prxy5606's picture
Training in progress, step 150, checkpoint
4f6cae8 verified
raw
history blame
27.7 kB
{
"best_metric": 0.9018179774284363,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.2579535683576956,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017196904557179708,
"grad_norm": 0.04371219500899315,
"learning_rate": 5e-06,
"loss": 0.5013,
"step": 1
},
{
"epoch": 0.0017196904557179708,
"eval_loss": 1.1150983572006226,
"eval_runtime": 26.0196,
"eval_samples_per_second": 37.664,
"eval_steps_per_second": 18.832,
"step": 1
},
{
"epoch": 0.0034393809114359416,
"grad_norm": 0.05066497623920441,
"learning_rate": 1e-05,
"loss": 0.6556,
"step": 2
},
{
"epoch": 0.005159071367153913,
"grad_norm": 0.05329379439353943,
"learning_rate": 1.5e-05,
"loss": 0.6847,
"step": 3
},
{
"epoch": 0.006878761822871883,
"grad_norm": 0.051895491778850555,
"learning_rate": 2e-05,
"loss": 0.5981,
"step": 4
},
{
"epoch": 0.008598452278589854,
"grad_norm": 0.06517327576875687,
"learning_rate": 2.5e-05,
"loss": 0.6962,
"step": 5
},
{
"epoch": 0.010318142734307825,
"grad_norm": 0.05350270867347717,
"learning_rate": 3e-05,
"loss": 0.6678,
"step": 6
},
{
"epoch": 0.012037833190025795,
"grad_norm": 0.062394555658102036,
"learning_rate": 3.5e-05,
"loss": 0.706,
"step": 7
},
{
"epoch": 0.013757523645743766,
"grad_norm": 0.058834996074438095,
"learning_rate": 4e-05,
"loss": 0.7226,
"step": 8
},
{
"epoch": 0.015477214101461736,
"grad_norm": 0.058221857994794846,
"learning_rate": 4.5e-05,
"loss": 0.6948,
"step": 9
},
{
"epoch": 0.017196904557179708,
"grad_norm": 0.05588304251432419,
"learning_rate": 5e-05,
"loss": 0.6798,
"step": 10
},
{
"epoch": 0.018916595012897677,
"grad_norm": 0.0636599138379097,
"learning_rate": 5.500000000000001e-05,
"loss": 0.7023,
"step": 11
},
{
"epoch": 0.02063628546861565,
"grad_norm": 0.06145975738763809,
"learning_rate": 6e-05,
"loss": 0.6432,
"step": 12
},
{
"epoch": 0.02235597592433362,
"grad_norm": 0.06953848898410797,
"learning_rate": 6.500000000000001e-05,
"loss": 0.7669,
"step": 13
},
{
"epoch": 0.02407566638005159,
"grad_norm": 0.07056722790002823,
"learning_rate": 7e-05,
"loss": 0.8379,
"step": 14
},
{
"epoch": 0.025795356835769563,
"grad_norm": 0.06908471137285233,
"learning_rate": 7.500000000000001e-05,
"loss": 0.8114,
"step": 15
},
{
"epoch": 0.027515047291487533,
"grad_norm": 0.06860286742448807,
"learning_rate": 8e-05,
"loss": 0.765,
"step": 16
},
{
"epoch": 0.029234737747205503,
"grad_norm": 0.06991557031869888,
"learning_rate": 8.5e-05,
"loss": 0.8112,
"step": 17
},
{
"epoch": 0.030954428202923472,
"grad_norm": 0.07742810249328613,
"learning_rate": 9e-05,
"loss": 0.8295,
"step": 18
},
{
"epoch": 0.03267411865864144,
"grad_norm": 0.08711075782775879,
"learning_rate": 9.5e-05,
"loss": 0.8386,
"step": 19
},
{
"epoch": 0.034393809114359415,
"grad_norm": 0.08179605007171631,
"learning_rate": 0.0001,
"loss": 0.9093,
"step": 20
},
{
"epoch": 0.03611349957007739,
"grad_norm": 0.08795295655727386,
"learning_rate": 9.999238475781957e-05,
"loss": 0.9145,
"step": 21
},
{
"epoch": 0.037833190025795355,
"grad_norm": 0.08331762999296188,
"learning_rate": 9.99695413509548e-05,
"loss": 0.9265,
"step": 22
},
{
"epoch": 0.03955288048151333,
"grad_norm": 0.07908172160387039,
"learning_rate": 9.99314767377287e-05,
"loss": 0.9195,
"step": 23
},
{
"epoch": 0.0412725709372313,
"grad_norm": 0.09061425179243088,
"learning_rate": 9.987820251299122e-05,
"loss": 0.8748,
"step": 24
},
{
"epoch": 0.04299226139294927,
"grad_norm": 0.0851019099354744,
"learning_rate": 9.980973490458728e-05,
"loss": 0.7701,
"step": 25
},
{
"epoch": 0.04471195184866724,
"grad_norm": 0.09329686313867569,
"learning_rate": 9.972609476841367e-05,
"loss": 0.8657,
"step": 26
},
{
"epoch": 0.046431642304385214,
"grad_norm": 0.09710376709699631,
"learning_rate": 9.962730758206611e-05,
"loss": 0.9217,
"step": 27
},
{
"epoch": 0.04815133276010318,
"grad_norm": 0.10121080279350281,
"learning_rate": 9.951340343707852e-05,
"loss": 0.8995,
"step": 28
},
{
"epoch": 0.04987102321582115,
"grad_norm": 0.1065475270152092,
"learning_rate": 9.938441702975689e-05,
"loss": 0.8886,
"step": 29
},
{
"epoch": 0.051590713671539126,
"grad_norm": 0.11212456971406937,
"learning_rate": 9.924038765061042e-05,
"loss": 0.867,
"step": 30
},
{
"epoch": 0.05331040412725709,
"grad_norm": 0.0965503603219986,
"learning_rate": 9.908135917238321e-05,
"loss": 0.806,
"step": 31
},
{
"epoch": 0.055030094582975066,
"grad_norm": 0.10261840373277664,
"learning_rate": 9.890738003669029e-05,
"loss": 0.9247,
"step": 32
},
{
"epoch": 0.05674978503869303,
"grad_norm": 0.11739654093980789,
"learning_rate": 9.871850323926177e-05,
"loss": 0.927,
"step": 33
},
{
"epoch": 0.058469475494411005,
"grad_norm": 0.12067130953073502,
"learning_rate": 9.851478631379982e-05,
"loss": 0.9822,
"step": 34
},
{
"epoch": 0.06018916595012898,
"grad_norm": 0.11332730948925018,
"learning_rate": 9.829629131445342e-05,
"loss": 0.8538,
"step": 35
},
{
"epoch": 0.061908856405846945,
"grad_norm": 0.12802854180335999,
"learning_rate": 9.806308479691595e-05,
"loss": 0.9749,
"step": 36
},
{
"epoch": 0.06362854686156492,
"grad_norm": 0.13656459748744965,
"learning_rate": 9.781523779815179e-05,
"loss": 0.9501,
"step": 37
},
{
"epoch": 0.06534823731728288,
"grad_norm": 0.1332613080739975,
"learning_rate": 9.755282581475769e-05,
"loss": 1.0124,
"step": 38
},
{
"epoch": 0.06706792777300086,
"grad_norm": 0.168551504611969,
"learning_rate": 9.727592877996585e-05,
"loss": 1.1085,
"step": 39
},
{
"epoch": 0.06878761822871883,
"grad_norm": 0.16357570886611938,
"learning_rate": 9.698463103929542e-05,
"loss": 1.0838,
"step": 40
},
{
"epoch": 0.0705073086844368,
"grad_norm": 0.18186220526695251,
"learning_rate": 9.667902132486009e-05,
"loss": 1.2419,
"step": 41
},
{
"epoch": 0.07222699914015478,
"grad_norm": 0.25837743282318115,
"learning_rate": 9.635919272833938e-05,
"loss": 1.5677,
"step": 42
},
{
"epoch": 0.07394668959587274,
"grad_norm": 0.2586553692817688,
"learning_rate": 9.602524267262203e-05,
"loss": 1.3784,
"step": 43
},
{
"epoch": 0.07566638005159071,
"grad_norm": 0.2590441107749939,
"learning_rate": 9.567727288213005e-05,
"loss": 1.5176,
"step": 44
},
{
"epoch": 0.07738607050730868,
"grad_norm": 0.240685373544693,
"learning_rate": 9.53153893518325e-05,
"loss": 1.5495,
"step": 45
},
{
"epoch": 0.07910576096302666,
"grad_norm": 0.2492353618144989,
"learning_rate": 9.493970231495835e-05,
"loss": 1.3381,
"step": 46
},
{
"epoch": 0.08082545141874463,
"grad_norm": 0.2738623023033142,
"learning_rate": 9.45503262094184e-05,
"loss": 1.5593,
"step": 47
},
{
"epoch": 0.0825451418744626,
"grad_norm": 0.362883061170578,
"learning_rate": 9.414737964294636e-05,
"loss": 1.6339,
"step": 48
},
{
"epoch": 0.08426483233018056,
"grad_norm": 0.4202761650085449,
"learning_rate": 9.373098535696979e-05,
"loss": 1.6848,
"step": 49
},
{
"epoch": 0.08598452278589853,
"grad_norm": 0.9379512667655945,
"learning_rate": 9.330127018922194e-05,
"loss": 2.2938,
"step": 50
},
{
"epoch": 0.08598452278589853,
"eval_loss": 0.9957740902900696,
"eval_runtime": 26.1033,
"eval_samples_per_second": 37.543,
"eval_steps_per_second": 18.772,
"step": 50
},
{
"epoch": 0.08770421324161651,
"grad_norm": 0.15448810160160065,
"learning_rate": 9.285836503510562e-05,
"loss": 0.6494,
"step": 51
},
{
"epoch": 0.08942390369733448,
"grad_norm": 0.19541579484939575,
"learning_rate": 9.24024048078213e-05,
"loss": 0.6789,
"step": 52
},
{
"epoch": 0.09114359415305245,
"grad_norm": 0.22956673800945282,
"learning_rate": 9.193352839727121e-05,
"loss": 0.6399,
"step": 53
},
{
"epoch": 0.09286328460877043,
"grad_norm": 0.20343832671642303,
"learning_rate": 9.145187862775209e-05,
"loss": 0.7056,
"step": 54
},
{
"epoch": 0.09458297506448839,
"grad_norm": 0.20558185875415802,
"learning_rate": 9.09576022144496e-05,
"loss": 0.695,
"step": 55
},
{
"epoch": 0.09630266552020636,
"grad_norm": 0.20323364436626434,
"learning_rate": 9.045084971874738e-05,
"loss": 0.7068,
"step": 56
},
{
"epoch": 0.09802235597592433,
"grad_norm": 0.18025411665439606,
"learning_rate": 8.993177550236464e-05,
"loss": 0.6984,
"step": 57
},
{
"epoch": 0.0997420464316423,
"grad_norm": 0.15938173234462738,
"learning_rate": 8.940053768033609e-05,
"loss": 0.6744,
"step": 58
},
{
"epoch": 0.10146173688736028,
"grad_norm": 0.1582622081041336,
"learning_rate": 8.885729807284856e-05,
"loss": 0.7612,
"step": 59
},
{
"epoch": 0.10318142734307825,
"grad_norm": 0.12570132315158844,
"learning_rate": 8.83022221559489e-05,
"loss": 0.7241,
"step": 60
},
{
"epoch": 0.10490111779879621,
"grad_norm": 0.10931485146284103,
"learning_rate": 8.773547901113862e-05,
"loss": 0.7559,
"step": 61
},
{
"epoch": 0.10662080825451418,
"grad_norm": 0.09841756522655487,
"learning_rate": 8.715724127386972e-05,
"loss": 0.6782,
"step": 62
},
{
"epoch": 0.10834049871023216,
"grad_norm": 0.09882379323244095,
"learning_rate": 8.656768508095853e-05,
"loss": 0.7601,
"step": 63
},
{
"epoch": 0.11006018916595013,
"grad_norm": 0.10225917398929596,
"learning_rate": 8.596699001693255e-05,
"loss": 0.7911,
"step": 64
},
{
"epoch": 0.1117798796216681,
"grad_norm": 0.10474953055381775,
"learning_rate": 8.535533905932738e-05,
"loss": 0.7669,
"step": 65
},
{
"epoch": 0.11349957007738606,
"grad_norm": 0.10357484966516495,
"learning_rate": 8.473291852294987e-05,
"loss": 0.7644,
"step": 66
},
{
"epoch": 0.11521926053310404,
"grad_norm": 0.11238912492990494,
"learning_rate": 8.409991800312493e-05,
"loss": 0.8878,
"step": 67
},
{
"epoch": 0.11693895098882201,
"grad_norm": 0.11020366847515106,
"learning_rate": 8.345653031794292e-05,
"loss": 0.8643,
"step": 68
},
{
"epoch": 0.11865864144453998,
"grad_norm": 0.10074474662542343,
"learning_rate": 8.280295144952536e-05,
"loss": 0.8067,
"step": 69
},
{
"epoch": 0.12037833190025796,
"grad_norm": 0.09557520598173141,
"learning_rate": 8.213938048432697e-05,
"loss": 0.7716,
"step": 70
},
{
"epoch": 0.12209802235597593,
"grad_norm": 0.10227945446968079,
"learning_rate": 8.146601955249188e-05,
"loss": 0.923,
"step": 71
},
{
"epoch": 0.12381771281169389,
"grad_norm": 0.10992958396673203,
"learning_rate": 8.07830737662829e-05,
"loss": 0.8756,
"step": 72
},
{
"epoch": 0.12553740326741186,
"grad_norm": 0.10675280541181564,
"learning_rate": 8.009075115760243e-05,
"loss": 0.7982,
"step": 73
},
{
"epoch": 0.12725709372312985,
"grad_norm": 0.1144600510597229,
"learning_rate": 7.938926261462366e-05,
"loss": 0.7169,
"step": 74
},
{
"epoch": 0.1289767841788478,
"grad_norm": 0.10181998461484909,
"learning_rate": 7.86788218175523e-05,
"loss": 0.736,
"step": 75
},
{
"epoch": 0.13069647463456577,
"grad_norm": 0.10681930184364319,
"learning_rate": 7.795964517353735e-05,
"loss": 0.8836,
"step": 76
},
{
"epoch": 0.13241616509028376,
"grad_norm": 0.11621927469968796,
"learning_rate": 7.723195175075136e-05,
"loss": 0.8581,
"step": 77
},
{
"epoch": 0.13413585554600171,
"grad_norm": 0.09889838099479675,
"learning_rate": 7.649596321166024e-05,
"loss": 0.7897,
"step": 78
},
{
"epoch": 0.1358555460017197,
"grad_norm": 0.09543070942163467,
"learning_rate": 7.575190374550272e-05,
"loss": 0.8192,
"step": 79
},
{
"epoch": 0.13757523645743766,
"grad_norm": 0.11200384050607681,
"learning_rate": 7.500000000000001e-05,
"loss": 0.7359,
"step": 80
},
{
"epoch": 0.13929492691315562,
"grad_norm": 0.10140563547611237,
"learning_rate": 7.424048101231686e-05,
"loss": 0.824,
"step": 81
},
{
"epoch": 0.1410146173688736,
"grad_norm": 0.102725550532341,
"learning_rate": 7.347357813929454e-05,
"loss": 0.8458,
"step": 82
},
{
"epoch": 0.14273430782459157,
"grad_norm": 0.10617943853139877,
"learning_rate": 7.269952498697734e-05,
"loss": 0.7649,
"step": 83
},
{
"epoch": 0.14445399828030955,
"grad_norm": 0.10800634324550629,
"learning_rate": 7.191855733945387e-05,
"loss": 0.7318,
"step": 84
},
{
"epoch": 0.1461736887360275,
"grad_norm": 0.1077365055680275,
"learning_rate": 7.113091308703498e-05,
"loss": 0.8679,
"step": 85
},
{
"epoch": 0.14789337919174547,
"grad_norm": 0.11147390305995941,
"learning_rate": 7.033683215379002e-05,
"loss": 0.8635,
"step": 86
},
{
"epoch": 0.14961306964746346,
"grad_norm": 0.13498784601688385,
"learning_rate": 6.953655642446368e-05,
"loss": 0.9565,
"step": 87
},
{
"epoch": 0.15133276010318142,
"grad_norm": 0.1289157271385193,
"learning_rate": 6.873032967079561e-05,
"loss": 1.041,
"step": 88
},
{
"epoch": 0.1530524505588994,
"grad_norm": 0.1310902088880539,
"learning_rate": 6.7918397477265e-05,
"loss": 0.8777,
"step": 89
},
{
"epoch": 0.15477214101461736,
"grad_norm": 0.160873144865036,
"learning_rate": 6.710100716628344e-05,
"loss": 1.1091,
"step": 90
},
{
"epoch": 0.15649183147033535,
"grad_norm": 0.15653099119663239,
"learning_rate": 6.627840772285784e-05,
"loss": 1.1321,
"step": 91
},
{
"epoch": 0.1582115219260533,
"grad_norm": 0.19784240424633026,
"learning_rate": 6.545084971874738e-05,
"loss": 1.1846,
"step": 92
},
{
"epoch": 0.15993121238177127,
"grad_norm": 0.19561642408370972,
"learning_rate": 6.461858523613684e-05,
"loss": 1.3051,
"step": 93
},
{
"epoch": 0.16165090283748926,
"grad_norm": 0.19523312151432037,
"learning_rate": 6.378186779084995e-05,
"loss": 1.3682,
"step": 94
},
{
"epoch": 0.16337059329320722,
"grad_norm": 0.21068979799747467,
"learning_rate": 6.294095225512603e-05,
"loss": 1.2489,
"step": 95
},
{
"epoch": 0.1650902837489252,
"grad_norm": 0.20077933371067047,
"learning_rate": 6.209609477998338e-05,
"loss": 1.3355,
"step": 96
},
{
"epoch": 0.16680997420464316,
"grad_norm": 0.21723942458629608,
"learning_rate": 6.124755271719325e-05,
"loss": 1.6464,
"step": 97
},
{
"epoch": 0.16852966466036112,
"grad_norm": 0.28459852933883667,
"learning_rate": 6.0395584540887963e-05,
"loss": 1.7727,
"step": 98
},
{
"epoch": 0.1702493551160791,
"grad_norm": 0.37411239743232727,
"learning_rate": 5.9540449768827246e-05,
"loss": 2.0809,
"step": 99
},
{
"epoch": 0.17196904557179707,
"grad_norm": 0.6213313937187195,
"learning_rate": 5.868240888334653e-05,
"loss": 2.2677,
"step": 100
},
{
"epoch": 0.17196904557179707,
"eval_loss": 0.9143250584602356,
"eval_runtime": 26.1292,
"eval_samples_per_second": 37.506,
"eval_steps_per_second": 18.753,
"step": 100
},
{
"epoch": 0.17368873602751506,
"grad_norm": 0.0647941306233406,
"learning_rate": 5.782172325201155e-05,
"loss": 0.5759,
"step": 101
},
{
"epoch": 0.17540842648323302,
"grad_norm": 0.07381158322095871,
"learning_rate": 5.695865504800327e-05,
"loss": 0.5957,
"step": 102
},
{
"epoch": 0.177128116938951,
"grad_norm": 0.07971695810556412,
"learning_rate": 5.6093467170257374e-05,
"loss": 0.6366,
"step": 103
},
{
"epoch": 0.17884780739466896,
"grad_norm": 0.073166623711586,
"learning_rate": 5.522642316338268e-05,
"loss": 0.5878,
"step": 104
},
{
"epoch": 0.18056749785038692,
"grad_norm": 0.08162125200033188,
"learning_rate": 5.435778713738292e-05,
"loss": 0.6366,
"step": 105
},
{
"epoch": 0.1822871883061049,
"grad_norm": 0.0808592289686203,
"learning_rate": 5.348782368720626e-05,
"loss": 0.6407,
"step": 106
},
{
"epoch": 0.18400687876182287,
"grad_norm": 0.09443782269954681,
"learning_rate": 5.26167978121472e-05,
"loss": 0.6592,
"step": 107
},
{
"epoch": 0.18572656921754085,
"grad_norm": 0.08486565947532654,
"learning_rate": 5.174497483512506e-05,
"loss": 0.6987,
"step": 108
},
{
"epoch": 0.1874462596732588,
"grad_norm": 0.08635884523391724,
"learning_rate": 5.0872620321864185e-05,
"loss": 0.6941,
"step": 109
},
{
"epoch": 0.18916595012897677,
"grad_norm": 0.0893407091498375,
"learning_rate": 5e-05,
"loss": 0.7226,
"step": 110
},
{
"epoch": 0.19088564058469476,
"grad_norm": 0.09018551558256149,
"learning_rate": 4.912737967813583e-05,
"loss": 0.7208,
"step": 111
},
{
"epoch": 0.19260533104041272,
"grad_norm": 0.07536663860082626,
"learning_rate": 4.825502516487497e-05,
"loss": 0.5846,
"step": 112
},
{
"epoch": 0.1943250214961307,
"grad_norm": 0.08711609989404678,
"learning_rate": 4.738320218785281e-05,
"loss": 0.6862,
"step": 113
},
{
"epoch": 0.19604471195184867,
"grad_norm": 0.06564276665449142,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.6931,
"step": 114
},
{
"epoch": 0.19776440240756663,
"grad_norm": 0.08047173917293549,
"learning_rate": 4.564221286261709e-05,
"loss": 0.7913,
"step": 115
},
{
"epoch": 0.1994840928632846,
"grad_norm": 0.08029168099164963,
"learning_rate": 4.477357683661734e-05,
"loss": 0.6937,
"step": 116
},
{
"epoch": 0.20120378331900257,
"grad_norm": 0.07913923263549805,
"learning_rate": 4.390653282974264e-05,
"loss": 0.7687,
"step": 117
},
{
"epoch": 0.20292347377472056,
"grad_norm": 0.0775957927107811,
"learning_rate": 4.3041344951996746e-05,
"loss": 0.7796,
"step": 118
},
{
"epoch": 0.20464316423043852,
"grad_norm": 0.07749712467193604,
"learning_rate": 4.2178276747988446e-05,
"loss": 0.7374,
"step": 119
},
{
"epoch": 0.2063628546861565,
"grad_norm": 0.07898925989866257,
"learning_rate": 4.131759111665349e-05,
"loss": 0.7796,
"step": 120
},
{
"epoch": 0.20808254514187446,
"grad_norm": 0.07860884070396423,
"learning_rate": 4.045955023117276e-05,
"loss": 0.7887,
"step": 121
},
{
"epoch": 0.20980223559759242,
"grad_norm": 0.077889084815979,
"learning_rate": 3.960441545911204e-05,
"loss": 0.8293,
"step": 122
},
{
"epoch": 0.2115219260533104,
"grad_norm": 0.07636513561010361,
"learning_rate": 3.875244728280676e-05,
"loss": 0.7912,
"step": 123
},
{
"epoch": 0.21324161650902837,
"grad_norm": 0.07946857064962387,
"learning_rate": 3.790390522001662e-05,
"loss": 0.8765,
"step": 124
},
{
"epoch": 0.21496130696474636,
"grad_norm": 0.07615929841995239,
"learning_rate": 3.705904774487396e-05,
"loss": 0.6885,
"step": 125
},
{
"epoch": 0.21668099742046432,
"grad_norm": 0.07800007611513138,
"learning_rate": 3.6218132209150045e-05,
"loss": 0.7583,
"step": 126
},
{
"epoch": 0.21840068787618228,
"grad_norm": 0.0879930779337883,
"learning_rate": 3.5381414763863166e-05,
"loss": 0.7962,
"step": 127
},
{
"epoch": 0.22012037833190026,
"grad_norm": 0.08408991992473602,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.7565,
"step": 128
},
{
"epoch": 0.22184006878761822,
"grad_norm": 0.08975850045681,
"learning_rate": 3.372159227714218e-05,
"loss": 0.8412,
"step": 129
},
{
"epoch": 0.2235597592433362,
"grad_norm": 0.08965165913105011,
"learning_rate": 3.289899283371657e-05,
"loss": 0.8464,
"step": 130
},
{
"epoch": 0.22527944969905417,
"grad_norm": 0.09056264162063599,
"learning_rate": 3.2081602522734986e-05,
"loss": 0.663,
"step": 131
},
{
"epoch": 0.22699914015477213,
"grad_norm": 0.0920715406537056,
"learning_rate": 3.12696703292044e-05,
"loss": 0.8896,
"step": 132
},
{
"epoch": 0.22871883061049011,
"grad_norm": 0.10946381837129593,
"learning_rate": 3.046344357553632e-05,
"loss": 0.7847,
"step": 133
},
{
"epoch": 0.23043852106620807,
"grad_norm": 0.10407907515764236,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.8615,
"step": 134
},
{
"epoch": 0.23215821152192606,
"grad_norm": 0.09890785813331604,
"learning_rate": 2.886908691296504e-05,
"loss": 0.8844,
"step": 135
},
{
"epoch": 0.23387790197764402,
"grad_norm": 0.12885335087776184,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.7755,
"step": 136
},
{
"epoch": 0.235597592433362,
"grad_norm": 0.10378793627023697,
"learning_rate": 2.7300475013022663e-05,
"loss": 0.7874,
"step": 137
},
{
"epoch": 0.23731728288907997,
"grad_norm": 0.12850679457187653,
"learning_rate": 2.6526421860705473e-05,
"loss": 0.7773,
"step": 138
},
{
"epoch": 0.23903697334479793,
"grad_norm": 0.1387593150138855,
"learning_rate": 2.575951898768315e-05,
"loss": 0.8046,
"step": 139
},
{
"epoch": 0.2407566638005159,
"grad_norm": 0.14513392746448517,
"learning_rate": 2.500000000000001e-05,
"loss": 0.9875,
"step": 140
},
{
"epoch": 0.24247635425623387,
"grad_norm": 0.14788322150707245,
"learning_rate": 2.4248096254497288e-05,
"loss": 0.9912,
"step": 141
},
{
"epoch": 0.24419604471195186,
"grad_norm": 0.16071070730686188,
"learning_rate": 2.350403678833976e-05,
"loss": 1.2427,
"step": 142
},
{
"epoch": 0.24591573516766982,
"grad_norm": 0.18315501511096954,
"learning_rate": 2.2768048249248648e-05,
"loss": 1.3647,
"step": 143
},
{
"epoch": 0.24763542562338778,
"grad_norm": 0.2040652483701706,
"learning_rate": 2.2040354826462668e-05,
"loss": 1.3373,
"step": 144
},
{
"epoch": 0.24935511607910577,
"grad_norm": 0.20529639720916748,
"learning_rate": 2.132117818244771e-05,
"loss": 1.421,
"step": 145
},
{
"epoch": 0.2510748065348237,
"grad_norm": 0.18773475289344788,
"learning_rate": 2.061073738537635e-05,
"loss": 1.3484,
"step": 146
},
{
"epoch": 0.2527944969905417,
"grad_norm": 0.20955699682235718,
"learning_rate": 1.9909248842397584e-05,
"loss": 1.3517,
"step": 147
},
{
"epoch": 0.2545141874462597,
"grad_norm": 0.22871288657188416,
"learning_rate": 1.9216926233717085e-05,
"loss": 1.4738,
"step": 148
},
{
"epoch": 0.25623387790197766,
"grad_norm": 0.27887439727783203,
"learning_rate": 1.8533980447508137e-05,
"loss": 1.8532,
"step": 149
},
{
"epoch": 0.2579535683576956,
"grad_norm": 0.40441471338272095,
"learning_rate": 1.7860619515673033e-05,
"loss": 2.2748,
"step": 150
},
{
"epoch": 0.2579535683576956,
"eval_loss": 0.9018179774284363,
"eval_runtime": 26.0633,
"eval_samples_per_second": 37.601,
"eval_steps_per_second": 18.8,
"step": 150
}
],
"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": false
},
"attributes": {}
}
},
"total_flos": 1.066393548619776e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}