prxy5605's picture
Training in progress, step 200, checkpoint
8074000 verified
raw
history blame
36.8 kB
{
"best_metric": 0.46923279762268066,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.02185911798458932,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00010929558992294661,
"grad_norm": 0.08892586827278137,
"learning_rate": 5e-06,
"loss": 0.407,
"step": 1
},
{
"epoch": 0.00010929558992294661,
"eval_loss": 0.9313396215438843,
"eval_runtime": 1188.3423,
"eval_samples_per_second": 12.968,
"eval_steps_per_second": 6.484,
"step": 1
},
{
"epoch": 0.00021859117984589322,
"grad_norm": 0.10184711962938309,
"learning_rate": 1e-05,
"loss": 0.3912,
"step": 2
},
{
"epoch": 0.0003278867697688398,
"grad_norm": 0.1291767805814743,
"learning_rate": 1.5e-05,
"loss": 0.5147,
"step": 3
},
{
"epoch": 0.00043718235969178644,
"grad_norm": 0.13007928431034088,
"learning_rate": 2e-05,
"loss": 0.4359,
"step": 4
},
{
"epoch": 0.0005464779496147331,
"grad_norm": 0.14250938594341278,
"learning_rate": 2.5e-05,
"loss": 0.4897,
"step": 5
},
{
"epoch": 0.0006557735395376796,
"grad_norm": 0.15091027319431305,
"learning_rate": 3e-05,
"loss": 0.5612,
"step": 6
},
{
"epoch": 0.0007650691294606263,
"grad_norm": 0.14838960766792297,
"learning_rate": 3.5e-05,
"loss": 0.5994,
"step": 7
},
{
"epoch": 0.0008743647193835729,
"grad_norm": 0.1545994132757187,
"learning_rate": 4e-05,
"loss": 0.6009,
"step": 8
},
{
"epoch": 0.0009836603093065195,
"grad_norm": 0.15585535764694214,
"learning_rate": 4.5e-05,
"loss": 0.5009,
"step": 9
},
{
"epoch": 0.0010929558992294661,
"grad_norm": 0.18895578384399414,
"learning_rate": 5e-05,
"loss": 0.6854,
"step": 10
},
{
"epoch": 0.0012022514891524127,
"grad_norm": 0.20997057855129242,
"learning_rate": 5.500000000000001e-05,
"loss": 0.6106,
"step": 11
},
{
"epoch": 0.0013115470790753593,
"grad_norm": 0.20784635841846466,
"learning_rate": 6e-05,
"loss": 0.7,
"step": 12
},
{
"epoch": 0.0014208426689983058,
"grad_norm": 0.20637793838977814,
"learning_rate": 6.500000000000001e-05,
"loss": 0.4913,
"step": 13
},
{
"epoch": 0.0015301382589212526,
"grad_norm": 0.18955039978027344,
"learning_rate": 7e-05,
"loss": 0.5854,
"step": 14
},
{
"epoch": 0.0016394338488441992,
"grad_norm": 0.19074691832065582,
"learning_rate": 7.500000000000001e-05,
"loss": 0.5278,
"step": 15
},
{
"epoch": 0.0017487294387671457,
"grad_norm": 0.1751364767551422,
"learning_rate": 8e-05,
"loss": 0.4145,
"step": 16
},
{
"epoch": 0.0018580250286900923,
"grad_norm": 0.17601102590560913,
"learning_rate": 8.5e-05,
"loss": 0.5324,
"step": 17
},
{
"epoch": 0.001967320618613039,
"grad_norm": 0.18196499347686768,
"learning_rate": 9e-05,
"loss": 0.5041,
"step": 18
},
{
"epoch": 0.0020766162085359857,
"grad_norm": 0.18326377868652344,
"learning_rate": 9.5e-05,
"loss": 0.4329,
"step": 19
},
{
"epoch": 0.0021859117984589322,
"grad_norm": 0.23563292622566223,
"learning_rate": 0.0001,
"loss": 0.484,
"step": 20
},
{
"epoch": 0.002295207388381879,
"grad_norm": 0.21941961348056793,
"learning_rate": 9.999238475781957e-05,
"loss": 0.6038,
"step": 21
},
{
"epoch": 0.0024045029783048254,
"grad_norm": 0.18175636231899261,
"learning_rate": 9.99695413509548e-05,
"loss": 0.5373,
"step": 22
},
{
"epoch": 0.002513798568227772,
"grad_norm": 0.1632622629404068,
"learning_rate": 9.99314767377287e-05,
"loss": 0.4324,
"step": 23
},
{
"epoch": 0.0026230941581507185,
"grad_norm": 0.18101082742214203,
"learning_rate": 9.987820251299122e-05,
"loss": 0.5009,
"step": 24
},
{
"epoch": 0.002732389748073665,
"grad_norm": 0.36991167068481445,
"learning_rate": 9.980973490458728e-05,
"loss": 0.6138,
"step": 25
},
{
"epoch": 0.0028416853379966116,
"grad_norm": 0.15769365429878235,
"learning_rate": 9.972609476841367e-05,
"loss": 0.4178,
"step": 26
},
{
"epoch": 0.0029509809279195586,
"grad_norm": 0.1861845850944519,
"learning_rate": 9.962730758206611e-05,
"loss": 0.5209,
"step": 27
},
{
"epoch": 0.003060276517842505,
"grad_norm": 0.17047907412052155,
"learning_rate": 9.951340343707852e-05,
"loss": 0.575,
"step": 28
},
{
"epoch": 0.003169572107765452,
"grad_norm": 0.15702685713768005,
"learning_rate": 9.938441702975689e-05,
"loss": 0.4291,
"step": 29
},
{
"epoch": 0.0032788676976883984,
"grad_norm": 0.2200898826122284,
"learning_rate": 9.924038765061042e-05,
"loss": 0.6081,
"step": 30
},
{
"epoch": 0.003388163287611345,
"grad_norm": 0.225937157869339,
"learning_rate": 9.908135917238321e-05,
"loss": 0.5231,
"step": 31
},
{
"epoch": 0.0034974588775342915,
"grad_norm": 0.2006777971982956,
"learning_rate": 9.890738003669029e-05,
"loss": 0.4612,
"step": 32
},
{
"epoch": 0.003606754467457238,
"grad_norm": 0.22215096652507782,
"learning_rate": 9.871850323926177e-05,
"loss": 0.6789,
"step": 33
},
{
"epoch": 0.0037160500573801846,
"grad_norm": 0.2149656116962433,
"learning_rate": 9.851478631379982e-05,
"loss": 0.4645,
"step": 34
},
{
"epoch": 0.003825345647303131,
"grad_norm": 0.22449809312820435,
"learning_rate": 9.829629131445342e-05,
"loss": 0.5203,
"step": 35
},
{
"epoch": 0.003934641237226078,
"grad_norm": 0.21824942529201508,
"learning_rate": 9.806308479691595e-05,
"loss": 0.3769,
"step": 36
},
{
"epoch": 0.004043936827149024,
"grad_norm": 0.37824153900146484,
"learning_rate": 9.781523779815179e-05,
"loss": 0.433,
"step": 37
},
{
"epoch": 0.004153232417071971,
"grad_norm": 1.0172040462493896,
"learning_rate": 9.755282581475769e-05,
"loss": 0.6214,
"step": 38
},
{
"epoch": 0.0042625280069949175,
"grad_norm": 0.28730088472366333,
"learning_rate": 9.727592877996585e-05,
"loss": 0.6083,
"step": 39
},
{
"epoch": 0.0043718235969178645,
"grad_norm": 0.2713054418563843,
"learning_rate": 9.698463103929542e-05,
"loss": 0.5272,
"step": 40
},
{
"epoch": 0.004481119186840811,
"grad_norm": 0.40768107771873474,
"learning_rate": 9.667902132486009e-05,
"loss": 0.6015,
"step": 41
},
{
"epoch": 0.004590414776763758,
"grad_norm": 0.3207384943962097,
"learning_rate": 9.635919272833938e-05,
"loss": 0.6781,
"step": 42
},
{
"epoch": 0.004699710366686705,
"grad_norm": 0.3168956935405731,
"learning_rate": 9.602524267262203e-05,
"loss": 0.6227,
"step": 43
},
{
"epoch": 0.004809005956609651,
"grad_norm": 0.3231648802757263,
"learning_rate": 9.567727288213005e-05,
"loss": 0.7363,
"step": 44
},
{
"epoch": 0.004918301546532598,
"grad_norm": 0.32550543546676636,
"learning_rate": 9.53153893518325e-05,
"loss": 0.6612,
"step": 45
},
{
"epoch": 0.005027597136455544,
"grad_norm": 0.4946689009666443,
"learning_rate": 9.493970231495835e-05,
"loss": 0.7281,
"step": 46
},
{
"epoch": 0.005136892726378491,
"grad_norm": 0.41630205512046814,
"learning_rate": 9.45503262094184e-05,
"loss": 0.5782,
"step": 47
},
{
"epoch": 0.005246188316301437,
"grad_norm": 0.4432646334171295,
"learning_rate": 9.414737964294636e-05,
"loss": 0.6469,
"step": 48
},
{
"epoch": 0.005355483906224384,
"grad_norm": 0.7148913145065308,
"learning_rate": 9.373098535696979e-05,
"loss": 0.9674,
"step": 49
},
{
"epoch": 0.00546477949614733,
"grad_norm": 0.6914791464805603,
"learning_rate": 9.330127018922194e-05,
"loss": 0.5803,
"step": 50
},
{
"epoch": 0.00546477949614733,
"eval_loss": 0.5413779616355896,
"eval_runtime": 1194.3838,
"eval_samples_per_second": 12.902,
"eval_steps_per_second": 6.451,
"step": 50
},
{
"epoch": 0.005574075086070277,
"grad_norm": 0.25189682841300964,
"learning_rate": 9.285836503510562e-05,
"loss": 0.8563,
"step": 51
},
{
"epoch": 0.005683370675993223,
"grad_norm": 0.21652118861675262,
"learning_rate": 9.24024048078213e-05,
"loss": 0.3482,
"step": 52
},
{
"epoch": 0.00579266626591617,
"grad_norm": 0.2325475662946701,
"learning_rate": 9.193352839727121e-05,
"loss": 0.3885,
"step": 53
},
{
"epoch": 0.005901961855839117,
"grad_norm": 0.20061779022216797,
"learning_rate": 9.145187862775209e-05,
"loss": 0.3972,
"step": 54
},
{
"epoch": 0.006011257445762063,
"grad_norm": 0.14447438716888428,
"learning_rate": 9.09576022144496e-05,
"loss": 0.4096,
"step": 55
},
{
"epoch": 0.00612055303568501,
"grad_norm": 0.12227091938257217,
"learning_rate": 9.045084971874738e-05,
"loss": 0.3501,
"step": 56
},
{
"epoch": 0.006229848625607957,
"grad_norm": 0.12859652936458588,
"learning_rate": 8.993177550236464e-05,
"loss": 0.5619,
"step": 57
},
{
"epoch": 0.006339144215530904,
"grad_norm": 0.12088293582201004,
"learning_rate": 8.940053768033609e-05,
"loss": 0.3909,
"step": 58
},
{
"epoch": 0.00644843980545385,
"grad_norm": 0.11673817783594131,
"learning_rate": 8.885729807284856e-05,
"loss": 0.3682,
"step": 59
},
{
"epoch": 0.006557735395376797,
"grad_norm": 0.11229289323091507,
"learning_rate": 8.83022221559489e-05,
"loss": 0.3972,
"step": 60
},
{
"epoch": 0.006667030985299743,
"grad_norm": 0.10862474143505096,
"learning_rate": 8.773547901113862e-05,
"loss": 0.403,
"step": 61
},
{
"epoch": 0.00677632657522269,
"grad_norm": 0.117657370865345,
"learning_rate": 8.715724127386972e-05,
"loss": 0.511,
"step": 62
},
{
"epoch": 0.006885622165145636,
"grad_norm": 0.12006518989801407,
"learning_rate": 8.656768508095853e-05,
"loss": 0.3802,
"step": 63
},
{
"epoch": 0.006994917755068583,
"grad_norm": 0.10380808264017105,
"learning_rate": 8.596699001693255e-05,
"loss": 0.3455,
"step": 64
},
{
"epoch": 0.00710421334499153,
"grad_norm": 0.1075916737318039,
"learning_rate": 8.535533905932738e-05,
"loss": 0.4197,
"step": 65
},
{
"epoch": 0.007213508934914476,
"grad_norm": 0.12685179710388184,
"learning_rate": 8.473291852294987e-05,
"loss": 0.368,
"step": 66
},
{
"epoch": 0.007322804524837423,
"grad_norm": 0.12550005316734314,
"learning_rate": 8.409991800312493e-05,
"loss": 0.5413,
"step": 67
},
{
"epoch": 0.007432100114760369,
"grad_norm": 0.12594176828861237,
"learning_rate": 8.345653031794292e-05,
"loss": 0.4589,
"step": 68
},
{
"epoch": 0.007541395704683316,
"grad_norm": 0.12614470720291138,
"learning_rate": 8.280295144952536e-05,
"loss": 0.4523,
"step": 69
},
{
"epoch": 0.007650691294606262,
"grad_norm": 0.11181683838367462,
"learning_rate": 8.213938048432697e-05,
"loss": 0.3537,
"step": 70
},
{
"epoch": 0.007759986884529209,
"grad_norm": 0.13527949154376984,
"learning_rate": 8.146601955249188e-05,
"loss": 0.4204,
"step": 71
},
{
"epoch": 0.007869282474452156,
"grad_norm": 0.13055859506130219,
"learning_rate": 8.07830737662829e-05,
"loss": 0.3639,
"step": 72
},
{
"epoch": 0.007978578064375103,
"grad_norm": 0.13407902419567108,
"learning_rate": 8.009075115760243e-05,
"loss": 0.3647,
"step": 73
},
{
"epoch": 0.008087873654298049,
"grad_norm": 0.13400597870349884,
"learning_rate": 7.938926261462366e-05,
"loss": 0.4119,
"step": 74
},
{
"epoch": 0.008197169244220997,
"grad_norm": 0.16241265833377838,
"learning_rate": 7.86788218175523e-05,
"loss": 0.5364,
"step": 75
},
{
"epoch": 0.008306464834143943,
"grad_norm": 0.13452617824077606,
"learning_rate": 7.795964517353735e-05,
"loss": 0.3586,
"step": 76
},
{
"epoch": 0.008415760424066889,
"grad_norm": 0.17259980738162994,
"learning_rate": 7.723195175075136e-05,
"loss": 0.4718,
"step": 77
},
{
"epoch": 0.008525056013989835,
"grad_norm": 0.1500622034072876,
"learning_rate": 7.649596321166024e-05,
"loss": 0.4104,
"step": 78
},
{
"epoch": 0.008634351603912783,
"grad_norm": 0.17057955265045166,
"learning_rate": 7.575190374550272e-05,
"loss": 0.5204,
"step": 79
},
{
"epoch": 0.008743647193835729,
"grad_norm": 0.15768682956695557,
"learning_rate": 7.500000000000001e-05,
"loss": 0.4258,
"step": 80
},
{
"epoch": 0.008852942783758675,
"grad_norm": 0.1671830117702484,
"learning_rate": 7.424048101231686e-05,
"loss": 0.3407,
"step": 81
},
{
"epoch": 0.008962238373681621,
"grad_norm": 0.17148494720458984,
"learning_rate": 7.347357813929454e-05,
"loss": 0.4753,
"step": 82
},
{
"epoch": 0.009071533963604569,
"grad_norm": 0.14277490973472595,
"learning_rate": 7.269952498697734e-05,
"loss": 0.3654,
"step": 83
},
{
"epoch": 0.009180829553527515,
"grad_norm": 0.17424607276916504,
"learning_rate": 7.191855733945387e-05,
"loss": 0.5099,
"step": 84
},
{
"epoch": 0.009290125143450461,
"grad_norm": 0.191071555018425,
"learning_rate": 7.113091308703498e-05,
"loss": 0.5481,
"step": 85
},
{
"epoch": 0.00939942073337341,
"grad_norm": 0.22640280425548553,
"learning_rate": 7.033683215379002e-05,
"loss": 0.5513,
"step": 86
},
{
"epoch": 0.009508716323296355,
"grad_norm": 0.16032098233699799,
"learning_rate": 6.953655642446368e-05,
"loss": 0.438,
"step": 87
},
{
"epoch": 0.009618011913219301,
"grad_norm": 0.20057062804698944,
"learning_rate": 6.873032967079561e-05,
"loss": 0.4187,
"step": 88
},
{
"epoch": 0.009727307503142248,
"grad_norm": 0.25190460681915283,
"learning_rate": 6.7918397477265e-05,
"loss": 0.686,
"step": 89
},
{
"epoch": 0.009836603093065195,
"grad_norm": 0.2412964105606079,
"learning_rate": 6.710100716628344e-05,
"loss": 0.6421,
"step": 90
},
{
"epoch": 0.009945898682988142,
"grad_norm": 0.2152530401945114,
"learning_rate": 6.627840772285784e-05,
"loss": 0.3452,
"step": 91
},
{
"epoch": 0.010055194272911088,
"grad_norm": 0.2889910936355591,
"learning_rate": 6.545084971874738e-05,
"loss": 0.6647,
"step": 92
},
{
"epoch": 0.010164489862834034,
"grad_norm": 0.25227007269859314,
"learning_rate": 6.461858523613684e-05,
"loss": 0.5819,
"step": 93
},
{
"epoch": 0.010273785452756982,
"grad_norm": 0.29229801893234253,
"learning_rate": 6.378186779084995e-05,
"loss": 0.6188,
"step": 94
},
{
"epoch": 0.010383081042679928,
"grad_norm": 0.3063337504863739,
"learning_rate": 6.294095225512603e-05,
"loss": 0.6259,
"step": 95
},
{
"epoch": 0.010492376632602874,
"grad_norm": 0.30890288949012756,
"learning_rate": 6.209609477998338e-05,
"loss": 0.6699,
"step": 96
},
{
"epoch": 0.010601672222525822,
"grad_norm": 0.3483825922012329,
"learning_rate": 6.124755271719325e-05,
"loss": 0.6592,
"step": 97
},
{
"epoch": 0.010710967812448768,
"grad_norm": 0.344511479139328,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.5184,
"step": 98
},
{
"epoch": 0.010820263402371714,
"grad_norm": 0.5086371898651123,
"learning_rate": 5.9540449768827246e-05,
"loss": 0.7996,
"step": 99
},
{
"epoch": 0.01092955899229466,
"grad_norm": 0.6137983798980713,
"learning_rate": 5.868240888334653e-05,
"loss": 0.9048,
"step": 100
},
{
"epoch": 0.01092955899229466,
"eval_loss": 0.487389475107193,
"eval_runtime": 1194.2587,
"eval_samples_per_second": 12.903,
"eval_steps_per_second": 6.452,
"step": 100
},
{
"epoch": 0.011038854582217608,
"grad_norm": 0.08348676562309265,
"learning_rate": 5.782172325201155e-05,
"loss": 1.0152,
"step": 101
},
{
"epoch": 0.011148150172140554,
"grad_norm": 0.09717176854610443,
"learning_rate": 5.695865504800327e-05,
"loss": 0.4026,
"step": 102
},
{
"epoch": 0.0112574457620635,
"grad_norm": 0.10635527223348618,
"learning_rate": 5.6093467170257374e-05,
"loss": 0.3539,
"step": 103
},
{
"epoch": 0.011366741351986447,
"grad_norm": 0.11456354707479477,
"learning_rate": 5.522642316338268e-05,
"loss": 0.4686,
"step": 104
},
{
"epoch": 0.011476036941909394,
"grad_norm": 0.1162208616733551,
"learning_rate": 5.435778713738292e-05,
"loss": 0.292,
"step": 105
},
{
"epoch": 0.01158533253183234,
"grad_norm": 0.126183420419693,
"learning_rate": 5.348782368720626e-05,
"loss": 0.56,
"step": 106
},
{
"epoch": 0.011694628121755287,
"grad_norm": 0.11952321231365204,
"learning_rate": 5.26167978121472e-05,
"loss": 0.3656,
"step": 107
},
{
"epoch": 0.011803923711678235,
"grad_norm": 0.12617449462413788,
"learning_rate": 5.174497483512506e-05,
"loss": 0.43,
"step": 108
},
{
"epoch": 0.01191321930160118,
"grad_norm": 0.12929527461528778,
"learning_rate": 5.0872620321864185e-05,
"loss": 0.4259,
"step": 109
},
{
"epoch": 0.012022514891524127,
"grad_norm": 0.11484142392873764,
"learning_rate": 5e-05,
"loss": 0.3938,
"step": 110
},
{
"epoch": 0.012131810481447073,
"grad_norm": 0.09470567852258682,
"learning_rate": 4.912737967813583e-05,
"loss": 0.2844,
"step": 111
},
{
"epoch": 0.01224110607137002,
"grad_norm": 0.10879397392272949,
"learning_rate": 4.825502516487497e-05,
"loss": 0.3645,
"step": 112
},
{
"epoch": 0.012350401661292967,
"grad_norm": 0.10353327542543411,
"learning_rate": 4.738320218785281e-05,
"loss": 0.4109,
"step": 113
},
{
"epoch": 0.012459697251215913,
"grad_norm": 0.10917459428310394,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.3751,
"step": 114
},
{
"epoch": 0.01256899284113886,
"grad_norm": 0.11443409323692322,
"learning_rate": 4.564221286261709e-05,
"loss": 0.4385,
"step": 115
},
{
"epoch": 0.012678288431061807,
"grad_norm": 0.12315183877944946,
"learning_rate": 4.477357683661734e-05,
"loss": 0.4995,
"step": 116
},
{
"epoch": 0.012787584020984753,
"grad_norm": 0.1159660667181015,
"learning_rate": 4.390653282974264e-05,
"loss": 0.478,
"step": 117
},
{
"epoch": 0.0128968796109077,
"grad_norm": 0.11784326285123825,
"learning_rate": 4.3041344951996746e-05,
"loss": 0.421,
"step": 118
},
{
"epoch": 0.013006175200830647,
"grad_norm": 0.12483936548233032,
"learning_rate": 4.2178276747988446e-05,
"loss": 0.434,
"step": 119
},
{
"epoch": 0.013115470790753593,
"grad_norm": 0.13112543523311615,
"learning_rate": 4.131759111665349e-05,
"loss": 0.4981,
"step": 120
},
{
"epoch": 0.01322476638067654,
"grad_norm": 0.12915010750293732,
"learning_rate": 4.045955023117276e-05,
"loss": 0.5198,
"step": 121
},
{
"epoch": 0.013334061970599486,
"grad_norm": 0.12868228554725647,
"learning_rate": 3.960441545911204e-05,
"loss": 0.4058,
"step": 122
},
{
"epoch": 0.013443357560522434,
"grad_norm": 0.1531195491552353,
"learning_rate": 3.875244728280676e-05,
"loss": 0.4973,
"step": 123
},
{
"epoch": 0.01355265315044538,
"grad_norm": 0.1404736340045929,
"learning_rate": 3.790390522001662e-05,
"loss": 0.4539,
"step": 124
},
{
"epoch": 0.013661948740368326,
"grad_norm": 0.1469733566045761,
"learning_rate": 3.705904774487396e-05,
"loss": 0.4203,
"step": 125
},
{
"epoch": 0.013771244330291272,
"grad_norm": 0.14171703159809113,
"learning_rate": 3.6218132209150045e-05,
"loss": 0.4354,
"step": 126
},
{
"epoch": 0.01388053992021422,
"grad_norm": 0.15275560319423676,
"learning_rate": 3.5381414763863166e-05,
"loss": 0.5334,
"step": 127
},
{
"epoch": 0.013989835510137166,
"grad_norm": 0.16623587906360626,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.748,
"step": 128
},
{
"epoch": 0.014099131100060112,
"grad_norm": 0.15390785038471222,
"learning_rate": 3.372159227714218e-05,
"loss": 0.4446,
"step": 129
},
{
"epoch": 0.01420842668998306,
"grad_norm": 0.16154845058918,
"learning_rate": 3.289899283371657e-05,
"loss": 0.5223,
"step": 130
},
{
"epoch": 0.014317722279906006,
"grad_norm": 0.17848701775074005,
"learning_rate": 3.2081602522734986e-05,
"loss": 0.4334,
"step": 131
},
{
"epoch": 0.014427017869828952,
"grad_norm": 0.18458040058612823,
"learning_rate": 3.12696703292044e-05,
"loss": 0.5952,
"step": 132
},
{
"epoch": 0.014536313459751898,
"grad_norm": 0.16637226939201355,
"learning_rate": 3.046344357553632e-05,
"loss": 0.4745,
"step": 133
},
{
"epoch": 0.014645609049674846,
"grad_norm": 0.17600120604038239,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.4086,
"step": 134
},
{
"epoch": 0.014754904639597792,
"grad_norm": 0.20289093255996704,
"learning_rate": 2.886908691296504e-05,
"loss": 0.4969,
"step": 135
},
{
"epoch": 0.014864200229520739,
"grad_norm": 0.1863214075565338,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.4525,
"step": 136
},
{
"epoch": 0.014973495819443685,
"grad_norm": 0.19627094268798828,
"learning_rate": 2.7300475013022663e-05,
"loss": 0.6143,
"step": 137
},
{
"epoch": 0.015082791409366633,
"grad_norm": 0.1941378265619278,
"learning_rate": 2.6526421860705473e-05,
"loss": 0.3371,
"step": 138
},
{
"epoch": 0.015192086999289579,
"grad_norm": 0.2424362599849701,
"learning_rate": 2.575951898768315e-05,
"loss": 0.6709,
"step": 139
},
{
"epoch": 0.015301382589212525,
"grad_norm": 0.23324838280677795,
"learning_rate": 2.500000000000001e-05,
"loss": 0.6355,
"step": 140
},
{
"epoch": 0.015410678179135473,
"grad_norm": 0.23842982947826385,
"learning_rate": 2.4248096254497288e-05,
"loss": 0.5407,
"step": 141
},
{
"epoch": 0.015519973769058419,
"grad_norm": 0.2603646516799927,
"learning_rate": 2.350403678833976e-05,
"loss": 0.5855,
"step": 142
},
{
"epoch": 0.015629269358981367,
"grad_norm": 0.329253226518631,
"learning_rate": 2.2768048249248648e-05,
"loss": 0.6169,
"step": 143
},
{
"epoch": 0.015738564948904313,
"grad_norm": 0.2668045461177826,
"learning_rate": 2.2040354826462668e-05,
"loss": 0.52,
"step": 144
},
{
"epoch": 0.01584786053882726,
"grad_norm": 0.28101295232772827,
"learning_rate": 2.132117818244771e-05,
"loss": 0.5727,
"step": 145
},
{
"epoch": 0.015957156128750205,
"grad_norm": 0.28658443689346313,
"learning_rate": 2.061073738537635e-05,
"loss": 0.5835,
"step": 146
},
{
"epoch": 0.01606645171867315,
"grad_norm": 0.3398421108722687,
"learning_rate": 1.9909248842397584e-05,
"loss": 0.6378,
"step": 147
},
{
"epoch": 0.016175747308596097,
"grad_norm": 0.3835708200931549,
"learning_rate": 1.9216926233717085e-05,
"loss": 0.598,
"step": 148
},
{
"epoch": 0.016285042898519043,
"grad_norm": 0.7383447885513306,
"learning_rate": 1.8533980447508137e-05,
"loss": 0.8202,
"step": 149
},
{
"epoch": 0.016394338488441993,
"grad_norm": 0.6827495098114014,
"learning_rate": 1.7860619515673033e-05,
"loss": 0.8189,
"step": 150
},
{
"epoch": 0.016394338488441993,
"eval_loss": 0.46980416774749756,
"eval_runtime": 1194.1023,
"eval_samples_per_second": 12.905,
"eval_steps_per_second": 6.453,
"step": 150
},
{
"epoch": 0.01650363407836494,
"grad_norm": 0.05671292915940285,
"learning_rate": 1.7197048550474643e-05,
"loss": 0.3498,
"step": 151
},
{
"epoch": 0.016612929668287885,
"grad_norm": 0.07922675460577011,
"learning_rate": 1.6543469682057106e-05,
"loss": 0.5638,
"step": 152
},
{
"epoch": 0.01672222525821083,
"grad_norm": 0.06751131266355515,
"learning_rate": 1.5900081996875083e-05,
"loss": 0.2989,
"step": 153
},
{
"epoch": 0.016831520848133778,
"grad_norm": 0.08673208206892014,
"learning_rate": 1.526708147705013e-05,
"loss": 0.3434,
"step": 154
},
{
"epoch": 0.016940816438056724,
"grad_norm": 0.10014075040817261,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.3313,
"step": 155
},
{
"epoch": 0.01705011202797967,
"grad_norm": 0.0925699844956398,
"learning_rate": 1.4033009983067452e-05,
"loss": 0.3351,
"step": 156
},
{
"epoch": 0.017159407617902616,
"grad_norm": 0.10073317587375641,
"learning_rate": 1.3432314919041478e-05,
"loss": 0.4239,
"step": 157
},
{
"epoch": 0.017268703207825566,
"grad_norm": 0.09681018441915512,
"learning_rate": 1.2842758726130283e-05,
"loss": 0.3196,
"step": 158
},
{
"epoch": 0.017377998797748512,
"grad_norm": 0.10117655992507935,
"learning_rate": 1.22645209888614e-05,
"loss": 0.3483,
"step": 159
},
{
"epoch": 0.017487294387671458,
"grad_norm": 0.10316099971532822,
"learning_rate": 1.1697777844051105e-05,
"loss": 0.3765,
"step": 160
},
{
"epoch": 0.017596589977594404,
"grad_norm": 0.10998133569955826,
"learning_rate": 1.1142701927151456e-05,
"loss": 0.3845,
"step": 161
},
{
"epoch": 0.01770588556751735,
"grad_norm": 0.10539877414703369,
"learning_rate": 1.0599462319663905e-05,
"loss": 0.4918,
"step": 162
},
{
"epoch": 0.017815181157440296,
"grad_norm": 0.1355060189962387,
"learning_rate": 1.006822449763537e-05,
"loss": 0.472,
"step": 163
},
{
"epoch": 0.017924476747363242,
"grad_norm": 0.12122693657875061,
"learning_rate": 9.549150281252633e-06,
"loss": 0.3635,
"step": 164
},
{
"epoch": 0.018033772337286192,
"grad_norm": 0.11582615971565247,
"learning_rate": 9.042397785550405e-06,
"loss": 0.5667,
"step": 165
},
{
"epoch": 0.018143067927209138,
"grad_norm": 0.12401402741670609,
"learning_rate": 8.548121372247918e-06,
"loss": 0.3543,
"step": 166
},
{
"epoch": 0.018252363517132084,
"grad_norm": 0.12098807841539383,
"learning_rate": 8.066471602728803e-06,
"loss": 0.4069,
"step": 167
},
{
"epoch": 0.01836165910705503,
"grad_norm": 0.12497370690107346,
"learning_rate": 7.597595192178702e-06,
"loss": 0.4353,
"step": 168
},
{
"epoch": 0.018470954696977977,
"grad_norm": 0.11947774142026901,
"learning_rate": 7.1416349648943894e-06,
"loss": 0.4151,
"step": 169
},
{
"epoch": 0.018580250286900923,
"grad_norm": 0.12466960400342941,
"learning_rate": 6.698729810778065e-06,
"loss": 0.3535,
"step": 170
},
{
"epoch": 0.01868954587682387,
"grad_norm": 0.14808349311351776,
"learning_rate": 6.269014643030213e-06,
"loss": 0.531,
"step": 171
},
{
"epoch": 0.01879884146674682,
"grad_norm": 0.13079893589019775,
"learning_rate": 5.852620357053651e-06,
"loss": 0.3183,
"step": 172
},
{
"epoch": 0.018908137056669765,
"grad_norm": 0.153338223695755,
"learning_rate": 5.449673790581611e-06,
"loss": 0.4308,
"step": 173
},
{
"epoch": 0.01901743264659271,
"grad_norm": 0.1578577756881714,
"learning_rate": 5.060297685041659e-06,
"loss": 0.5877,
"step": 174
},
{
"epoch": 0.019126728236515657,
"grad_norm": 0.1331440508365631,
"learning_rate": 4.684610648167503e-06,
"loss": 0.3637,
"step": 175
},
{
"epoch": 0.019236023826438603,
"grad_norm": 0.1452208012342453,
"learning_rate": 4.322727117869951e-06,
"loss": 0.4592,
"step": 176
},
{
"epoch": 0.01934531941636155,
"grad_norm": 0.1602085381746292,
"learning_rate": 3.974757327377981e-06,
"loss": 0.5317,
"step": 177
},
{
"epoch": 0.019454615006284495,
"grad_norm": 0.15811043977737427,
"learning_rate": 3.6408072716606346e-06,
"loss": 0.5555,
"step": 178
},
{
"epoch": 0.01956391059620744,
"grad_norm": 0.1520129144191742,
"learning_rate": 3.3209786751399187e-06,
"loss": 0.4347,
"step": 179
},
{
"epoch": 0.01967320618613039,
"grad_norm": 0.17405475676059723,
"learning_rate": 3.0153689607045845e-06,
"loss": 0.4352,
"step": 180
},
{
"epoch": 0.019782501776053337,
"grad_norm": 0.20877398550510406,
"learning_rate": 2.724071220034158e-06,
"loss": 0.5259,
"step": 181
},
{
"epoch": 0.019891797365976283,
"grad_norm": 0.1546728014945984,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.4277,
"step": 182
},
{
"epoch": 0.02000109295589923,
"grad_norm": 0.207755446434021,
"learning_rate": 2.1847622018482283e-06,
"loss": 0.5322,
"step": 183
},
{
"epoch": 0.020110388545822176,
"grad_norm": 0.17791689932346344,
"learning_rate": 1.9369152030840556e-06,
"loss": 0.3993,
"step": 184
},
{
"epoch": 0.02021968413574512,
"grad_norm": 0.1971198171377182,
"learning_rate": 1.70370868554659e-06,
"loss": 0.4922,
"step": 185
},
{
"epoch": 0.020328979725668068,
"grad_norm": 0.18837548792362213,
"learning_rate": 1.4852136862001764e-06,
"loss": 0.669,
"step": 186
},
{
"epoch": 0.020438275315591017,
"grad_norm": 0.21775005757808685,
"learning_rate": 1.2814967607382432e-06,
"loss": 0.5298,
"step": 187
},
{
"epoch": 0.020547570905513964,
"grad_norm": 0.23758465051651,
"learning_rate": 1.0926199633097157e-06,
"loss": 0.574,
"step": 188
},
{
"epoch": 0.02065686649543691,
"grad_norm": 0.23550760746002197,
"learning_rate": 9.186408276168013e-07,
"loss": 0.6356,
"step": 189
},
{
"epoch": 0.020766162085359856,
"grad_norm": 0.2456381767988205,
"learning_rate": 7.596123493895991e-07,
"loss": 0.5453,
"step": 190
},
{
"epoch": 0.020875457675282802,
"grad_norm": 0.2014353722333908,
"learning_rate": 6.15582970243117e-07,
"loss": 0.4603,
"step": 191
},
{
"epoch": 0.020984753265205748,
"grad_norm": 0.2850938141345978,
"learning_rate": 4.865965629214819e-07,
"loss": 0.6694,
"step": 192
},
{
"epoch": 0.021094048855128694,
"grad_norm": 0.2577400803565979,
"learning_rate": 3.7269241793390085e-07,
"loss": 0.6761,
"step": 193
},
{
"epoch": 0.021203344445051644,
"grad_norm": 0.2811027467250824,
"learning_rate": 2.7390523158633554e-07,
"loss": 0.621,
"step": 194
},
{
"epoch": 0.02131264003497459,
"grad_norm": 0.2799067199230194,
"learning_rate": 1.9026509541272275e-07,
"loss": 0.6045,
"step": 195
},
{
"epoch": 0.021421935624897536,
"grad_norm": 0.40083521604537964,
"learning_rate": 1.2179748700879012e-07,
"loss": 0.8314,
"step": 196
},
{
"epoch": 0.021531231214820482,
"grad_norm": 0.48128101229667664,
"learning_rate": 6.852326227130834e-08,
"loss": 0.5519,
"step": 197
},
{
"epoch": 0.02164052680474343,
"grad_norm": 0.3779641389846802,
"learning_rate": 3.04586490452119e-08,
"loss": 0.6474,
"step": 198
},
{
"epoch": 0.021749822394666374,
"grad_norm": 0.38349881768226624,
"learning_rate": 7.615242180436522e-09,
"loss": 0.6104,
"step": 199
},
{
"epoch": 0.02185911798458932,
"grad_norm": 0.6852728724479675,
"learning_rate": 0.0,
"loss": 0.8279,
"step": 200
},
{
"epoch": 0.02185911798458932,
"eval_loss": 0.46923279762268066,
"eval_runtime": 1195.4856,
"eval_samples_per_second": 12.89,
"eval_steps_per_second": 6.445,
"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": 2.6780376395415552e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}