karths/binary_classification_train_documentation
021
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 4.999679630934837,5 "eval_steps": 500,6 "global_step": 39015,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.06,13 "learning_rate": 4.9800000000000004e-05,14 "loss": 0.049,15 "step": 50016 },17 {18 "epoch": 0.13,19 "learning_rate": 4.997937713868709e-05,20 "loss": 0.0574,21 "step": 100022 },23 {24 "epoch": 0.19,25 "learning_rate": 4.991721127523219e-05,26 "loss": 0.0621,27 "step": 150028 },29 {30 "epoch": 0.26,31 "learning_rate": 4.981360546534587e-05,32 "loss": 0.0639,33 "step": 200034 },35 {36 "epoch": 0.32,37 "learning_rate": 4.966873201640091e-05,38 "loss": 0.0679,39 "step": 250040 },41 {42 "epoch": 0.38,43 "learning_rate": 4.948283186819981e-05,44 "loss": 0.0746,45 "step": 300046 },47 {48 "epoch": 0.45,49 "learning_rate": 4.9256214192266534e-05,50 "loss": 0.0778,51 "step": 350052 },53 {54 "epoch": 0.51,55 "learning_rate": 4.898982977024972e-05,56 "loss": 0.0752,57 "step": 400058 },59 {60 "epoch": 0.58,61 "learning_rate": 4.868305410275411e-05,62 "loss": 0.0763,63 "step": 450064 },65 {66 "epoch": 0.64,67 "learning_rate": 4.833689102217645e-05,68 "loss": 0.0769,69 "step": 500070 },71 {72 "epoch": 0.7,73 "learning_rate": 4.795191623417485e-05,74 "loss": 0.0755,75 "step": 550076 },77 {78 "epoch": 0.77,79 "learning_rate": 4.752965392266396e-05,80 "loss": 0.0751,81 "step": 600082 },83 {84 "epoch": 0.83,85 "learning_rate": 4.706911415528901e-05,86 "loss": 0.0783,87 "step": 650088 },89 {90 "epoch": 0.9,91 "learning_rate": 4.6571871126931825e-05,92 "loss": 0.078,93 "step": 700094 },95 {96 "epoch": 0.96,97 "learning_rate": 4.6038751805114225e-05,98 "loss": 0.0785,99 "step": 7500100 },101 {102 "epoch": 1.03,103 "learning_rate": 4.547064282341224e-05,104 "loss": 0.0719,105 "step": 8000106 },107 {108 "epoch": 1.09,109 "learning_rate": 4.486848900689111e-05,110 "loss": 0.0593,111 "step": 8500112 },113 {114 "epoch": 1.15,115 "learning_rate": 4.423329180076173e-05,116 "loss": 0.0636,117 "step": 9000118 },119 {120 "epoch": 1.22,121 "learning_rate": 4.356747316744135e-05,122 "loss": 0.0639,123 "step": 9500124 },125 {126 "epoch": 1.28,127 "learning_rate": 4.286947219232885e-05,128 "loss": 0.0614,129 "step": 10000130 },131 {132 "epoch": 1.35,133 "learning_rate": 4.214175240309113e-05,134 "loss": 0.0657,135 "step": 10500136 },137 {138 "epoch": 1.41,139 "learning_rate": 4.138552407437527e-05,140 "loss": 0.0625,141 "step": 11000142 },143 {144 "epoch": 1.47,145 "learning_rate": 4.0602044893531846e-05,146 "loss": 0.065,147 "step": 11500148 },149 {150 "epoch": 1.54,151 "learning_rate": 3.979426173115841e-05,152 "loss": 0.0625,153 "step": 12000154 },155 {156 "epoch": 1.6,157 "learning_rate": 3.89619724591825e-05,158 "loss": 0.0635,159 "step": 12500160 },161 {162 "epoch": 1.67,163 "learning_rate": 3.81048191928653e-05,164 "loss": 0.0627,165 "step": 13000166 },167 {168 "epoch": 1.73,169 "learning_rate": 3.7225871232136e-05,170 "loss": 0.0669,171 "step": 13500172 },173 {174 "epoch": 1.79,175 "learning_rate": 3.6326590360017014e-05,176 "loss": 0.0638,177 "step": 14000178 },179 {180 "epoch": 1.86,181 "learning_rate": 3.540847217530374e-05,182 "loss": 0.0632,183 "step": 14500184 },185 {186 "epoch": 1.92,187 "learning_rate": 3.447304360522618e-05,188 "loss": 0.0666,189 "step": 15000190 },191 {192 "epoch": 1.99,193 "learning_rate": 3.352186036600821e-05,194 "loss": 0.0626,195 "step": 15500196 },197 {198 "epoch": 2.05,199 "learning_rate": 3.2556504375547626e-05,200 "loss": 0.0514,201 "step": 16000202 },203 {204 "epoch": 2.11,205 "learning_rate": 3.158054843335624e-05,206 "loss": 0.0463,207 "step": 16500208 },209 {210 "epoch": 2.18,211 "learning_rate": 3.0591704553180736e-05,212 "loss": 0.0467,213 "step": 17000214 },215 {216 "epoch": 2.24,217 "learning_rate": 2.959356107945986e-05,218 "loss": 0.0476,219 "step": 17500220 },221 {222 "epoch": 2.31,223 "learning_rate": 2.858979611033543e-05,224 "loss": 0.0505,225 "step": 18000226 },227 {228 "epoch": 2.37,229 "learning_rate": 2.75780564653496e-05,230 "loss": 0.0502,231 "step": 18500232 },233 {234 "epoch": 2.43,235 "learning_rate": 2.656202924096166e-05,236 "loss": 0.047,237 "step": 19000238 },239 {240 "epoch": 2.5,241 "learning_rate": 2.554340419744563e-05,242 "loss": 0.0461,243 "step": 19500244 },245 {246 "epoch": 2.56,247 "learning_rate": 2.4523875415522277e-05,248 "loss": 0.0465,249 "step": 20000250 },251 {252 "epoch": 2.63,253 "learning_rate": 2.350513847892453e-05,254 "loss": 0.05,255 "step": 20500256 },257 {258 "epoch": 2.69,259 "learning_rate": 2.2488887654463146e-05,260 "loss": 0.0471,261 "step": 21000262 },263 {264 "epoch": 2.76,265 "learning_rate": 2.1478831935354516e-05,266 "loss": 0.0478,267 "step": 21500268 },269 {270 "epoch": 2.82,271 "learning_rate": 2.047260339339565e-05,272 "loss": 0.0467,273 "step": 22000274 },275 {276 "epoch": 2.88,277 "learning_rate": 1.9473904388782642e-05,278 "loss": 0.0458,279 "step": 22500280 },281 {282 "epoch": 2.95,283 "learning_rate": 1.8484395863135113e-05,284 "loss": 0.0451,285 "step": 23000286 },287 {288 "epoch": 3.01,289 "learning_rate": 1.750572347333834e-05,290 "loss": 0.0443,291 "step": 23500292 },293 {294 "epoch": 3.08,295 "learning_rate": 1.6541433761257506e-05,296 "loss": 0.0307,297 "step": 24000298 },299 {300 "epoch": 3.14,301 "learning_rate": 1.558926609041298e-05,302 "loss": 0.0313,303 "step": 24500304 },305 {306 "epoch": 3.2,307 "learning_rate": 1.4652749461123058e-05,308 "loss": 0.0362,309 "step": 25000310 },311 {312 "epoch": 3.27,313 "learning_rate": 1.3733441399168673e-05,314 "loss": 0.035,315 "step": 25500316 },317 {318 "epoch": 3.33,319 "learning_rate": 1.2832870810670993e-05,320 "loss": 0.0324,321 "step": 26000322 },323 {324 "epoch": 3.4,325 "learning_rate": 1.1952535439359563e-05,326 "loss": 0.0335,327 "step": 26500328 },329 {330 "epoch": 3.46,331 "learning_rate": 1.1095594036489903e-05,332 "loss": 0.0322,333 "step": 27000334 },335 {336 "epoch": 3.52,337 "learning_rate": 1.0260037628024472e-05,338 "loss": 0.0332,339 "step": 27500340 },341 {342 "epoch": 3.59,343 "learning_rate": 9.448995329278178e-06,344 "loss": 0.033,345 "step": 28000346 },347 {348 "epoch": 3.65,349 "learning_rate": 8.66381598900628e-06,350 "loss": 0.035,351 "step": 28500352 },353 {354 "epoch": 3.72,355 "learning_rate": 7.905805443140457e-06,356 "loss": 0.035,357 "step": 29000358 },359 {360 "epoch": 3.78,361 "learning_rate": 7.177654318094604e-06,362 "loss": 0.0349,363 "step": 29500364 },365 {366 "epoch": 3.84,367 "learning_rate": 6.4776555698389505e-06,368 "loss": 0.0333,369 "step": 30000370 },371 {372 "epoch": 3.91,373 "learning_rate": 5.808461430995301e-06,374 "loss": 0.0313,375 "step": 30500376 },377 {378 "epoch": 3.97,379 "learning_rate": 5.171184841890728e-06,380 "loss": 0.0358,381 "step": 31000382 },383 {384 "epoch": 4.04,385 "learning_rate": 4.568060670213628e-06,386 "loss": 0.0301,387 "step": 31500388 },389 {390 "epoch": 4.1,391 "learning_rate": 3.99767497937713e-06,392 "loss": 0.028,393 "step": 32000394 },395 {396 "epoch": 4.16,397 "learning_rate": 3.4622183668462316e-06,398 "loss": 0.028,399 "step": 32500400 },401 {402 "epoch": 4.23,403 "learning_rate": 2.962581353357577e-06,404 "loss": 0.0269,405 "step": 33000406 },407 {408 "epoch": 4.29,409 "learning_rate": 2.5004837614951537e-06,410 "loss": 0.0273,411 "step": 33500412 },413 {414 "epoch": 4.36,415 "learning_rate": 2.0748422709038623e-06,416 "loss": 0.0277,417 "step": 34000418 },419 {420 "epoch": 4.42,421 "learning_rate": 1.6873277319096742e-06,422 "loss": 0.027,423 "step": 34500424 },425 {426 "epoch": 4.49,427 "learning_rate": 1.3385846220008548e-06,428 "loss": 0.0271,429 "step": 35000430 },431 {432 "epoch": 4.55,433 "learning_rate": 1.0297720953505841e-06,434 "loss": 0.0297,435 "step": 35500436 },437 {438 "epoch": 4.61,439 "learning_rate": 7.601661860652421e-07,440 "loss": 0.0276,441 "step": 36000442 },443 {444 "epoch": 4.68,445 "learning_rate": 5.308736731572172e-07,446 "loss": 0.0283,447 "step": 36500448 },449 {450 "epoch": 4.74,451 "learning_rate": 3.4227589422272943e-07,452 "loss": 0.0305,453 "step": 37000454 },455 {456 "epoch": 4.81,457 "learning_rate": 1.9468650722975211e-07,458 "loss": 0.0302,459 "step": 37500460 },461 {462 "epoch": 4.87,463 "learning_rate": 8.852233960627565e-08,464 "loss": 0.028,465 "step": 38000466 },467 {468 "epoch": 4.93,469 "learning_rate": 2.3534504957314906e-08,470 "loss": 0.0344,471 "step": 38500472 },473 {474 "epoch": 5.0,475 "learning_rate": 9.056858269462787e-11,476 "loss": 0.0306,477 "step": 39000478 }479 ],480 "logging_steps": 500,481 "max_steps": 39015,482 "num_train_epochs": 5,483 "save_steps": 500,484 "total_flos": 3.307647360088965e+17,485 "trial_name": null,486 "trial_params": null487}488 