.07387042045593262,
"learning_rate": 8.028829725485199e-05,
"loss": 10.3615,
"step": 117
},
{
"epoch": 0.022303076123422954,
"grad_norm": 0.07770082354545593,
"learning_rate": 7.867003692562534e-05,
"loss": 10.3611,
"step": 118
},
{
"epoch": 0.02249208524311298,
"grad_norm": 0.06714287400245667,
"learning_rate": 7.705760799532485e-05,
"loss": 10.3588,
"step": 119
},
{
"epoch": 0.022681094362803005,
"grad_norm": 0.06426379829645157,
"learning_rate": 7.54514512859201e-05,
"loss": 10.3609,
"step": 120
},
{
"epoch": 0.02287010348249303,
"grad_norm": 0.06445758044719696,
"learning_rate": 7.385200590461803e-05,
"loss": 10.3584,
"step": 121
},
{
"epoch": 0.023059112602183057,
"grad_norm": 0.08041175454854965,
"learning_rate": 7.225970912381556e-05,
"loss": 10.3583,
"step": 122
},
{
"epoch": 0.02324812172187308,
"grad_norm": 0.06840039044618607,
"learning_rate": 7.067499626155354e-05,
"loss": 10.3619,
"step": 123
},
{
"epoch": 0.023437130841563104,
"grad_norm": 0.06949985772371292,
"learning_rate": 6.909830056250527e-05,
"loss": 10.3595,
"step": 124
},
{
"epoch": 0.02362613996125313,
"grad_norm": 0.07371090352535248,
"learning_rate": 6.753005307953167e-05,
"loss": 10.3602,
"step": 125
},
{
"epoch": 0.023815149080943156,
"grad_norm": 0.059921570122241974,
"learning_rate": 6.59706825558357e-05,
"loss": 10.36,
"step": 126
},
{
"epoch": 0.02400415820063318,
"grad_norm": 0.056925393640995026,
"learning_rate": 6.442061530774834e-05,
"loss": 10.3556,
"step": 127
},
{
"epoch": 0.024193167320323207,
"grad_norm": 0.06497975438833237,
"learning_rate": 6.28802751081779e-05,
"loss": 10.3599,
"step": 128
},
{
"epoch": 0.02438217644001323,
"grad_norm": 0.0650826096534729,
"learning_rate": 6.135008307075481e-05,
"loss": 10.3586,
"step": 129
},
{
"epoch": 0.024571185559703255,
"grad_norm": 0.07630787789821625,
"learning_rate": 5.983045753470308e-05,
"loss": 10.3565,
"step": 130
},
{
"epoch": 0.02476019467939328,
"grad_norm": 0.05852606147527695,
"learning_rate": 5.832181395047098e-05,
"loss": 10.3634,
"step": 131
},
{
"epoch": 0.024949203799083306,
"grad_norm": 0.0687006339430809,
"learning_rate": 5.6824564766150726e-05,
"loss": 10.3579,
"step": 132
},
{
"epoch": 0.025138212918773332,
"grad_norm": 0.0733431875705719,
"learning_rate": 5.533911931471936e-05,
"loss": 10.355,
"step": 133
},
{
"epoch": 0.025327222038463357,
"grad_norm": 0.05864822492003441,
"learning_rate": 5.386588370213124e-05,
"loss": 10.3593,
"step": 134
},
{
"epoch": 0.02551623115815338,
"grad_norm": 0.055226318538188934,
"learning_rate": 5.240526069629265e-05,
"loss": 10.359,
"step": 135
},
{
"epoch": 0.025705240277843405,
"grad_norm": 0.07053076475858688,
"learning_rate": 5.095764961694922e-05,
"loss": 10.3572,
"step": 136
},
{
"epoch": 0.02589424939753343,
"grad_norm": 0.07019758224487305,
"learning_rate": 4.952344622651566e-05,
"loss": 10.3572,
"step": 137
},
{
"epoch": 0.026083258517223457,
"grad_norm": 0.06227070838212967,
"learning_rate": 4.810304262187852e-05,
"loss": 10.3573,
"step": 138
},
{
"epoch": 0.026272267636913482,
"grad_norm": 0.06058792397379875,
"learning_rate": 4.669682712720065e-05,
"loss": 10.3586,
"step": 139
},
{
"epoch": 0.026461276756603504,
"grad_norm": 0.06949535012245178,
"learning_rate": 4.530518418775733e-05,
"loss": 10.356,
"step": 140
},
{
"epoch": 0.02665028587629353,
"grad_norm": 0.07298791408538818,
"learning_rate": 4.392849426483274e-05,
"loss": 10.3584,
"step": 141
},
{
"epoch": 0.026839294995983556,
"grad_norm": 0.05652182549238205,
"learning_rate": 4.256713373170564e-05,
"loss": 10.3584,
"step": 142
},
{
"epoch": 0.02702830411567358,
"grad_norm": 0.05551915243268013,
"learning_rate": 4.12214747707527e-05,
"loss": 10.3588,
"step": 143
},
{
"epoch": 0.027217313235363607,
"grad_norm": 0.05911076441407204,
"learning_rate": 3.9891885271697496e-05,
"loss": 10.3593,
"step": 144
},
{
"epoch": 0.027406322355053633,
"grad_norm": 0.054930880665779114,
"learning_rate": 3.857872873103322e-05,
"loss": 10.3573,
"step": 145
},
{
"epoch": 0.027595331474743655,
"grad_norm": 0.05678775534033775,
"learning_rate": 3.7282364152646297e-05,
"loss": 10.3593,
"step": 146
},
{
"epoch": 0.02778434059443368,
"grad_norm": 0.06021711975336075,
"learning_rate": 3.600314594966834e-05,
"loss": 10.3568,
"step": 147
},
{
"epoch": 0.027973349714123706,
"grad_norm": 0.05524953454732895,
"learning_rate": 3.4741423847583134e-05,
"loss": 10.3577,
"step": 148
},
{
"epoch": 0.028162358833813732,
"grad_norm": 0.056392621248960495,
"learning_rate": 3.349754278861517e-05,
"loss": 10.3564,
"step": 149
},
{
"epoch": 0.028351367953503757,
"grad_norm": 0.047636594623327255,
"learning_rate": 3.227184283742591e-05,
"loss": 10.355,
"step": 150
},
{
"epoch": 0.028351367953503757,
"eval_loss": 10.35706901550293,
"eval_runtime": 7.9784,
"eval_samples_per_second": 279.253,
"eval_steps_per_second": 139.626,
"step": 150
},
{
"epoch": 0.028540377073193783,
"grad_norm": 0.06216558441519737,
"learning_rate": 3.106465908814342e-05,
"loss": 10.3635,
"step": 151
},
{
"epoch": 0.028729386192883805,
"grad_norm": 0.05615238845348358,
"learning_rate": 2.9876321572751144e-05,
"loss": 10.3545,
"step": 152
},
{
"epoch": 0.02891839531257383,
"grad_norm": 0.057838547974824905,
"learning_rate": 2.87071551708603e-05,
"loss": 10.3583,
"step": 153
},
{
"epoch": 0.029107404432263857,
"grad_norm": 0.052986498922109604,
"learning_rate": 2.7557479520891104e-05,
"loss": 10.3552,
"step": 154
},
{
"epoch": 0.029296413551953882,
"grad_norm": 0.055312514305114746,
"learning_rate": 2.6427608932686843e-05,
"loss": 10.356,
"step": 155
},
{
"epoch": 0.029485422671643908,
"grad_norm": 0.05807175859808922,
"learning_rate": 2.5317852301584643e-05,
"loss": 10.3565,
"step": 156
},
{
"epoch": 0.029674431791333934,
"grad_norm": 0.06103501841425896,
"learning_rate": 2.422851302396655e-05,
"loss": 10.3547,
"step": 157
},
{
"epoch": 0.029863440911023956,
"grad_norm": 0.05311097204685211,
"learning_rate": 2.315988891431412e-05,
"loss": 10.355,
"step": 158
},
{
"epoch": 0.03005245003071398,
"grad_norm": 0.05598808079957962,
"learning_rate": 2.2112272123788768e-05,
"loss": 10.3571,
"step": 159
},
{
"epoch": 0.030241459150404007,
"grad_norm": 0.05674521625041962,
"learning_rate": 2.1085949060360654e-05,
"loss": 10.3537,
"step": 160
},
{
"epoch": 0.030430468270094033,
"grad_norm": 0.05536748096346855,
"learning_rate": 2.008120031050753e-05,
"loss": 10.3545,
"step": 161
},
{
"epoch": 0.03061947738978406,
"grad_norm": 0.051667895168066025,
"learning_rate": 1.9098300562505266e-05,
"loss": 10.3562,
"step": 162
},
{
"epoch": 0.03080848650947408,
"grad_norm": 0.05974581092596054,
"learning_rate": 1.8137518531330767e-05,
"loss": 10.3538,
"step": 163
},
{
"epoch": 0.030997495629164106,
"grad_norm": 0.05384739860892296,
"learning_rate": 1.7199116885197995e-05,
"loss": 10.3574,
"step": 164
},
{
"epoch": 0.031186504748854132,
"grad_norm": 0.06221851706504822,
"learning_rate": 1.6283352173747145e-05,
"loss": 10.3545,
"step": 165
},
{
"epoch": 0.031375513868544154,
"grad_norm": 0.05726971849799156,
"learning_rate": 1.5390474757906446e-05,
"loss": 10.3546,
"step": 166
},
{
"epoch": 0.03156452298823418,
"grad_norm": 0.061142805963754654,
"learning_rate": 1.4520728741446089e-05,
"loss": 10.3572,
"step": 167
},
{
"epoch": 0.031753532107924205,
"grad_norm": 0.055892013013362885,
"learning_rate": 1.3674351904242611e-05,
"loss": 10.3557,
"step": 168
},
{
"epoch": 0.03194254122761423,
"grad_norm": 0.04323485121130943,
"learning_rate": 1.2851575637272262e-05,
"loss": 10.3557,
"step": 169
},
{
"epoch": 0.03213155034730426,
"grad_norm": 0.060065269470214844,
"learning_rate": 1.2052624879351104e-05,
"loss": 10.358,
"step": 170
},
{
"epoch": 0.03232055946699428,
"grad_norm": 0.05526785925030708,
"learning_rate": 1.1277718055638819e-05,
"loss": 10.3573,
"step": 171
},
{
"epoch": 0.03250956858668431,
"grad_norm": 0.05861446261405945,
"learning_rate": 1.0527067017923654e-05,
"loss": 10.3558,
"step": 172
},
{
"epoch": 0.032698577706374334,
"grad_norm": 0.04735025390982628,
"learning_rate": 9.80087698670411e-06,
"loss": 10.36,
"step": 173
},
{
"epoch": 0.03288758682606436,
"grad_norm": 0.05781494081020355,
"learning_rate": 9.09934649508375e-06,
"loss": 10.3573,
"step": 174
},
{
"epoch": 0.033076595945754385,
"grad_norm": 0.050222914665937424,
"learning_rate": 8.422667334494249e-06,
"loss": 10.3582,
"step": 175
},
{
"epoch": 0.03326560506544441,
"grad_norm": 0.048023052513599396,
"learning_rate": 7.771024502261526e-06,
"loss": 10.3555,
"step": 176
},
{
"epoch": 0.033454614185134436,
"grad_norm": 0.05381546914577484,
"learning_rate": 7.144596151029303e-06,
"loss": 10.3539,
"step": 177
},
{
"epoch": 0.033643623304824455,
"grad_norm": 0.047901567071676254,
"learning_rate": 6.543553540053926e-06,
"loss": 10.3579,
"step": 178
},
{
"epoch": 0.03383263242451448,
"grad_norm": 0.06044565513730049,
"learning_rate": 5.968060988383883e-06,
"loss": 10.3576,
"step": 179
},
{
"epoch": 0.034021641544204506,
"grad_norm": 0.046510256826877594,
"learning_rate": 5.418275829936537e-06,
"loss": 10.3577,
"step": 180
},
{
"epoch": 0.03421065066389453,
"grad_norm": 0.06163431704044342,
"learning_rate": 4.8943483704846475e-06,
"loss": 10.3548,
"step": 181
},
{
"epoch": 0.03439965978358456,
"grad_norm": 0.04503452777862549,
"learning_rate": 4.3964218465642355e-06,
"loss": 10.3549,
"step": 182
},
{
"epoch": 0.03458866890327458,
"grad_norm": 0.06345223635435104,
"learning_rate": 3.924632386315186e-06,
"loss": 10.3554,
"step": 183
},
{
"epoch": 0.03477767802296461,
"grad_norm": 0.06070295348763466,
"learning_rate": 3.4791089722651436e-06,
"loss": 10.3572,
"step": 184
},
{
"epoch": 0.034966687142654634,
"grad_norm": 0.056091003119945526,
"learning_rate": 3.059973406066963e-06,
"loss": 10.3572,
"step": 185
},
{
"epoch": 0.03515569626234466,
"grad_norm": 0.06234334036707878,
"learning_rate": 2.667340275199426e-06,
"loss": 10.3522,
"step": 186
},
{
"epoch": 0.035344705382034686,
"grad_norm": 0.060099318623542786,
"learning_rate": 2.3013169216400733e-06,
"loss": 10.3557,
"step": 187
},
{
"epoch": 0.03553371450172471,
"grad_norm": 0.04145883023738861,
"learning_rate": 1.9620034125190644e-06,
"loss": 10.3583,
"step": 188
},
{
"epoch": 0.03572272362141473,
"grad_norm": 0.06402470171451569,
"learning_rate": 1.6494925127617634e-06,
"loss": 10.3515,
"step": 189
},
{
"epoch": 0.035911732741104756,
"grad_norm": 0.054933883249759674,
"learning_rate": 1.3638696597277679e-06,
"loss": 10.3598,
"step": 190
},
{
"epoch": 0.03610074186079478,
"grad_norm": 0.058887969702482224,
"learning_rate": 1.1052129398531507e-06,
"loss": 10.3567,
"step": 191
},
{
"epoch": 0.03628975098048481,
"grad_norm": 0.057484857738018036,
"learning_rate": 8.735930673024806e-07,
"loss": 10.3565,
"step": 192
},
{
"epoch": 0.03647876010017483,
"grad_norm": 0.057735905051231384,
"learning_rate": 6.690733646361857e-07,
"loss": 10.357,
"step": 193
},
{
"epoch": 0.03666776921986486,
"grad_norm": 0.05184992402791977,
"learning_rate": 4.917097454988584e-07,
"loss": 10.3594,
"step": 194
},
{
"epoch": 0.036856778339554884,
"grad_norm": 0.061963826417922974,
"learning_rate": 3.415506993330153e-07,
"loss": 10.3577,
"step": 195
},
{
"epoch": 0.03704578745924491,
"grad_norm": 0.06438171863555908,
"learning_rate": 2.1863727812254653e-07,
"loss": 10.3575,
"step": 196
},
{
"epoch": 0.037234796578934935,
"grad_norm": 0.05486460402607918,
"learning_rate": 1.230030851695263e-07,
"loss": 10.3526,
"step": 197
},
{
"epoch": 0.03742380569862496,
"grad_norm": 0.05459611490368843,
"learning_rate": 5.467426590739511e-08,
"loss": 10.3542,
"step": 198
},
{
"epoch": 0.03761281481831499,
"grad_norm": 0.05004322901368141,
"learning_rate": 1.3669500753099585e-08,
"loss": 10.3573,
"step": 199
},
{
"epoch": 0.037801823938005005,
"grad_norm": 0.06536795943975449,
"learning_rate": 0.0,
"loss": 10.3544,
"step": 200
},
{
"epoch": 0.037801823938005005,
"eval_loss": 10.35628604888916,
"eval_runtime": 7.8439,
"eval_samples_per_second": 284.041,
"eval_steps_per_second": 142.021,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5172363264000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}