prxy5605's picture
Training in progress, step 200, checkpoint
0b0a764 verified
raw
history blame
36.8 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.08982708286548394,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00044913541432741973,
"grad_norm": 1.838648495322559e-05,
"learning_rate": 5e-06,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.00044913541432741973,
"eval_loss": 11.5,
"eval_runtime": 24.2446,
"eval_samples_per_second": 154.674,
"eval_steps_per_second": 77.337,
"step": 1
},
{
"epoch": 0.0008982708286548395,
"grad_norm": 1.2990568393433932e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.001347406242982259,
"grad_norm": 1.8343982446822338e-05,
"learning_rate": 1.5e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.001796541657309679,
"grad_norm": 1.3080456483294256e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.0022456770716370988,
"grad_norm": 1.5889010683167726e-05,
"learning_rate": 2.5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.002694812485964518,
"grad_norm": 2.7616410079644993e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.003143947900291938,
"grad_norm": 2.0526989828795195e-05,
"learning_rate": 3.5e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.003593083314619358,
"grad_norm": 1.759777842380572e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.004042218728946777,
"grad_norm": 1.6452084310003556e-05,
"learning_rate": 4.5e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.0044913541432741975,
"grad_norm": 1.6463358406326734e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.004940489557601617,
"grad_norm": 1.8078573702950962e-05,
"learning_rate": 5.500000000000001e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.005389624971929036,
"grad_norm": 1.6838948795339093e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.005838760386256457,
"grad_norm": 1.541178244224284e-05,
"learning_rate": 6.500000000000001e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.006287895800583876,
"grad_norm": 1.2977827282156795e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.0067370312149112955,
"grad_norm": 1.57095528265927e-05,
"learning_rate": 7.500000000000001e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.007186166629238716,
"grad_norm": 1.694589991529938e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.007635302043566135,
"grad_norm": 1.0791429303935729e-05,
"learning_rate": 8.5e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.008084437457893555,
"grad_norm": 1.7452706742915325e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.008533572872220974,
"grad_norm": 2.773817686829716e-05,
"learning_rate": 9.5e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.008982708286548395,
"grad_norm": 2.2375161279342137e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.009431843700875815,
"grad_norm": 1.9166653146385215e-05,
"learning_rate": 9.999238475781957e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.009880979115203234,
"grad_norm": 1.3334756658878177e-05,
"learning_rate": 9.99695413509548e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.010330114529530653,
"grad_norm": 2.297369428561069e-05,
"learning_rate": 9.99314767377287e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.010779249943858073,
"grad_norm": 1.520256046205759e-05,
"learning_rate": 9.987820251299122e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.011228385358185492,
"grad_norm": 1.1953277862630785e-05,
"learning_rate": 9.980973490458728e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.011677520772512913,
"grad_norm": 1.437636910850415e-05,
"learning_rate": 9.972609476841367e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.012126656186840333,
"grad_norm": 1.8797289158101194e-05,
"learning_rate": 9.962730758206611e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.012575791601167752,
"grad_norm": 1.934461761265993e-05,
"learning_rate": 9.951340343707852e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.013024927015495171,
"grad_norm": 1.2589272046170663e-05,
"learning_rate": 9.938441702975689e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.013474062429822591,
"grad_norm": 2.8147243938292377e-05,
"learning_rate": 9.924038765061042e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.013923197844150012,
"grad_norm": 1.534887451271061e-05,
"learning_rate": 9.908135917238321e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.014372333258477431,
"grad_norm": 2.1180412659305148e-05,
"learning_rate": 9.890738003669029e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.01482146867280485,
"grad_norm": 1.593550950929057e-05,
"learning_rate": 9.871850323926177e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.01527060408713227,
"grad_norm": 3.8066697015892714e-05,
"learning_rate": 9.851478631379982e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.01571973950145969,
"grad_norm": 1.754353979777079e-05,
"learning_rate": 9.829629131445342e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.01616887491578711,
"grad_norm": 1.624736250960268e-05,
"learning_rate": 9.806308479691595e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.01661801033011453,
"grad_norm": 1.8036285837297328e-05,
"learning_rate": 9.781523779815179e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.017067145744441948,
"grad_norm": 1.700466418697033e-05,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.017516281158769367,
"grad_norm": 3.25874425470829e-05,
"learning_rate": 9.727592877996585e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.01796541657309679,
"grad_norm": 1.892649925139267e-05,
"learning_rate": 9.698463103929542e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.01841455198742421,
"grad_norm": 1.3684399164048955e-05,
"learning_rate": 9.667902132486009e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.01886368740175163,
"grad_norm": 2.2879992684465833e-05,
"learning_rate": 9.635919272833938e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.01931282281607905,
"grad_norm": 2.1507212295546196e-05,
"learning_rate": 9.602524267262203e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.019761958230406468,
"grad_norm": 2.5594701583031565e-05,
"learning_rate": 9.567727288213005e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.020211093644733887,
"grad_norm": 3.893139728461392e-05,
"learning_rate": 9.53153893518325e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.020660229059061307,
"grad_norm": 2.4852359274518676e-05,
"learning_rate": 9.493970231495835e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.021109364473388726,
"grad_norm": 5.0232982175657526e-05,
"learning_rate": 9.45503262094184e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.021558499887716145,
"grad_norm": 2.7157999284099787e-05,
"learning_rate": 9.414737964294636e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.022007635302043565,
"grad_norm": 3.0149305530358106e-05,
"learning_rate": 9.373098535696979e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.022456770716370984,
"grad_norm": 4.1423827497055754e-05,
"learning_rate": 9.330127018922194e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.022456770716370984,
"eval_loss": 11.5,
"eval_runtime": 24.2683,
"eval_samples_per_second": 154.523,
"eval_steps_per_second": 77.261,
"step": 50
},
{
"epoch": 0.022905906130698407,
"grad_norm": 1.5592015188303776e-05,
"learning_rate": 9.285836503510562e-05,
"loss": 46.0,
"step": 51
},
{
"epoch": 0.023355041545025827,
"grad_norm": 1.280045307794353e-05,
"learning_rate": 9.24024048078213e-05,
"loss": 46.0,
"step": 52
},
{
"epoch": 0.023804176959353246,
"grad_norm": 2.069097536150366e-05,
"learning_rate": 9.193352839727121e-05,
"loss": 46.0,
"step": 53
},
{
"epoch": 0.024253312373680665,
"grad_norm": 2.5162336896755733e-05,
"learning_rate": 9.145187862775209e-05,
"loss": 46.0,
"step": 54
},
{
"epoch": 0.024702447788008085,
"grad_norm": 3.217296762159094e-05,
"learning_rate": 9.09576022144496e-05,
"loss": 46.0,
"step": 55
},
{
"epoch": 0.025151583202335504,
"grad_norm": 3.4474760468583554e-05,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 56
},
{
"epoch": 0.025600718616662924,
"grad_norm": 3.134864164167084e-05,
"learning_rate": 8.993177550236464e-05,
"loss": 46.0,
"step": 57
},
{
"epoch": 0.026049854030990343,
"grad_norm": 2.7241056159255095e-05,
"learning_rate": 8.940053768033609e-05,
"loss": 46.0,
"step": 58
},
{
"epoch": 0.026498989445317762,
"grad_norm": 3.1343828595709056e-05,
"learning_rate": 8.885729807284856e-05,
"loss": 46.0,
"step": 59
},
{
"epoch": 0.026948124859645182,
"grad_norm": 2.3026888811727986e-05,
"learning_rate": 8.83022221559489e-05,
"loss": 46.0,
"step": 60
},
{
"epoch": 0.0273972602739726,
"grad_norm": 4.045252353535034e-05,
"learning_rate": 8.773547901113862e-05,
"loss": 46.0,
"step": 61
},
{
"epoch": 0.027846395688300024,
"grad_norm": 5.758315455750562e-05,
"learning_rate": 8.715724127386972e-05,
"loss": 46.0,
"step": 62
},
{
"epoch": 0.028295531102627444,
"grad_norm": 2.3458678697352298e-05,
"learning_rate": 8.656768508095853e-05,
"loss": 46.0,
"step": 63
},
{
"epoch": 0.028744666516954863,
"grad_norm": 2.0376308384584263e-05,
"learning_rate": 8.596699001693255e-05,
"loss": 46.0,
"step": 64
},
{
"epoch": 0.029193801931282282,
"grad_norm": 3.670160367619246e-05,
"learning_rate": 8.535533905932738e-05,
"loss": 46.0,
"step": 65
},
{
"epoch": 0.0296429373456097,
"grad_norm": 3.101183392573148e-05,
"learning_rate": 8.473291852294987e-05,
"loss": 46.0,
"step": 66
},
{
"epoch": 0.03009207275993712,
"grad_norm": 3.032161112059839e-05,
"learning_rate": 8.409991800312493e-05,
"loss": 46.0,
"step": 67
},
{
"epoch": 0.03054120817426454,
"grad_norm": 3.268122236477211e-05,
"learning_rate": 8.345653031794292e-05,
"loss": 46.0,
"step": 68
},
{
"epoch": 0.03099034358859196,
"grad_norm": 3.1394203688250855e-05,
"learning_rate": 8.280295144952536e-05,
"loss": 46.0,
"step": 69
},
{
"epoch": 0.03143947900291938,
"grad_norm": 3.980135443271138e-05,
"learning_rate": 8.213938048432697e-05,
"loss": 46.0,
"step": 70
},
{
"epoch": 0.0318886144172468,
"grad_norm": 3.355582521180622e-05,
"learning_rate": 8.146601955249188e-05,
"loss": 46.0,
"step": 71
},
{
"epoch": 0.03233774983157422,
"grad_norm": 4.067844929522835e-05,
"learning_rate": 8.07830737662829e-05,
"loss": 46.0,
"step": 72
},
{
"epoch": 0.03278688524590164,
"grad_norm": 5.312855864758603e-05,
"learning_rate": 8.009075115760243e-05,
"loss": 46.0,
"step": 73
},
{
"epoch": 0.03323602066022906,
"grad_norm": 2.6573492505121976e-05,
"learning_rate": 7.938926261462366e-05,
"loss": 46.0,
"step": 74
},
{
"epoch": 0.03368515607455648,
"grad_norm": 6.407412729458883e-05,
"learning_rate": 7.86788218175523e-05,
"loss": 46.0,
"step": 75
},
{
"epoch": 0.034134291488883896,
"grad_norm": 4.746004560729489e-05,
"learning_rate": 7.795964517353735e-05,
"loss": 46.0,
"step": 76
},
{
"epoch": 0.03458342690321132,
"grad_norm": 3.733126141014509e-05,
"learning_rate": 7.723195175075136e-05,
"loss": 46.0,
"step": 77
},
{
"epoch": 0.035032562317538735,
"grad_norm": 8.151544898282737e-05,
"learning_rate": 7.649596321166024e-05,
"loss": 46.0,
"step": 78
},
{
"epoch": 0.03548169773186616,
"grad_norm": 2.8419528462109156e-05,
"learning_rate": 7.575190374550272e-05,
"loss": 46.0,
"step": 79
},
{
"epoch": 0.03593083314619358,
"grad_norm": 3.4233249607495964e-05,
"learning_rate": 7.500000000000001e-05,
"loss": 46.0,
"step": 80
},
{
"epoch": 0.036379968560520996,
"grad_norm": 5.3122937970329076e-05,
"learning_rate": 7.424048101231686e-05,
"loss": 46.0,
"step": 81
},
{
"epoch": 0.03682910397484842,
"grad_norm": 5.805513501400128e-05,
"learning_rate": 7.347357813929454e-05,
"loss": 46.0,
"step": 82
},
{
"epoch": 0.037278239389175835,
"grad_norm": 2.634433076309506e-05,
"learning_rate": 7.269952498697734e-05,
"loss": 46.0,
"step": 83
},
{
"epoch": 0.03772737480350326,
"grad_norm": 5.438110383693129e-05,
"learning_rate": 7.191855733945387e-05,
"loss": 46.0,
"step": 84
},
{
"epoch": 0.038176510217830674,
"grad_norm": 5.9794343542307615e-05,
"learning_rate": 7.113091308703498e-05,
"loss": 46.0,
"step": 85
},
{
"epoch": 0.0386256456321581,
"grad_norm": 8.437032374786213e-05,
"learning_rate": 7.033683215379002e-05,
"loss": 46.0,
"step": 86
},
{
"epoch": 0.03907478104648551,
"grad_norm": 9.161300113191828e-05,
"learning_rate": 6.953655642446368e-05,
"loss": 46.0,
"step": 87
},
{
"epoch": 0.039523916460812936,
"grad_norm": 9.054856491275132e-05,
"learning_rate": 6.873032967079561e-05,
"loss": 46.0,
"step": 88
},
{
"epoch": 0.03997305187514035,
"grad_norm": 7.056965841911733e-05,
"learning_rate": 6.7918397477265e-05,
"loss": 46.0,
"step": 89
},
{
"epoch": 0.040422187289467774,
"grad_norm": 5.0735634431475773e-05,
"learning_rate": 6.710100716628344e-05,
"loss": 46.0,
"step": 90
},
{
"epoch": 0.0408713227037952,
"grad_norm": 4.1233262891182676e-05,
"learning_rate": 6.627840772285784e-05,
"loss": 46.0,
"step": 91
},
{
"epoch": 0.04132045811812261,
"grad_norm": 7.487056427635252e-05,
"learning_rate": 6.545084971874738e-05,
"loss": 46.0,
"step": 92
},
{
"epoch": 0.041769593532450036,
"grad_norm": 5.445545684779063e-05,
"learning_rate": 6.461858523613684e-05,
"loss": 46.0,
"step": 93
},
{
"epoch": 0.04221872894677745,
"grad_norm": 7.229465700220317e-05,
"learning_rate": 6.378186779084995e-05,
"loss": 46.0,
"step": 94
},
{
"epoch": 0.042667864361104875,
"grad_norm": 6.044282781658694e-05,
"learning_rate": 6.294095225512603e-05,
"loss": 46.0,
"step": 95
},
{
"epoch": 0.04311699977543229,
"grad_norm": 7.44121425668709e-05,
"learning_rate": 6.209609477998338e-05,
"loss": 46.0,
"step": 96
},
{
"epoch": 0.043566135189759714,
"grad_norm": 6.77663556416519e-05,
"learning_rate": 6.124755271719325e-05,
"loss": 46.0,
"step": 97
},
{
"epoch": 0.04401527060408713,
"grad_norm": 4.348663060227409e-05,
"learning_rate": 6.0395584540887963e-05,
"loss": 46.0,
"step": 98
},
{
"epoch": 0.04446440601841455,
"grad_norm": 9.123215568251908e-05,
"learning_rate": 5.9540449768827246e-05,
"loss": 46.0,
"step": 99
},
{
"epoch": 0.04491354143274197,
"grad_norm": 5.847312422702089e-05,
"learning_rate": 5.868240888334653e-05,
"loss": 46.0,
"step": 100
},
{
"epoch": 0.04491354143274197,
"eval_loss": 11.5,
"eval_runtime": 24.4817,
"eval_samples_per_second": 153.176,
"eval_steps_per_second": 76.588,
"step": 100
},
{
"epoch": 0.04536267684706939,
"grad_norm": 6.564732029801235e-05,
"learning_rate": 5.782172325201155e-05,
"loss": 46.0,
"step": 101
},
{
"epoch": 0.045811812261396814,
"grad_norm": 9.073306864593178e-05,
"learning_rate": 5.695865504800327e-05,
"loss": 46.0,
"step": 102
},
{
"epoch": 0.04626094767572423,
"grad_norm": 5.6581779062980786e-05,
"learning_rate": 5.6093467170257374e-05,
"loss": 46.0,
"step": 103
},
{
"epoch": 0.04671008309005165,
"grad_norm": 4.856206942349672e-05,
"learning_rate": 5.522642316338268e-05,
"loss": 46.0,
"step": 104
},
{
"epoch": 0.04715921850437907,
"grad_norm": 0.00014515251677948982,
"learning_rate": 5.435778713738292e-05,
"loss": 46.0,
"step": 105
},
{
"epoch": 0.04760835391870649,
"grad_norm": 4.484998862608336e-05,
"learning_rate": 5.348782368720626e-05,
"loss": 46.0,
"step": 106
},
{
"epoch": 0.04805748933303391,
"grad_norm": 5.431281897472218e-05,
"learning_rate": 5.26167978121472e-05,
"loss": 46.0,
"step": 107
},
{
"epoch": 0.04850662474736133,
"grad_norm": 5.2316147048259154e-05,
"learning_rate": 5.174497483512506e-05,
"loss": 46.0,
"step": 108
},
{
"epoch": 0.04895576016168875,
"grad_norm": 0.00020991968631278723,
"learning_rate": 5.0872620321864185e-05,
"loss": 46.0,
"step": 109
},
{
"epoch": 0.04940489557601617,
"grad_norm": 0.0001119155203923583,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 110
},
{
"epoch": 0.049854030990343585,
"grad_norm": 3.5669108910951763e-05,
"learning_rate": 4.912737967813583e-05,
"loss": 46.0,
"step": 111
},
{
"epoch": 0.05030316640467101,
"grad_norm": 8.696071745362133e-05,
"learning_rate": 4.825502516487497e-05,
"loss": 46.0,
"step": 112
},
{
"epoch": 0.05075230181899843,
"grad_norm": 4.1281185986008495e-05,
"learning_rate": 4.738320218785281e-05,
"loss": 46.0,
"step": 113
},
{
"epoch": 0.05120143723332585,
"grad_norm": 7.59501926950179e-05,
"learning_rate": 4.6512176312793736e-05,
"loss": 46.0,
"step": 114
},
{
"epoch": 0.05165057264765327,
"grad_norm": 4.041286592837423e-05,
"learning_rate": 4.564221286261709e-05,
"loss": 46.0,
"step": 115
},
{
"epoch": 0.052099708061980686,
"grad_norm": 0.00012405925372149795,
"learning_rate": 4.477357683661734e-05,
"loss": 46.0,
"step": 116
},
{
"epoch": 0.05254884347630811,
"grad_norm": 4.541510497801937e-05,
"learning_rate": 4.390653282974264e-05,
"loss": 46.0,
"step": 117
},
{
"epoch": 0.052997978890635525,
"grad_norm": 3.6235865991329774e-05,
"learning_rate": 4.3041344951996746e-05,
"loss": 46.0,
"step": 118
},
{
"epoch": 0.05344711430496295,
"grad_norm": 0.0001397922169417143,
"learning_rate": 4.2178276747988446e-05,
"loss": 46.0,
"step": 119
},
{
"epoch": 0.053896249719290364,
"grad_norm": 4.858409010921605e-05,
"learning_rate": 4.131759111665349e-05,
"loss": 46.0,
"step": 120
},
{
"epoch": 0.054345385133617786,
"grad_norm": 6.559174653375521e-05,
"learning_rate": 4.045955023117276e-05,
"loss": 46.0,
"step": 121
},
{
"epoch": 0.0547945205479452,
"grad_norm": 9.03177133295685e-05,
"learning_rate": 3.960441545911204e-05,
"loss": 46.0,
"step": 122
},
{
"epoch": 0.055243655962272625,
"grad_norm": 7.547564746346325e-05,
"learning_rate": 3.875244728280676e-05,
"loss": 46.0,
"step": 123
},
{
"epoch": 0.05569279137660005,
"grad_norm": 8.072968194028363e-05,
"learning_rate": 3.790390522001662e-05,
"loss": 46.0,
"step": 124
},
{
"epoch": 0.056141926790927464,
"grad_norm": 0.00010309958452126011,
"learning_rate": 3.705904774487396e-05,
"loss": 46.0,
"step": 125
},
{
"epoch": 0.05659106220525489,
"grad_norm": 8.730621630093083e-05,
"learning_rate": 3.6218132209150045e-05,
"loss": 46.0,
"step": 126
},
{
"epoch": 0.0570401976195823,
"grad_norm": 7.893842848716304e-05,
"learning_rate": 3.5381414763863166e-05,
"loss": 46.0,
"step": 127
},
{
"epoch": 0.057489333033909726,
"grad_norm": 7.924601959530264e-05,
"learning_rate": 3.4549150281252636e-05,
"loss": 46.0,
"step": 128
},
{
"epoch": 0.05793846844823714,
"grad_norm": 9.8539145255927e-05,
"learning_rate": 3.372159227714218e-05,
"loss": 46.0,
"step": 129
},
{
"epoch": 0.058387603862564565,
"grad_norm": 0.00011634702241281047,
"learning_rate": 3.289899283371657e-05,
"loss": 46.0,
"step": 130
},
{
"epoch": 0.05883673927689198,
"grad_norm": 9.868943743640557e-05,
"learning_rate": 3.2081602522734986e-05,
"loss": 46.0,
"step": 131
},
{
"epoch": 0.0592858746912194,
"grad_norm": 0.0001640073605813086,
"learning_rate": 3.12696703292044e-05,
"loss": 46.0,
"step": 132
},
{
"epoch": 0.05973501010554682,
"grad_norm": 0.00012898287968710065,
"learning_rate": 3.046344357553632e-05,
"loss": 46.0,
"step": 133
},
{
"epoch": 0.06018414551987424,
"grad_norm": 8.394714677706361e-05,
"learning_rate": 2.9663167846209998e-05,
"loss": 46.0,
"step": 134
},
{
"epoch": 0.060633280934201665,
"grad_norm": 0.00014036337961442769,
"learning_rate": 2.886908691296504e-05,
"loss": 46.0,
"step": 135
},
{
"epoch": 0.06108241634852908,
"grad_norm": 8.231115498347208e-05,
"learning_rate": 2.8081442660546125e-05,
"loss": 46.0,
"step": 136
},
{
"epoch": 0.061531551762856504,
"grad_norm": 0.00014053141057956964,
"learning_rate": 2.7300475013022663e-05,
"loss": 46.0,
"step": 137
},
{
"epoch": 0.06198068717718392,
"grad_norm": 9.784067515283823e-05,
"learning_rate": 2.6526421860705473e-05,
"loss": 46.0,
"step": 138
},
{
"epoch": 0.06242982259151134,
"grad_norm": 9.869643690763041e-05,
"learning_rate": 2.575951898768315e-05,
"loss": 46.0,
"step": 139
},
{
"epoch": 0.06287895800583876,
"grad_norm": 7.148009171942249e-05,
"learning_rate": 2.500000000000001e-05,
"loss": 46.0,
"step": 140
},
{
"epoch": 0.06332809342016618,
"grad_norm": 0.00010294223466189578,
"learning_rate": 2.4248096254497288e-05,
"loss": 46.0,
"step": 141
},
{
"epoch": 0.0637772288344936,
"grad_norm": 9.365833102492616e-05,
"learning_rate": 2.350403678833976e-05,
"loss": 46.0,
"step": 142
},
{
"epoch": 0.06422636424882101,
"grad_norm": 6.49421926937066e-05,
"learning_rate": 2.2768048249248648e-05,
"loss": 46.0,
"step": 143
},
{
"epoch": 0.06467549966314844,
"grad_norm": 0.0001447576651116833,
"learning_rate": 2.2040354826462668e-05,
"loss": 46.0,
"step": 144
},
{
"epoch": 0.06512463507747586,
"grad_norm": 8.269389218185097e-05,
"learning_rate": 2.132117818244771e-05,
"loss": 46.0,
"step": 145
},
{
"epoch": 0.06557377049180328,
"grad_norm": 8.899991371436045e-05,
"learning_rate": 2.061073738537635e-05,
"loss": 46.0,
"step": 146
},
{
"epoch": 0.0660229059061307,
"grad_norm": 6.125797517597675e-05,
"learning_rate": 1.9909248842397584e-05,
"loss": 46.0,
"step": 147
},
{
"epoch": 0.06647204132045811,
"grad_norm": 0.00010218821262242272,
"learning_rate": 1.9216926233717085e-05,
"loss": 46.0,
"step": 148
},
{
"epoch": 0.06692117673478554,
"grad_norm": 5.742968642152846e-05,
"learning_rate": 1.8533980447508137e-05,
"loss": 46.0,
"step": 149
},
{
"epoch": 0.06737031214911296,
"grad_norm": 0.0001050592545652762,
"learning_rate": 1.7860619515673033e-05,
"loss": 46.0,
"step": 150
},
{
"epoch": 0.06737031214911296,
"eval_loss": 11.5,
"eval_runtime": 24.4902,
"eval_samples_per_second": 153.122,
"eval_steps_per_second": 76.561,
"step": 150
},
{
"epoch": 0.06781944756344038,
"grad_norm": 0.0001438720792066306,
"learning_rate": 1.7197048550474643e-05,
"loss": 46.0,
"step": 151
},
{
"epoch": 0.06826858297776779,
"grad_norm": 7.472206925740466e-05,
"learning_rate": 1.6543469682057106e-05,
"loss": 46.0,
"step": 152
},
{
"epoch": 0.06871771839209521,
"grad_norm": 9.493398829363286e-05,
"learning_rate": 1.5900081996875083e-05,
"loss": 46.0,
"step": 153
},
{
"epoch": 0.06916685380642264,
"grad_norm": 5.300561315380037e-05,
"learning_rate": 1.526708147705013e-05,
"loss": 46.0,
"step": 154
},
{
"epoch": 0.06961598922075006,
"grad_norm": 6.254475738387555e-05,
"learning_rate": 1.4644660940672627e-05,
"loss": 46.0,
"step": 155
},
{
"epoch": 0.07006512463507747,
"grad_norm": 0.0001307373313466087,
"learning_rate": 1.4033009983067452e-05,
"loss": 46.0,
"step": 156
},
{
"epoch": 0.07051426004940489,
"grad_norm": 9.006000618683174e-05,
"learning_rate": 1.3432314919041478e-05,
"loss": 46.0,
"step": 157
},
{
"epoch": 0.07096339546373231,
"grad_norm": 8.949954644776881e-05,
"learning_rate": 1.2842758726130283e-05,
"loss": 46.0,
"step": 158
},
{
"epoch": 0.07141253087805974,
"grad_norm": 0.00011812666343757883,
"learning_rate": 1.22645209888614e-05,
"loss": 46.0,
"step": 159
},
{
"epoch": 0.07186166629238716,
"grad_norm": 0.00010641237895470113,
"learning_rate": 1.1697777844051105e-05,
"loss": 46.0,
"step": 160
},
{
"epoch": 0.07231080170671457,
"grad_norm": 5.68857321923133e-05,
"learning_rate": 1.1142701927151456e-05,
"loss": 46.0,
"step": 161
},
{
"epoch": 0.07275993712104199,
"grad_norm": 7.178529631346464e-05,
"learning_rate": 1.0599462319663905e-05,
"loss": 46.0,
"step": 162
},
{
"epoch": 0.07320907253536942,
"grad_norm": 6.591699639102444e-05,
"learning_rate": 1.006822449763537e-05,
"loss": 46.0,
"step": 163
},
{
"epoch": 0.07365820794969684,
"grad_norm": 7.649638428119943e-05,
"learning_rate": 9.549150281252633e-06,
"loss": 46.0,
"step": 164
},
{
"epoch": 0.07410734336402425,
"grad_norm": 0.0001560054370202124,
"learning_rate": 9.042397785550405e-06,
"loss": 46.0,
"step": 165
},
{
"epoch": 0.07455647877835167,
"grad_norm": 8.290179539471865e-05,
"learning_rate": 8.548121372247918e-06,
"loss": 46.0,
"step": 166
},
{
"epoch": 0.0750056141926791,
"grad_norm": 0.00012351403711363673,
"learning_rate": 8.066471602728803e-06,
"loss": 46.0,
"step": 167
},
{
"epoch": 0.07545474960700652,
"grad_norm": 7.974076288519427e-05,
"learning_rate": 7.597595192178702e-06,
"loss": 46.0,
"step": 168
},
{
"epoch": 0.07590388502133394,
"grad_norm": 5.896786387893371e-05,
"learning_rate": 7.1416349648943894e-06,
"loss": 46.0,
"step": 169
},
{
"epoch": 0.07635302043566135,
"grad_norm": 0.00010927852417808026,
"learning_rate": 6.698729810778065e-06,
"loss": 46.0,
"step": 170
},
{
"epoch": 0.07680215584998877,
"grad_norm": 7.081931835273281e-05,
"learning_rate": 6.269014643030213e-06,
"loss": 46.0,
"step": 171
},
{
"epoch": 0.0772512912643162,
"grad_norm": 0.00013235144433565438,
"learning_rate": 5.852620357053651e-06,
"loss": 46.0,
"step": 172
},
{
"epoch": 0.07770042667864362,
"grad_norm": 7.40899340598844e-05,
"learning_rate": 5.449673790581611e-06,
"loss": 46.0,
"step": 173
},
{
"epoch": 0.07814956209297103,
"grad_norm": 7.721033762209117e-05,
"learning_rate": 5.060297685041659e-06,
"loss": 46.0,
"step": 174
},
{
"epoch": 0.07859869750729845,
"grad_norm": 0.00010103748354595155,
"learning_rate": 4.684610648167503e-06,
"loss": 46.0,
"step": 175
},
{
"epoch": 0.07904783292162587,
"grad_norm": 5.865566708962433e-05,
"learning_rate": 4.322727117869951e-06,
"loss": 46.0,
"step": 176
},
{
"epoch": 0.0794969683359533,
"grad_norm": 0.0001235765084857121,
"learning_rate": 3.974757327377981e-06,
"loss": 46.0,
"step": 177
},
{
"epoch": 0.0799461037502807,
"grad_norm": 9.430928184883669e-05,
"learning_rate": 3.6408072716606346e-06,
"loss": 46.0,
"step": 178
},
{
"epoch": 0.08039523916460813,
"grad_norm": 8.264468488050625e-05,
"learning_rate": 3.3209786751399187e-06,
"loss": 46.0,
"step": 179
},
{
"epoch": 0.08084437457893555,
"grad_norm": 5.9367048379499465e-05,
"learning_rate": 3.0153689607045845e-06,
"loss": 46.0,
"step": 180
},
{
"epoch": 0.08129350999326297,
"grad_norm": 0.00012005270400550216,
"learning_rate": 2.724071220034158e-06,
"loss": 46.0,
"step": 181
},
{
"epoch": 0.0817426454075904,
"grad_norm": 6.05574095970951e-05,
"learning_rate": 2.4471741852423237e-06,
"loss": 46.0,
"step": 182
},
{
"epoch": 0.0821917808219178,
"grad_norm": 0.00014828034909442067,
"learning_rate": 2.1847622018482283e-06,
"loss": 46.0,
"step": 183
},
{
"epoch": 0.08264091623624523,
"grad_norm": 0.0001592932385392487,
"learning_rate": 1.9369152030840556e-06,
"loss": 46.0,
"step": 184
},
{
"epoch": 0.08309005165057265,
"grad_norm": 0.0001511089358245954,
"learning_rate": 1.70370868554659e-06,
"loss": 46.0,
"step": 185
},
{
"epoch": 0.08353918706490007,
"grad_norm": 0.00013895431766286492,
"learning_rate": 1.4852136862001764e-06,
"loss": 46.0,
"step": 186
},
{
"epoch": 0.08398832247922748,
"grad_norm": 5.225280256127007e-05,
"learning_rate": 1.2814967607382432e-06,
"loss": 46.0,
"step": 187
},
{
"epoch": 0.0844374578935549,
"grad_norm": 0.0001045409808284603,
"learning_rate": 1.0926199633097157e-06,
"loss": 46.0,
"step": 188
},
{
"epoch": 0.08488659330788233,
"grad_norm": 0.00014955301594454795,
"learning_rate": 9.186408276168013e-07,
"loss": 46.0,
"step": 189
},
{
"epoch": 0.08533572872220975,
"grad_norm": 0.00010593217302812263,
"learning_rate": 7.596123493895991e-07,
"loss": 46.0,
"step": 190
},
{
"epoch": 0.08578486413653717,
"grad_norm": 7.444553921232e-05,
"learning_rate": 6.15582970243117e-07,
"loss": 46.0,
"step": 191
},
{
"epoch": 0.08623399955086458,
"grad_norm": 4.052293297718279e-05,
"learning_rate": 4.865965629214819e-07,
"loss": 46.0,
"step": 192
},
{
"epoch": 0.086683134965192,
"grad_norm": 0.00012066525232512504,
"learning_rate": 3.7269241793390085e-07,
"loss": 46.0,
"step": 193
},
{
"epoch": 0.08713227037951943,
"grad_norm": 8.483009150950238e-05,
"learning_rate": 2.7390523158633554e-07,
"loss": 46.0,
"step": 194
},
{
"epoch": 0.08758140579384685,
"grad_norm": 9.945972851710394e-05,
"learning_rate": 1.9026509541272275e-07,
"loss": 46.0,
"step": 195
},
{
"epoch": 0.08803054120817426,
"grad_norm": 9.102479816647246e-05,
"learning_rate": 1.2179748700879012e-07,
"loss": 46.0,
"step": 196
},
{
"epoch": 0.08847967662250168,
"grad_norm": 0.0001648725738050416,
"learning_rate": 6.852326227130834e-08,
"loss": 46.0,
"step": 197
},
{
"epoch": 0.0889288120368291,
"grad_norm": 0.00018249057757202536,
"learning_rate": 3.04586490452119e-08,
"loss": 46.0,
"step": 198
},
{
"epoch": 0.08937794745115653,
"grad_norm": 8.922704728320241e-05,
"learning_rate": 7.615242180436522e-09,
"loss": 46.0,
"step": 199
},
{
"epoch": 0.08982708286548394,
"grad_norm": 0.0001207529567182064,
"learning_rate": 0.0,
"loss": 46.0,
"step": 200
},
{
"epoch": 0.08982708286548394,
"eval_loss": 11.5,
"eval_runtime": 24.3109,
"eval_samples_per_second": 154.252,
"eval_steps_per_second": 77.126,
"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": 3
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 32399651241984.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}