| { | |
| "best_metric": 0.03369523584842682, | |
| "best_model_checkpoint": "./windturbine_outputs/checkpoint-394", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 985, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.050761421319796954, | |
| "grad_norm": 46.4831657409668, | |
| "learning_rate": 1.9796954314720812e-05, | |
| "loss": 1.233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10152284263959391, | |
| "grad_norm": 181.1588592529297, | |
| "learning_rate": 1.9593908629441626e-05, | |
| "loss": 0.7105, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15228426395939088, | |
| "grad_norm": 23.9494686126709, | |
| "learning_rate": 1.939086294416244e-05, | |
| "loss": 0.499, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 51.11117935180664, | |
| "learning_rate": 1.918781725888325e-05, | |
| "loss": 0.3099, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25380710659898476, | |
| "grad_norm": 47.91529083251953, | |
| "learning_rate": 1.8984771573604063e-05, | |
| "loss": 0.3527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.30456852791878175, | |
| "grad_norm": 655.8473510742188, | |
| "learning_rate": 1.8781725888324877e-05, | |
| "loss": 0.4137, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3553299492385787, | |
| "grad_norm": 1.7267569303512573, | |
| "learning_rate": 1.8578680203045687e-05, | |
| "loss": 0.3445, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 11.01191234588623, | |
| "learning_rate": 1.8375634517766498e-05, | |
| "loss": 0.3102, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.45685279187817257, | |
| "grad_norm": 169.2871551513672, | |
| "learning_rate": 1.817258883248731e-05, | |
| "loss": 0.3288, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5076142131979695, | |
| "grad_norm": 31.255569458007812, | |
| "learning_rate": 1.7969543147208125e-05, | |
| "loss": 0.1398, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5583756345177665, | |
| "grad_norm": 33.036746978759766, | |
| "learning_rate": 1.7766497461928935e-05, | |
| "loss": 0.1228, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6091370558375635, | |
| "grad_norm": 0.6117672920227051, | |
| "learning_rate": 1.7563451776649745e-05, | |
| "loss": 0.1126, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6598984771573604, | |
| "grad_norm": 1.1897255182266235, | |
| "learning_rate": 1.736040609137056e-05, | |
| "loss": 0.0152, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7106598984771574, | |
| "grad_norm": 438.8088073730469, | |
| "learning_rate": 1.7157360406091373e-05, | |
| "loss": 0.279, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7614213197969543, | |
| "grad_norm": 492.2366638183594, | |
| "learning_rate": 1.6954314720812183e-05, | |
| "loss": 0.5028, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "grad_norm": 0.6856859922409058, | |
| "learning_rate": 1.6751269035532997e-05, | |
| "loss": 0.0962, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8629441624365483, | |
| "grad_norm": 46.26337814331055, | |
| "learning_rate": 1.654822335025381e-05, | |
| "loss": 0.0995, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9137055837563451, | |
| "grad_norm": 52.820518493652344, | |
| "learning_rate": 1.634517766497462e-05, | |
| "loss": 0.2824, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9644670050761421, | |
| "grad_norm": 0.23557256162166595, | |
| "learning_rate": 1.614213197969543e-05, | |
| "loss": 0.0604, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.989247311827957, | |
| "eval_loss": 0.0458565279841423, | |
| "eval_runtime": 18.211, | |
| "eval_samples_per_second": 15.32, | |
| "eval_steps_per_second": 1.922, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.015228426395939, | |
| "grad_norm": 4.585972309112549, | |
| "learning_rate": 1.5939086294416245e-05, | |
| "loss": 0.1812, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0659898477157361, | |
| "grad_norm": 0.8356128931045532, | |
| "learning_rate": 1.573604060913706e-05, | |
| "loss": 0.0418, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.116751269035533, | |
| "grad_norm": 249.66070556640625, | |
| "learning_rate": 1.553299492385787e-05, | |
| "loss": 0.1217, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.16751269035533, | |
| "grad_norm": 131.45016479492188, | |
| "learning_rate": 1.5329949238578682e-05, | |
| "loss": 0.2738, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.218274111675127, | |
| "grad_norm": 0.0076106940396130085, | |
| "learning_rate": 1.5126903553299494e-05, | |
| "loss": 0.0528, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2690355329949239, | |
| "grad_norm": 191.85903930664062, | |
| "learning_rate": 1.4923857868020306e-05, | |
| "loss": 0.096, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.3197969543147208, | |
| "grad_norm": 43.89326477050781, | |
| "learning_rate": 1.4720812182741118e-05, | |
| "loss": 0.1814, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.3705583756345177, | |
| "grad_norm": 0.0087745301425457, | |
| "learning_rate": 1.4517766497461929e-05, | |
| "loss": 0.1263, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4213197969543148, | |
| "grad_norm": 342.1986083984375, | |
| "learning_rate": 1.4314720812182742e-05, | |
| "loss": 0.3518, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.4720812182741116, | |
| "grad_norm": 0.011494699865579605, | |
| "learning_rate": 1.4111675126903554e-05, | |
| "loss": 0.0469, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5228426395939088, | |
| "grad_norm": 0.02110651694238186, | |
| "learning_rate": 1.3908629441624366e-05, | |
| "loss": 0.0432, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5736040609137056, | |
| "grad_norm": 16.259416580200195, | |
| "learning_rate": 1.3705583756345178e-05, | |
| "loss": 0.0037, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6243654822335025, | |
| "grad_norm": 1.5435930490493774, | |
| "learning_rate": 1.3502538071065992e-05, | |
| "loss": 0.0055, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.6751269035532994, | |
| "grad_norm": 0.022236082702875137, | |
| "learning_rate": 1.3299492385786802e-05, | |
| "loss": 0.0251, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7258883248730963, | |
| "grad_norm": 0.002686608349904418, | |
| "learning_rate": 1.3096446700507614e-05, | |
| "loss": 0.0089, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.7766497461928934, | |
| "grad_norm": 0.48235443234443665, | |
| "learning_rate": 1.2893401015228428e-05, | |
| "loss": 0.067, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8274111675126905, | |
| "grad_norm": 0.0026509715244174004, | |
| "learning_rate": 1.269035532994924e-05, | |
| "loss": 0.0734, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.8781725888324874, | |
| "grad_norm": 0.0006726986030116677, | |
| "learning_rate": 1.2487309644670052e-05, | |
| "loss": 0.1744, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.9289340101522843, | |
| "grad_norm": 0.00010891614510910586, | |
| "learning_rate": 1.2284263959390864e-05, | |
| "loss": 0.0148, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.9796954314720812, | |
| "grad_norm": 0.12294577062129974, | |
| "learning_rate": 1.2081218274111678e-05, | |
| "loss": 0.1309, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.985663082437276, | |
| "eval_loss": 0.03369523584842682, | |
| "eval_runtime": 17.3849, | |
| "eval_samples_per_second": 16.048, | |
| "eval_steps_per_second": 2.013, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "grad_norm": 7.998709201812744, | |
| "learning_rate": 1.1878172588832488e-05, | |
| "loss": 0.2421, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.081218274111675, | |
| "grad_norm": 24.342329025268555, | |
| "learning_rate": 1.16751269035533e-05, | |
| "loss": 0.2092, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.1319796954314723, | |
| "grad_norm": 0.0385918989777565, | |
| "learning_rate": 1.1472081218274113e-05, | |
| "loss": 0.1426, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.182741116751269, | |
| "grad_norm": 0.007073443848639727, | |
| "learning_rate": 1.1269035532994925e-05, | |
| "loss": 0.1668, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.233502538071066, | |
| "grad_norm": 0.11695539951324463, | |
| "learning_rate": 1.1065989847715737e-05, | |
| "loss": 0.0358, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.284263959390863, | |
| "grad_norm": 10.85909652709961, | |
| "learning_rate": 1.0862944162436548e-05, | |
| "loss": 0.0129, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.33502538071066, | |
| "grad_norm": 83.56989288330078, | |
| "learning_rate": 1.0659898477157361e-05, | |
| "loss": 0.3374, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.3857868020304567, | |
| "grad_norm": 0.001134849968366325, | |
| "learning_rate": 1.0456852791878173e-05, | |
| "loss": 0.2406, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.436548223350254, | |
| "grad_norm": 0.303134560585022, | |
| "learning_rate": 1.0253807106598985e-05, | |
| "loss": 0.0009, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.487309644670051, | |
| "grad_norm": 1.2032800912857056, | |
| "learning_rate": 1.0050761421319797e-05, | |
| "loss": 0.0209, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.5380710659898478, | |
| "grad_norm": 0.6638129949569702, | |
| "learning_rate": 9.84771573604061e-06, | |
| "loss": 0.0677, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.5888324873096447, | |
| "grad_norm": 0.6139811277389526, | |
| "learning_rate": 9.644670050761421e-06, | |
| "loss": 0.2713, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.6395939086294415, | |
| "grad_norm": 0.042041704058647156, | |
| "learning_rate": 9.441624365482235e-06, | |
| "loss": 0.0177, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.6903553299492384, | |
| "grad_norm": 3578.884765625, | |
| "learning_rate": 9.238578680203047e-06, | |
| "loss": 0.1765, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.7411167512690353, | |
| "grad_norm": 0.800250232219696, | |
| "learning_rate": 9.035532994923859e-06, | |
| "loss": 0.0518, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.7918781725888326, | |
| "grad_norm": 0.12552772462368011, | |
| "learning_rate": 8.832487309644671e-06, | |
| "loss": 0.1098, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.8426395939086295, | |
| "grad_norm": 0.003844466060400009, | |
| "learning_rate": 8.629441624365483e-06, | |
| "loss": 0.1961, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.8934010152284264, | |
| "grad_norm": 0.0007168629672378302, | |
| "learning_rate": 8.426395939086295e-06, | |
| "loss": 0.0309, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.9441624365482233, | |
| "grad_norm": 0.20322203636169434, | |
| "learning_rate": 8.223350253807107e-06, | |
| "loss": 0.0921, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.99492385786802, | |
| "grad_norm": 0.010694732889533043, | |
| "learning_rate": 8.020304568527919e-06, | |
| "loss": 0.3207, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.978494623655914, | |
| "eval_loss": 0.12610773742198944, | |
| "eval_runtime": 16.6863, | |
| "eval_samples_per_second": 16.72, | |
| "eval_steps_per_second": 2.098, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 3.045685279187817, | |
| "grad_norm": 0.023461902514100075, | |
| "learning_rate": 7.817258883248731e-06, | |
| "loss": 0.2357, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.0964467005076144, | |
| "grad_norm": 0.19518044590950012, | |
| "learning_rate": 7.614213197969543e-06, | |
| "loss": 0.0022, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.1472081218274113, | |
| "grad_norm": 0.00014897708024363965, | |
| "learning_rate": 7.411167512690356e-06, | |
| "loss": 0.0005, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.197969543147208, | |
| "grad_norm": 294.190673828125, | |
| "learning_rate": 7.208121827411169e-06, | |
| "loss": 0.0252, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.248730964467005, | |
| "grad_norm": 0.00014258331793826073, | |
| "learning_rate": 7.0050761421319806e-06, | |
| "loss": 0.0231, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.299492385786802, | |
| "grad_norm": 0.006024135742336512, | |
| "learning_rate": 6.8020304568527926e-06, | |
| "loss": 0.1952, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.350253807106599, | |
| "grad_norm": 215.45094299316406, | |
| "learning_rate": 6.5989847715736045e-06, | |
| "loss": 0.175, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.401015228426396, | |
| "grad_norm": 0.15660379827022552, | |
| "learning_rate": 6.395939086294417e-06, | |
| "loss": 0.113, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.451776649746193, | |
| "grad_norm": 0.0003182363579981029, | |
| "learning_rate": 6.1928934010152285e-06, | |
| "loss": 0.3483, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.50253807106599, | |
| "grad_norm": 0.0007056689355522394, | |
| "learning_rate": 5.989847715736041e-06, | |
| "loss": 0.2458, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.553299492385787, | |
| "grad_norm": 313.6507263183594, | |
| "learning_rate": 5.7868020304568525e-06, | |
| "loss": 0.1121, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.6040609137055837, | |
| "grad_norm": 0.08964172750711441, | |
| "learning_rate": 5.583756345177665e-06, | |
| "loss": 0.0019, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.6548223350253806, | |
| "grad_norm": 0.05380258709192276, | |
| "learning_rate": 5.380710659898477e-06, | |
| "loss": 0.0163, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.7055837563451774, | |
| "grad_norm": 261.12548828125, | |
| "learning_rate": 5.17766497461929e-06, | |
| "loss": 0.1856, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.7563451776649748, | |
| "grad_norm": 0.021219402551651, | |
| "learning_rate": 4.974619289340102e-06, | |
| "loss": 0.1741, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.8071065989847717, | |
| "grad_norm": 0.006986899767071009, | |
| "learning_rate": 4.771573604060914e-06, | |
| "loss": 0.2666, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.8578680203045685, | |
| "grad_norm": 0.3382449746131897, | |
| "learning_rate": 4.568527918781726e-06, | |
| "loss": 0.0107, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.9086294416243654, | |
| "grad_norm": 6.089676026022062e-05, | |
| "learning_rate": 4.365482233502538e-06, | |
| "loss": 0.1188, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.9593908629441623, | |
| "grad_norm": 0.06970903277397156, | |
| "learning_rate": 4.162436548223351e-06, | |
| "loss": 0.2517, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.992831541218638, | |
| "eval_loss": 0.04906105622649193, | |
| "eval_runtime": 17.0919, | |
| "eval_samples_per_second": 16.323, | |
| "eval_steps_per_second": 2.048, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 4.01015228426396, | |
| "grad_norm": 0.7618089914321899, | |
| "learning_rate": 3.959390862944163e-06, | |
| "loss": 0.1249, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.060913705583756, | |
| "grad_norm": 0.11002158373594284, | |
| "learning_rate": 3.756345177664975e-06, | |
| "loss": 0.0001, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.111675126903553, | |
| "grad_norm": 0.009345640428364277, | |
| "learning_rate": 3.5532994923857873e-06, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.16243654822335, | |
| "grad_norm": 0.0008610596996732056, | |
| "learning_rate": 3.3502538071065993e-06, | |
| "loss": 0.1807, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.213197969543147, | |
| "grad_norm": 0.0372774712741375, | |
| "learning_rate": 3.1472081218274113e-06, | |
| "loss": 0.0744, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.2639593908629445, | |
| "grad_norm": 0.026972278952598572, | |
| "learning_rate": 2.9441624365482237e-06, | |
| "loss": 0.0216, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.314720812182741, | |
| "grad_norm": 0.14636941254138947, | |
| "learning_rate": 2.7411167512690357e-06, | |
| "loss": 0.0692, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.365482233502538, | |
| "grad_norm": 225.23846435546875, | |
| "learning_rate": 2.5380710659898476e-06, | |
| "loss": 0.2541, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.416243654822335, | |
| "grad_norm": 0.1878076195716858, | |
| "learning_rate": 2.33502538071066e-06, | |
| "loss": 0.0001, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.467005076142132, | |
| "grad_norm": 0.011137721128761768, | |
| "learning_rate": 2.1319796954314725e-06, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.517766497461929, | |
| "grad_norm": 8.737370808376e-05, | |
| "learning_rate": 1.9289340101522844e-06, | |
| "loss": 0.0004, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.568527918781726, | |
| "grad_norm": 0.0015903498278930783, | |
| "learning_rate": 1.7258883248730964e-06, | |
| "loss": 0.2335, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.619289340101523, | |
| "grad_norm": 0.02763758972287178, | |
| "learning_rate": 1.5228426395939088e-06, | |
| "loss": 0.0003, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.67005076142132, | |
| "grad_norm": 0.4715072214603424, | |
| "learning_rate": 1.319796954314721e-06, | |
| "loss": 0.2327, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.720812182741117, | |
| "grad_norm": 0.11949143558740616, | |
| "learning_rate": 1.116751269035533e-06, | |
| "loss": 0.0734, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.771573604060913, | |
| "grad_norm": 362.79876708984375, | |
| "learning_rate": 9.137055837563452e-07, | |
| "loss": 0.0735, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.822335025380711, | |
| "grad_norm": 0.0028335938695818186, | |
| "learning_rate": 7.106598984771574e-07, | |
| "loss": 0.2299, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.873096446700508, | |
| "grad_norm": 0.015159722417593002, | |
| "learning_rate": 5.076142131979696e-07, | |
| "loss": 0.0003, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.9238578680203045, | |
| "grad_norm": 0.07444437593221664, | |
| "learning_rate": 3.0456852791878176e-07, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.974619289340102, | |
| "grad_norm": 0.0017945471918210387, | |
| "learning_rate": 1.0152284263959391e-07, | |
| "loss": 0.1549, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.996415770609319, | |
| "eval_loss": 0.04717279225587845, | |
| "eval_runtime": 17.0835, | |
| "eval_samples_per_second": 16.332, | |
| "eval_steps_per_second": 2.049, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 985, | |
| "total_flos": 1.814619221089321e+18, | |
| "train_loss": 0.15722184067514908, | |
| "train_runtime": 1696.7849, | |
| "train_samples_per_second": 4.644, | |
| "train_steps_per_second": 0.581 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 985, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.814619221089321e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |