| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998570816064027, | |
| "eval_steps": 80, | |
| "global_step": 1166, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004287551807917679, | |
| "grad_norm": 49.0459476401418, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 1.2482, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008575103615835357, | |
| "grad_norm": 46.49636895863856, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.2111, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012862655423753037, | |
| "grad_norm": 75.02893655779658, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.2375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017150207231670715, | |
| "grad_norm": 3.8741623300934016, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.0833, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021437759039588396, | |
| "grad_norm": 8.80211103072482, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.0052, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025725310847506073, | |
| "grad_norm": 11.672065444786128, | |
| "learning_rate": 3e-06, | |
| "loss": 1.0283, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030012862655423755, | |
| "grad_norm": 4.987083560214949, | |
| "learning_rate": 3.5e-06, | |
| "loss": 1.0801, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03430041446334143, | |
| "grad_norm": 2.966299005953653, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0753, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.038587966271259114, | |
| "grad_norm": 3.0065164197825074, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.9409, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04287551807917679, | |
| "grad_norm": 3.381394216826962, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0198, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04716306988709447, | |
| "grad_norm": 3.6309559490350654, | |
| "learning_rate": 4.926711109482401e-06, | |
| "loss": 1.0699, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05145062169501215, | |
| "grad_norm": 4.134626791396976, | |
| "learning_rate": 4.854242179361151e-06, | |
| "loss": 1.0268, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.055738173502929825, | |
| "grad_norm": 3.3445998120937954, | |
| "learning_rate": 4.782587680591894e-06, | |
| "loss": 1.2315, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06002572531084751, | |
| "grad_norm": 2.4730316039429288, | |
| "learning_rate": 4.711742096614044e-06, | |
| "loss": 0.9914, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06431327711876518, | |
| "grad_norm": 3.063463397168402, | |
| "learning_rate": 4.641699923379107e-06, | |
| "loss": 0.9354, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06860082892668286, | |
| "grad_norm": 3.72217017018073, | |
| "learning_rate": 4.5724556693791996e-06, | |
| "loss": 1.0356, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06860082892668286, | |
| "eval_loss": 0.9710695743560791, | |
| "eval_runtime": 20.9077, | |
| "eval_samples_per_second": 9.566, | |
| "eval_steps_per_second": 2.391, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07288838073460055, | |
| "grad_norm": 2.8296964090488466, | |
| "learning_rate": 4.504003855675734e-06, | |
| "loss": 1.0218, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07717593254251823, | |
| "grad_norm": 3.9492533196858313, | |
| "learning_rate": 4.436339015928335e-06, | |
| "loss": 0.9059, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0814634843504359, | |
| "grad_norm": 2.945729589644999, | |
| "learning_rate": 4.369455696423936e-06, | |
| "loss": 0.9862, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08575103615835358, | |
| "grad_norm": 2.8934728265120553, | |
| "learning_rate": 4.303348456106082e-06, | |
| "loss": 0.9869, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09003858796627126, | |
| "grad_norm": 3.6370231743108636, | |
| "learning_rate": 4.238011866604447e-06, | |
| "loss": 1.0137, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09432613977418894, | |
| "grad_norm": 2.8095030003011976, | |
| "learning_rate": 4.173440512264544e-06, | |
| "loss": 0.9834, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09861369158210662, | |
| "grad_norm": 2.5605385368574205, | |
| "learning_rate": 4.109628990177651e-06, | |
| "loss": 0.9828, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1029012433900243, | |
| "grad_norm": 3.328262187145733, | |
| "learning_rate": 4.04657191021096e-06, | |
| "loss": 0.9892, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10718879519794197, | |
| "grad_norm": 3.4906689890189835, | |
| "learning_rate": 3.984263895037921e-06, | |
| "loss": 0.9903, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.11147634700585965, | |
| "grad_norm": 2.845690441710927, | |
| "learning_rate": 3.9226995801688165e-06, | |
| "loss": 1.1259, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11576389881377733, | |
| "grad_norm": 2.7267526391731334, | |
| "learning_rate": 3.8618736139815605e-06, | |
| "loss": 0.9734, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.12005145062169502, | |
| "grad_norm": 2.062870391280079, | |
| "learning_rate": 3.8017806577526982e-06, | |
| "loss": 1.0515, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1243390024296127, | |
| "grad_norm": 2.814034294378353, | |
| "learning_rate": 3.7424153856886596e-06, | |
| "loss": 0.8449, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.12862655423753036, | |
| "grad_norm": 3.0711652275263357, | |
| "learning_rate": 3.6837724849572175e-06, | |
| "loss": 0.8388, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13291410604544804, | |
| "grad_norm": 3.437400624778036, | |
| "learning_rate": 3.6258466557191907e-06, | |
| "loss": 1.1761, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.13720165785336572, | |
| "grad_norm": 3.081997188340036, | |
| "learning_rate": 3.5686326111603775e-06, | |
| "loss": 1.0348, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13720165785336572, | |
| "eval_loss": 0.9355081915855408, | |
| "eval_runtime": 19.1453, | |
| "eval_samples_per_second": 10.446, | |
| "eval_steps_per_second": 2.612, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1414892096612834, | |
| "grad_norm": 2.8114117836276513, | |
| "learning_rate": 3.512125077523717e-06, | |
| "loss": 1.0048, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1457767614692011, | |
| "grad_norm": 2.707619981442126, | |
| "learning_rate": 3.456318794141709e-06, | |
| "loss": 0.8126, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15006431327711878, | |
| "grad_norm": 2.6357116905007856, | |
| "learning_rate": 3.4012085134690555e-06, | |
| "loss": 0.8684, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.15435186508503645, | |
| "grad_norm": 2.902285405452677, | |
| "learning_rate": 3.346789001115556e-06, | |
| "loss": 1.023, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.15863941689295413, | |
| "grad_norm": 3.1470604950987546, | |
| "learning_rate": 3.293055035879266e-06, | |
| "loss": 0.979, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.1629269687008718, | |
| "grad_norm": 2.429084645315808, | |
| "learning_rate": 3.2400014097798766e-06, | |
| "loss": 0.9414, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1672145205087895, | |
| "grad_norm": 2.6607376091673283, | |
| "learning_rate": 3.187622928092377e-06, | |
| "loss": 1.0719, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.17150207231670717, | |
| "grad_norm": 3.064466109382867, | |
| "learning_rate": 3.1359144093809653e-06, | |
| "loss": 0.9007, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17578962412462484, | |
| "grad_norm": 3.3202976410761815, | |
| "learning_rate": 3.084870685533213e-06, | |
| "loss": 1.0225, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.18007717593254252, | |
| "grad_norm": 9.376729410524437, | |
| "learning_rate": 3.034486601794506e-06, | |
| "loss": 0.8927, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1843647277404602, | |
| "grad_norm": 4.24264134885146, | |
| "learning_rate": 2.984757016802754e-06, | |
| "loss": 0.8904, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.18865227954837788, | |
| "grad_norm": 3.401996163001482, | |
| "learning_rate": 2.935676802623359e-06, | |
| "loss": 0.89, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.19293983135629555, | |
| "grad_norm": 2.811911382062161, | |
| "learning_rate": 2.887240844784472e-06, | |
| "loss": 1.0528, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.19722738316421323, | |
| "grad_norm": 6.117694360086105, | |
| "learning_rate": 2.8394440423125295e-06, | |
| "loss": 0.957, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2015149349721309, | |
| "grad_norm": 2.5418193456876024, | |
| "learning_rate": 2.7922813077680564e-06, | |
| "loss": 0.8757, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2058024867800486, | |
| "grad_norm": 2.980094551138022, | |
| "learning_rate": 2.7457475672817817e-06, | |
| "loss": 0.7212, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2058024867800486, | |
| "eval_loss": 0.9225141406059265, | |
| "eval_runtime": 19.142, | |
| "eval_samples_per_second": 10.448, | |
| "eval_steps_per_second": 2.612, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21009003858796627, | |
| "grad_norm": 2.8229472248870113, | |
| "learning_rate": 2.6998377605910153e-06, | |
| "loss": 0.7847, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.21437759039588394, | |
| "grad_norm": 3.313576806878507, | |
| "learning_rate": 2.6545468410763466e-06, | |
| "loss": 0.7885, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21866514220380162, | |
| "grad_norm": 2.7546057206480863, | |
| "learning_rate": 2.60986977579862e-06, | |
| "loss": 0.9853, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2229526940117193, | |
| "grad_norm": 2.62325989569962, | |
| "learning_rate": 2.565801545536224e-06, | |
| "loss": 0.8693, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.22724024581963698, | |
| "grad_norm": 2.494330977302947, | |
| "learning_rate": 2.52233714482269e-06, | |
| "loss": 0.8483, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.23152779762755465, | |
| "grad_norm": 3.0508796153780815, | |
| "learning_rate": 2.479471581984588e-06, | |
| "loss": 0.9198, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.23581534943547233, | |
| "grad_norm": 2.8596047579477077, | |
| "learning_rate": 2.437199879179748e-06, | |
| "loss": 0.8111, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.24010290124339004, | |
| "grad_norm": 2.9634105907172676, | |
| "learning_rate": 2.395517072435804e-06, | |
| "loss": 0.9249, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.24439045305130772, | |
| "grad_norm": 2.876075717907315, | |
| "learning_rate": 2.35441821168905e-06, | |
| "loss": 0.8466, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.2486780048592254, | |
| "grad_norm": 2.707429407550077, | |
| "learning_rate": 2.313898360823632e-06, | |
| "loss": 0.8335, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.25296555666714304, | |
| "grad_norm": 2.424659422914543, | |
| "learning_rate": 2.2739525977110787e-06, | |
| "loss": 0.9591, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.2572531084750607, | |
| "grad_norm": 2.3503862613323054, | |
| "learning_rate": 2.234576014250154e-06, | |
| "loss": 0.8867, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2615406602829784, | |
| "grad_norm": 2.487930933633346, | |
| "learning_rate": 2.195763716407068e-06, | |
| "loss": 0.9301, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.2658282120908961, | |
| "grad_norm": 2.9951853980801206, | |
| "learning_rate": 2.15751082425603e-06, | |
| "loss": 0.8933, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.27011576389881375, | |
| "grad_norm": 2.6479548343780044, | |
| "learning_rate": 2.119812472020151e-06, | |
| "loss": 1.1902, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.27440331570673143, | |
| "grad_norm": 3.031373376327646, | |
| "learning_rate": 2.082663808112706e-06, | |
| "loss": 0.8077, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.27440331570673143, | |
| "eval_loss": 0.9141628742218018, | |
| "eval_runtime": 19.1329, | |
| "eval_samples_per_second": 10.453, | |
| "eval_steps_per_second": 2.613, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2786908675146491, | |
| "grad_norm": 3.8925204318472777, | |
| "learning_rate": 2.0460599951787676e-06, | |
| "loss": 1.003, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.2829784193225668, | |
| "grad_norm": 2.8374998009671213, | |
| "learning_rate": 2.0099962101371912e-06, | |
| "loss": 0.9517, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2872659711304845, | |
| "grad_norm": 2.7039222330267725, | |
| "learning_rate": 1.9744676442229893e-06, | |
| "loss": 0.8129, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.2915535229384022, | |
| "grad_norm": 3.5945398321446014, | |
| "learning_rate": 1.9394695030300814e-06, | |
| "loss": 0.9616, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2958410747463199, | |
| "grad_norm": 4.022714585976749, | |
| "learning_rate": 1.904997006554424e-06, | |
| "loss": 0.9347, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.30012862655423755, | |
| "grad_norm": 2.449025495886818, | |
| "learning_rate": 1.8710453892375372e-06, | |
| "loss": 0.9365, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.30441617836215523, | |
| "grad_norm": 1.97102566822208, | |
| "learning_rate": 1.837609900010423e-06, | |
| "loss": 1.0678, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3087037301700729, | |
| "grad_norm": 2.9794081240205292, | |
| "learning_rate": 1.8046858023378982e-06, | |
| "loss": 0.8233, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3129912819779906, | |
| "grad_norm": 2.623718879014175, | |
| "learning_rate": 1.7722683742633203e-06, | |
| "loss": 1.089, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.31727883378590827, | |
| "grad_norm": 3.1393160530750808, | |
| "learning_rate": 1.7403529084537394e-06, | |
| "loss": 0.8982, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.32156638559382594, | |
| "grad_norm": 3.5048967956402506, | |
| "learning_rate": 1.708934712245474e-06, | |
| "loss": 0.8602, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.3258539374017436, | |
| "grad_norm": 2.731824579589462, | |
| "learning_rate": 1.6780091076901074e-06, | |
| "loss": 0.9206, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3301414892096613, | |
| "grad_norm": 2.6508962987997164, | |
| "learning_rate": 1.6475714316009228e-06, | |
| "loss": 0.9, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.334429041017579, | |
| "grad_norm": 3.3563303629070194, | |
| "learning_rate": 1.6176170355997885e-06, | |
| "loss": 0.9077, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.33871659282549665, | |
| "grad_norm": 2.510811889533464, | |
| "learning_rate": 1.5881412861644783e-06, | |
| "loss": 0.8796, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.34300414463341433, | |
| "grad_norm": 2.7025767408039423, | |
| "learning_rate": 1.559139564676459e-06, | |
| "loss": 0.8442, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34300414463341433, | |
| "eval_loss": 0.9068123698234558, | |
| "eval_runtime": 19.1503, | |
| "eval_samples_per_second": 10.444, | |
| "eval_steps_per_second": 2.611, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.347291696441332, | |
| "grad_norm": 2.3723461526691687, | |
| "learning_rate": 1.530607267469142e-06, | |
| "loss": 0.8776, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.3515792482492497, | |
| "grad_norm": 2.326426360163379, | |
| "learning_rate": 1.502539805876598e-06, | |
| "loss": 0.8368, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.35586680005716737, | |
| "grad_norm": 2.609797589938526, | |
| "learning_rate": 1.4749326062827624e-06, | |
| "loss": 0.8314, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.36015435186508504, | |
| "grad_norm": 3.018034878541378, | |
| "learning_rate": 1.447781110171118e-06, | |
| "loss": 0.8639, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3644419036730027, | |
| "grad_norm": 2.9665919577118394, | |
| "learning_rate": 1.421080774174884e-06, | |
| "loss": 0.8738, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.3687294554809204, | |
| "grad_norm": 2.7395052466656082, | |
| "learning_rate": 1.3948270701276901e-06, | |
| "loss": 0.8124, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3730170072888381, | |
| "grad_norm": 2.4814426410417547, | |
| "learning_rate": 1.3690154851147892e-06, | |
| "loss": 0.8018, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.37730455909675575, | |
| "grad_norm": 2.9039262323143697, | |
| "learning_rate": 1.3436415215247681e-06, | |
| "loss": 0.7621, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.38159211090467343, | |
| "grad_norm": 2.776860383566422, | |
| "learning_rate": 1.3187006971017973e-06, | |
| "loss": 0.9082, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.3858796627125911, | |
| "grad_norm": 2.1181970553123257, | |
| "learning_rate": 1.2941885449984206e-06, | |
| "loss": 0.8821, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3901672145205088, | |
| "grad_norm": 2.5660032110684767, | |
| "learning_rate": 1.2701006138288915e-06, | |
| "loss": 0.9639, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.39445476632842646, | |
| "grad_norm": 4.632813592554, | |
| "learning_rate": 1.2464324677230652e-06, | |
| "loss": 0.9052, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.39874231813634414, | |
| "grad_norm": 3.394837987828098, | |
| "learning_rate": 1.22317968638086e-06, | |
| "loss": 0.8723, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4030298699442618, | |
| "grad_norm": 2.716611388027132, | |
| "learning_rate": 1.2003378651272997e-06, | |
| "loss": 0.8457, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.4073174217521795, | |
| "grad_norm": 2.1520375204146625, | |
| "learning_rate": 1.1779026149681347e-06, | |
| "loss": 0.9502, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4116049735600972, | |
| "grad_norm": 2.7552080232688696, | |
| "learning_rate": 1.155869562646071e-06, | |
| "loss": 0.831, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4116049735600972, | |
| "eval_loss": 0.9032189846038818, | |
| "eval_runtime": 19.1348, | |
| "eval_samples_per_second": 10.452, | |
| "eval_steps_per_second": 2.613, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.41589252536801485, | |
| "grad_norm": 2.0689491545152663, | |
| "learning_rate": 1.1342343506976044e-06, | |
| "loss": 0.8338, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.42018007717593253, | |
| "grad_norm": 3.2134570774473494, | |
| "learning_rate": 1.1129926375104734e-06, | |
| "loss": 0.8289, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4244676289838502, | |
| "grad_norm": 2.822597617038844, | |
| "learning_rate": 1.0921400973817452e-06, | |
| "loss": 0.9218, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.4287551807917679, | |
| "grad_norm": 3.1918997161652003, | |
| "learning_rate": 1.071672420576549e-06, | |
| "loss": 0.8467, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43304273259968556, | |
| "grad_norm": 3.0230981418285885, | |
| "learning_rate": 1.051585313387455e-06, | |
| "loss": 0.8871, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.43733028440760324, | |
| "grad_norm": 2.345223930068171, | |
| "learning_rate": 1.0318744981945303e-06, | |
| "loss": 1.1172, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.4416178362155209, | |
| "grad_norm": 2.23873439529607, | |
| "learning_rate": 1.0125357135260713e-06, | |
| "loss": 1.0281, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.4459053880234386, | |
| "grad_norm": 2.17521388870601, | |
| "learning_rate": 9.93564714120029e-07, | |
| "loss": 0.9027, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4501929398313563, | |
| "grad_norm": 2.805982076338286, | |
| "learning_rate": 9.749572709861371e-07, | |
| "loss": 0.8424, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.45448049163927395, | |
| "grad_norm": 3.076865463356093, | |
| "learning_rate": 9.5670917146877e-07, | |
| "loss": 1.0317, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.45876804344719163, | |
| "grad_norm": 2.351075063586948, | |
| "learning_rate": 9.38816219310525e-07, | |
| "loss": 0.9455, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.4630555952551093, | |
| "grad_norm": 3.042494238619368, | |
| "learning_rate": 9.212742347165562e-07, | |
| "loss": 0.914, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.467343147063027, | |
| "grad_norm": 2.51152797954818, | |
| "learning_rate": 9.040790544196722e-07, | |
| "loss": 0.8507, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.47163069887094466, | |
| "grad_norm": 2.2530854319732647, | |
| "learning_rate": 8.872265317462145e-07, | |
| "loss": 0.7923, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.47591825067886234, | |
| "grad_norm": 2.4496883783363876, | |
| "learning_rate": 8.707125366827236e-07, | |
| "loss": 0.8219, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.4802058024867801, | |
| "grad_norm": 2.85322554374369, | |
| "learning_rate": 8.54532955943421e-07, | |
| "loss": 0.9696, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4802058024867801, | |
| "eval_loss": 0.8974508047103882, | |
| "eval_runtime": 19.0314, | |
| "eval_samples_per_second": 10.509, | |
| "eval_steps_per_second": 2.627, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.48449335429469775, | |
| "grad_norm": 2.657892610245309, | |
| "learning_rate": 8.386836930385165e-07, | |
| "loss": 0.8421, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.48878090610261543, | |
| "grad_norm": 2.602711920187755, | |
| "learning_rate": 8.231606683433569e-07, | |
| "loss": 0.8295, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.4930684579105331, | |
| "grad_norm": 2.1213399589470616, | |
| "learning_rate": 8.079598191684382e-07, | |
| "loss": 0.8803, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.4973560097184508, | |
| "grad_norm": 2.244791995121278, | |
| "learning_rate": 7.930770998302978e-07, | |
| "loss": 0.8343, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5016435615263685, | |
| "grad_norm": 2.566423079642009, | |
| "learning_rate": 7.785084817233009e-07, | |
| "loss": 0.8736, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.5059311133342861, | |
| "grad_norm": 2.3039665634657487, | |
| "learning_rate": 7.642499533923466e-07, | |
| "loss": 0.8449, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5102186651422038, | |
| "grad_norm": 2.6413196407680095, | |
| "learning_rate": 7.502975206065118e-07, | |
| "loss": 0.9765, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.5145062169501214, | |
| "grad_norm": 2.6494694608389806, | |
| "learning_rate": 7.366472064336485e-07, | |
| "loss": 1.041, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5187937687580392, | |
| "grad_norm": 2.777084503723626, | |
| "learning_rate": 7.232950513159591e-07, | |
| "loss": 0.7932, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.5230813205659568, | |
| "grad_norm": 2.487662762486022, | |
| "learning_rate": 7.102371131465766e-07, | |
| "loss": 0.8704, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5273688723738745, | |
| "grad_norm": 2.55250344248028, | |
| "learning_rate": 6.974694673471581e-07, | |
| "loss": 0.8656, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.5316564241817922, | |
| "grad_norm": 3.215607059371808, | |
| "learning_rate": 6.849882069465297e-07, | |
| "loss": 0.8775, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5359439759897099, | |
| "grad_norm": 2.663679299659993, | |
| "learning_rate": 6.727894426603947e-07, | |
| "loss": 0.9558, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5402315277976275, | |
| "grad_norm": 1.8863771094416066, | |
| "learning_rate": 6.608693029721375e-07, | |
| "loss": 1.0649, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5445190796055452, | |
| "grad_norm": 2.3166038184540345, | |
| "learning_rate": 6.492239342147439e-07, | |
| "loss": 0.9116, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.5488066314134629, | |
| "grad_norm": 2.451365227453816, | |
| "learning_rate": 6.378495006538639e-07, | |
| "loss": 0.9949, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5488066314134629, | |
| "eval_loss": 0.8972450494766235, | |
| "eval_runtime": 19.0746, | |
| "eval_samples_per_second": 10.485, | |
| "eval_steps_per_second": 2.621, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5530941832213806, | |
| "grad_norm": 2.431525558235171, | |
| "learning_rate": 6.267421845720492e-07, | |
| "loss": 0.9208, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.5573817350292982, | |
| "grad_norm": 3.025842320604373, | |
| "learning_rate": 6.158981863541822e-07, | |
| "loss": 0.8782, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.561669286837216, | |
| "grad_norm": 2.713593393993989, | |
| "learning_rate": 6.053137245741388e-07, | |
| "loss": 0.8848, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.5659568386451336, | |
| "grad_norm": 2.364400143996411, | |
| "learning_rate": 5.949850360827048e-07, | |
| "loss": 0.8214, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5702443904530513, | |
| "grad_norm": 3.1249075781445654, | |
| "learning_rate": 5.849083760967786e-07, | |
| "loss": 0.9232, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.574531942260969, | |
| "grad_norm": 2.371939438179526, | |
| "learning_rate": 5.750800182898949e-07, | |
| "loss": 0.9599, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5788194940688867, | |
| "grad_norm": 2.657320971034355, | |
| "learning_rate": 5.654962548840998e-07, | |
| "loss": 0.957, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.5831070458768044, | |
| "grad_norm": 1.9610510581627134, | |
| "learning_rate": 5.561533967432111e-07, | |
| "loss": 0.8544, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.587394597684722, | |
| "grad_norm": 1.9590021785129759, | |
| "learning_rate": 5.470477734675006e-07, | |
| "loss": 0.9022, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.5916821494926398, | |
| "grad_norm": 3.0946081747543532, | |
| "learning_rate": 5.381757334898326e-07, | |
| "loss": 0.8607, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.5959697013005574, | |
| "grad_norm": 2.6523600890631447, | |
| "learning_rate": 5.295336441732995e-07, | |
| "loss": 0.9483, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.6002572531084751, | |
| "grad_norm": 2.6162593545931943, | |
| "learning_rate": 5.211178919103908e-07, | |
| "loss": 0.8484, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6045448049163927, | |
| "grad_norm": 2.7584028741566935, | |
| "learning_rate": 5.129248822237369e-07, | |
| "loss": 0.8153, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.6088323567243105, | |
| "grad_norm": 2.2177368688014263, | |
| "learning_rate": 5.049510398684706e-07, | |
| "loss": 0.8865, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6131199085322281, | |
| "grad_norm": 2.7385320493457175, | |
| "learning_rate": 4.97192808936251e-07, | |
| "loss": 0.8288, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.6174074603401458, | |
| "grad_norm": 2.969022490845044, | |
| "learning_rate": 4.896466529609901e-07, | |
| "loss": 0.8154, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6174074603401458, | |
| "eval_loss": 0.8948369026184082, | |
| "eval_runtime": 19.0474, | |
| "eval_samples_per_second": 10.5, | |
| "eval_steps_per_second": 2.625, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6216950121480634, | |
| "grad_norm": 2.4080414960336576, | |
| "learning_rate": 4.823090550263373e-07, | |
| "loss": 0.8132, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6259825639559812, | |
| "grad_norm": 2.4062548632108305, | |
| "learning_rate": 4.7517651787496393e-07, | |
| "loss": 0.8563, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.6302701157638988, | |
| "grad_norm": 2.4974176263678145, | |
| "learning_rate": 4.682455640197012e-07, | |
| "loss": 0.83, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.6345576675718165, | |
| "grad_norm": 2.782934403189113, | |
| "learning_rate": 4.6151273585658703e-07, | |
| "loss": 0.7722, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.6388452193797342, | |
| "grad_norm": 3.589995905013926, | |
| "learning_rate": 4.549745957798709e-07, | |
| "loss": 0.9013, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.6431327711876519, | |
| "grad_norm": 1.5164412373226497, | |
| "learning_rate": 4.486277262990414e-07, | |
| "loss": 0.8061, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6474203229955695, | |
| "grad_norm": 2.4822941257221496, | |
| "learning_rate": 4.424687301579312e-07, | |
| "loss": 0.8018, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.6517078748034872, | |
| "grad_norm": 2.3163460863010044, | |
| "learning_rate": 4.364942304559619e-07, | |
| "loss": 0.97, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6559954266114049, | |
| "grad_norm": 2.5709552598683048, | |
| "learning_rate": 4.307008707715972e-07, | |
| "loss": 0.8424, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.6602829784193226, | |
| "grad_norm": 2.97580695190474, | |
| "learning_rate": 4.250853152880694e-07, | |
| "loss": 0.9495, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6645705302272402, | |
| "grad_norm": 2.780816600415984, | |
| "learning_rate": 4.1964424892144836e-07, | |
| "loss": 0.9217, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.668858082035158, | |
| "grad_norm": 3.106789897489022, | |
| "learning_rate": 4.143743774511321e-07, | |
| "loss": 0.7872, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6731456338430756, | |
| "grad_norm": 2.6180834213520425, | |
| "learning_rate": 4.0927242765282987e-07, | |
| "loss": 0.9516, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.6774331856509933, | |
| "grad_norm": 3.3693090699327675, | |
| "learning_rate": 4.043351474341226e-07, | |
| "loss": 0.918, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6817207374589109, | |
| "grad_norm": 2.6455267685583292, | |
| "learning_rate": 3.995593059726841e-07, | |
| "loss": 0.8869, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.6860082892668287, | |
| "grad_norm": 2.6976779093683985, | |
| "learning_rate": 3.9494169385724855e-07, | |
| "loss": 0.9682, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6860082892668287, | |
| "eval_loss": 0.8931262493133545, | |
| "eval_runtime": 19.039, | |
| "eval_samples_per_second": 10.505, | |
| "eval_steps_per_second": 2.626, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6902958410747463, | |
| "grad_norm": 2.73935107332009, | |
| "learning_rate": 3.904791232314207e-07, | |
| "loss": 0.9497, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.694583392882664, | |
| "grad_norm": 2.594513781497614, | |
| "learning_rate": 3.861684279404229e-07, | |
| "loss": 0.9616, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.6988709446905816, | |
| "grad_norm": 2.2189306808012694, | |
| "learning_rate": 3.820064636808802e-07, | |
| "loss": 1.0817, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.7031584964984994, | |
| "grad_norm": 2.636673641067638, | |
| "learning_rate": 3.7799010815375107e-07, | |
| "loss": 0.9003, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.707446048306417, | |
| "grad_norm": 2.074697655719305, | |
| "learning_rate": 3.741162612205157e-07, | |
| "loss": 1.1193, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7117336001143347, | |
| "grad_norm": 2.4627913841496425, | |
| "learning_rate": 3.703818450627364e-07, | |
| "loss": 0.8603, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.7160211519222524, | |
| "grad_norm": 2.4468198599625044, | |
| "learning_rate": 3.6678380434511737e-07, | |
| "loss": 1.012, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.7203087037301701, | |
| "grad_norm": 2.231882643368985, | |
| "learning_rate": 3.6331910638219e-07, | |
| "loss": 1.0174, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.7245962555380877, | |
| "grad_norm": 3.0961788514759374, | |
| "learning_rate": 3.5998474130876195e-07, | |
| "loss": 0.982, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.7288838073460054, | |
| "grad_norm": 2.699948117104775, | |
| "learning_rate": 3.567777222542744e-07, | |
| "loss": 0.9954, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.7331713591539231, | |
| "grad_norm": 2.0352300295309815, | |
| "learning_rate": 3.536950855212165e-07, | |
| "loss": 0.9349, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.7374589109618408, | |
| "grad_norm": 2.3439290267355664, | |
| "learning_rate": 3.5073389076775976e-07, | |
| "loss": 1.1525, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.7417464627697584, | |
| "grad_norm": 1.8013900413258555, | |
| "learning_rate": 3.4789122119478064e-07, | |
| "loss": 1.0404, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.7460340145776762, | |
| "grad_norm": 2.432177798756092, | |
| "learning_rate": 3.451641837374477e-07, | |
| "loss": 1.1018, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7503215663855938, | |
| "grad_norm": 2.339931147492053, | |
| "learning_rate": 3.425499092615662e-07, | |
| "loss": 1.0088, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.7546091181935115, | |
| "grad_norm": 2.865649768086174, | |
| "learning_rate": 3.4004555276487614e-07, | |
| "loss": 0.9491, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7546091181935115, | |
| "eval_loss": 0.9030270576477051, | |
| "eval_runtime": 19.0612, | |
| "eval_samples_per_second": 10.493, | |
| "eval_steps_per_second": 2.623, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7588966700014291, | |
| "grad_norm": 1.9608521922901478, | |
| "learning_rate": 3.376482935835186e-07, | |
| "loss": 1.0566, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.7631842218093469, | |
| "grad_norm": 2.001405740517041, | |
| "learning_rate": 3.3535533560389486e-07, | |
| "loss": 1.0203, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7674717736172646, | |
| "grad_norm": 3.114574828020116, | |
| "learning_rate": 3.331639074801548e-07, | |
| "loss": 0.9489, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.7717593254251822, | |
| "grad_norm": 2.3092110155282985, | |
| "learning_rate": 3.3107126285757256e-07, | |
| "loss": 0.9057, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7760468772331, | |
| "grad_norm": 2.714773467015402, | |
| "learning_rate": 3.290746806020766e-07, | |
| "loss": 0.9441, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.7803344290410176, | |
| "grad_norm": 3.186486155591397, | |
| "learning_rate": 3.271714650362233e-07, | |
| "loss": 1.0213, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.7846219808489353, | |
| "grad_norm": 2.5861267874594174, | |
| "learning_rate": 3.2535894618192186e-07, | |
| "loss": 0.9689, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.7889095326568529, | |
| "grad_norm": 3.826794117846477, | |
| "learning_rate": 3.236344800102375e-07, | |
| "loss": 0.8944, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7931970844647707, | |
| "grad_norm": 2.7462154972645814, | |
| "learning_rate": 3.2199544869862547e-07, | |
| "loss": 1.0624, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.7974846362726883, | |
| "grad_norm": 2.8358584012860777, | |
| "learning_rate": 3.204392608959703e-07, | |
| "loss": 0.9327, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.801772188080606, | |
| "grad_norm": 2.101011305773841, | |
| "learning_rate": 3.1896335199583363e-07, | |
| "loss": 0.9159, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.8060597398885236, | |
| "grad_norm": 2.5833966453921198, | |
| "learning_rate": 3.1756518441834397e-07, | |
| "loss": 1.0248, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.8103472916964414, | |
| "grad_norm": 6.2684841674997775, | |
| "learning_rate": 3.151927901941027e-07, | |
| "loss": 1.0413, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.814634843504359, | |
| "grad_norm": 2.276372461235212, | |
| "learning_rate": 3.1032417503134016e-07, | |
| "loss": 1.1134, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8189223953122767, | |
| "grad_norm": 2.6812797606926555, | |
| "learning_rate": 3.054555598685777e-07, | |
| "loss": 0.9336, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.8232099471201944, | |
| "grad_norm": 2.417389224635538, | |
| "learning_rate": 3.0058694470581514e-07, | |
| "loss": 1.068, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.8232099471201944, | |
| "eval_loss": 0.9022178053855896, | |
| "eval_runtime": 19.0566, | |
| "eval_samples_per_second": 10.495, | |
| "eval_steps_per_second": 2.624, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.8274974989281121, | |
| "grad_norm": 2.503558384043619, | |
| "learning_rate": 2.9571832954305265e-07, | |
| "loss": 1.0307, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.8317850507360297, | |
| "grad_norm": 2.249581998288759, | |
| "learning_rate": 2.9084971438029017e-07, | |
| "loss": 0.9962, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.8360726025439474, | |
| "grad_norm": 3.875121879524354, | |
| "learning_rate": 2.8598109921752763e-07, | |
| "loss": 1.0143, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.8403601543518651, | |
| "grad_norm": 1.730446489555693, | |
| "learning_rate": 2.8111248405476515e-07, | |
| "loss": 0.9869, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.8446477061597828, | |
| "grad_norm": 3.3232425457372745, | |
| "learning_rate": 2.7624386889200266e-07, | |
| "loss": 1.0683, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.8489352579677004, | |
| "grad_norm": 2.4807364391304225, | |
| "learning_rate": 2.713752537292401e-07, | |
| "loss": 0.9797, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.8532228097756182, | |
| "grad_norm": 2.3616731714440724, | |
| "learning_rate": 2.6650663856647764e-07, | |
| "loss": 1.0389, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.8575103615835358, | |
| "grad_norm": 2.6062865385957514, | |
| "learning_rate": 2.616380234037151e-07, | |
| "loss": 1.0267, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8617979133914535, | |
| "grad_norm": 2.907979106229624, | |
| "learning_rate": 2.567694082409526e-07, | |
| "loss": 0.9329, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.8660854651993711, | |
| "grad_norm": 2.6968962865268407, | |
| "learning_rate": 2.5190079307819013e-07, | |
| "loss": 0.9386, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8703730170072889, | |
| "grad_norm": 2.21037904641155, | |
| "learning_rate": 2.4703217791542765e-07, | |
| "loss": 1.0709, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.8746605688152065, | |
| "grad_norm": 2.8255592337377915, | |
| "learning_rate": 2.421635627526651e-07, | |
| "loss": 0.8629, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.8789481206231242, | |
| "grad_norm": 2.6598508915895516, | |
| "learning_rate": 2.3729494758990262e-07, | |
| "loss": 0.9564, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.8832356724310418, | |
| "grad_norm": 2.5349227338549043, | |
| "learning_rate": 2.3242633242714014e-07, | |
| "loss": 0.9884, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.8875232242389596, | |
| "grad_norm": 1.8000674399648018, | |
| "learning_rate": 2.275577172643776e-07, | |
| "loss": 1.1607, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.8918107760468772, | |
| "grad_norm": 2.0150522007599654, | |
| "learning_rate": 2.2268910210161506e-07, | |
| "loss": 1.06, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.8918107760468772, | |
| "eval_loss": 0.9013447761535645, | |
| "eval_runtime": 19.0476, | |
| "eval_samples_per_second": 10.5, | |
| "eval_steps_per_second": 2.625, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.8960983278547949, | |
| "grad_norm": 2.714964092055051, | |
| "learning_rate": 2.1782048693885258e-07, | |
| "loss": 0.8408, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.9003858796627126, | |
| "grad_norm": 2.328572268378804, | |
| "learning_rate": 2.129518717760901e-07, | |
| "loss": 0.9585, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9046734314706303, | |
| "grad_norm": 3.3294058341520847, | |
| "learning_rate": 2.0808325661332756e-07, | |
| "loss": 1.0169, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.9089609832785479, | |
| "grad_norm": 2.3567378214154453, | |
| "learning_rate": 2.0321464145056507e-07, | |
| "loss": 1.0411, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.9132485350864656, | |
| "grad_norm": 2.3516481223731702, | |
| "learning_rate": 1.9834602628780256e-07, | |
| "loss": 1.0731, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.9175360868943833, | |
| "grad_norm": 2.3183322496467484, | |
| "learning_rate": 1.934774111250401e-07, | |
| "loss": 0.9489, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.921823638702301, | |
| "grad_norm": 1.97960646392379, | |
| "learning_rate": 1.8860879596227757e-07, | |
| "loss": 1.0331, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.9261111905102186, | |
| "grad_norm": 2.3395284448987086, | |
| "learning_rate": 1.8374018079951505e-07, | |
| "loss": 0.7678, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.9303987423181364, | |
| "grad_norm": 1.945316009597557, | |
| "learning_rate": 1.788715656367526e-07, | |
| "loss": 1.0268, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.934686294126054, | |
| "grad_norm": 2.5392514762785603, | |
| "learning_rate": 1.7400295047399006e-07, | |
| "loss": 1.0499, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.9389738459339717, | |
| "grad_norm": 2.147497075881358, | |
| "learning_rate": 1.6913433531122752e-07, | |
| "loss": 0.8984, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.9432613977418893, | |
| "grad_norm": 2.3338579963123043, | |
| "learning_rate": 1.6426572014846504e-07, | |
| "loss": 1.0244, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9475489495498071, | |
| "grad_norm": 2.272071646300021, | |
| "learning_rate": 1.5939710498570255e-07, | |
| "loss": 0.8251, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.9518365013577247, | |
| "grad_norm": 1.6609121532926487, | |
| "learning_rate": 1.5452848982294004e-07, | |
| "loss": 0.9794, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.9561240531656424, | |
| "grad_norm": 2.2563188492644493, | |
| "learning_rate": 1.4965987466017753e-07, | |
| "loss": 0.972, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.9604116049735602, | |
| "grad_norm": 2.667525192015302, | |
| "learning_rate": 1.4479125949741505e-07, | |
| "loss": 0.8302, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.9604116049735602, | |
| "eval_loss": 0.9002277851104736, | |
| "eval_runtime": 19.0592, | |
| "eval_samples_per_second": 10.494, | |
| "eval_steps_per_second": 2.623, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.9646991567814778, | |
| "grad_norm": 1.8891294277340498, | |
| "learning_rate": 1.3992264433465253e-07, | |
| "loss": 0.8849, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.9689867085893955, | |
| "grad_norm": 2.5578344667960127, | |
| "learning_rate": 1.3505402917189002e-07, | |
| "loss": 0.9591, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.9732742603973131, | |
| "grad_norm": 2.001959937555614, | |
| "learning_rate": 1.301854140091275e-07, | |
| "loss": 1.0343, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.9775618122052309, | |
| "grad_norm": 1.578569313456066, | |
| "learning_rate": 1.2531679884636503e-07, | |
| "loss": 1.0543, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9818493640131485, | |
| "grad_norm": 2.0720069005801953, | |
| "learning_rate": 1.2044818368360252e-07, | |
| "loss": 0.8641, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.9861369158210662, | |
| "grad_norm": 1.8810386084158826, | |
| "learning_rate": 1.1557956852084e-07, | |
| "loss": 1.0326, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.9904244676289838, | |
| "grad_norm": 2.0266012589600613, | |
| "learning_rate": 1.1071095335807752e-07, | |
| "loss": 1.0289, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.9947120194369016, | |
| "grad_norm": 2.2518373465247357, | |
| "learning_rate": 1.0584233819531501e-07, | |
| "loss": 0.939, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.9989995712448192, | |
| "grad_norm": 2.7326466173600337, | |
| "learning_rate": 1.009737230325525e-07, | |
| "loss": 1.0486, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.9998570816064027, | |
| "step": 1166, | |
| "total_flos": 1.7681949461682586e+17, | |
| "train_loss": 0.944941889564946, | |
| "train_runtime": 15099.9882, | |
| "train_samples_per_second": 2.78, | |
| "train_steps_per_second": 0.077 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1166, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1166, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7681949461682586e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |