| { | |
| "best_global_step": 5000, | |
| "best_metric": 78.11993940343729, | |
| "best_model_checkpoint": "./working_area/output_model/checkpoint-5000", | |
| "epoch": 0.30233401862377557, | |
| "eval_steps": 1000, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015116700931188777, | |
| "grad_norm": 10.39171028137207, | |
| "learning_rate": 4.800000000000001e-07, | |
| "loss": 0.2719, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0030233401862377555, | |
| "grad_norm": 0.3984987735748291, | |
| "learning_rate": 9.800000000000001e-07, | |
| "loss": 0.0431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004535010279356633, | |
| "grad_norm": 0.2931273877620697, | |
| "learning_rate": 1.48e-06, | |
| "loss": 0.0297, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006046680372475511, | |
| "grad_norm": 0.24546289443969727, | |
| "learning_rate": 1.98e-06, | |
| "loss": 0.027, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007558350465594389, | |
| "grad_norm": 0.2551668584346771, | |
| "learning_rate": 2.4800000000000004e-06, | |
| "loss": 0.0264, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.009070020558713266, | |
| "grad_norm": 0.22325266897678375, | |
| "learning_rate": 2.9800000000000003e-06, | |
| "loss": 0.0258, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010581690651832143, | |
| "grad_norm": 0.2603906989097595, | |
| "learning_rate": 3.48e-06, | |
| "loss": 0.0249, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.012093360744951022, | |
| "grad_norm": 0.24611017107963562, | |
| "learning_rate": 3.980000000000001e-06, | |
| "loss": 0.0246, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.013605030838069899, | |
| "grad_norm": 0.26433423161506653, | |
| "learning_rate": 4.48e-06, | |
| "loss": 0.0262, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.015116700931188777, | |
| "grad_norm": 0.2509951889514923, | |
| "learning_rate": 4.980000000000001e-06, | |
| "loss": 0.0263, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.016628371024307656, | |
| "grad_norm": 0.268083393573761, | |
| "learning_rate": 5.480000000000001e-06, | |
| "loss": 0.0255, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.018140041117426533, | |
| "grad_norm": 0.2258174866437912, | |
| "learning_rate": 5.98e-06, | |
| "loss": 0.0253, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01965171121054541, | |
| "grad_norm": 0.24694132804870605, | |
| "learning_rate": 6.480000000000001e-06, | |
| "loss": 0.024, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.021163381303664287, | |
| "grad_norm": 0.24790944159030914, | |
| "learning_rate": 6.98e-06, | |
| "loss": 0.0256, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.022675051396783167, | |
| "grad_norm": 0.25042369961738586, | |
| "learning_rate": 7.48e-06, | |
| "loss": 0.0251, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.024186721489902044, | |
| "grad_norm": 0.2964789569377899, | |
| "learning_rate": 7.980000000000002e-06, | |
| "loss": 0.026, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02569839158302092, | |
| "grad_norm": 0.2886582016944885, | |
| "learning_rate": 8.48e-06, | |
| "loss": 0.0261, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.027210061676139798, | |
| "grad_norm": 0.24788400530815125, | |
| "learning_rate": 8.98e-06, | |
| "loss": 0.0244, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.028721731769258678, | |
| "grad_norm": 0.25503554940223694, | |
| "learning_rate": 9.48e-06, | |
| "loss": 0.0237, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.030233401862377555, | |
| "grad_norm": 0.24687393009662628, | |
| "learning_rate": 9.980000000000001e-06, | |
| "loss": 0.0246, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03174507195549643, | |
| "grad_norm": 0.2741446793079376, | |
| "learning_rate": 9.946666666666667e-06, | |
| "loss": 0.0254, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.03325674204861531, | |
| "grad_norm": 0.25302210450172424, | |
| "learning_rate": 9.891111111111113e-06, | |
| "loss": 0.0241, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.034768412141734185, | |
| "grad_norm": 0.24115385115146637, | |
| "learning_rate": 9.835555555555556e-06, | |
| "loss": 0.025, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.036280082234853066, | |
| "grad_norm": 0.24566683173179626, | |
| "learning_rate": 9.780000000000001e-06, | |
| "loss": 0.0241, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.037791752327971946, | |
| "grad_norm": 0.21123534440994263, | |
| "learning_rate": 9.724444444444445e-06, | |
| "loss": 0.0238, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.03930342242109082, | |
| "grad_norm": 0.23343868553638458, | |
| "learning_rate": 9.66888888888889e-06, | |
| "loss": 0.0234, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.0408150925142097, | |
| "grad_norm": 0.28975582122802734, | |
| "learning_rate": 9.613333333333335e-06, | |
| "loss": 0.0229, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.04232676260732857, | |
| "grad_norm": 0.24031095206737518, | |
| "learning_rate": 9.557777777777777e-06, | |
| "loss": 0.0236, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.043838432700447454, | |
| "grad_norm": 0.29754847288131714, | |
| "learning_rate": 9.502222222222223e-06, | |
| "loss": 0.0235, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.045350102793566334, | |
| "grad_norm": 0.25962579250335693, | |
| "learning_rate": 9.446666666666667e-06, | |
| "loss": 0.0242, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.04686177288668521, | |
| "grad_norm": 0.2572610378265381, | |
| "learning_rate": 9.391111111111111e-06, | |
| "loss": 0.0233, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.04837344297980409, | |
| "grad_norm": 0.24092882871627808, | |
| "learning_rate": 9.335555555555557e-06, | |
| "loss": 0.0227, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.04988511307292297, | |
| "grad_norm": 0.23399066925048828, | |
| "learning_rate": 9.280000000000001e-06, | |
| "loss": 0.0239, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.05139678316604184, | |
| "grad_norm": 0.26382818818092346, | |
| "learning_rate": 9.224444444444445e-06, | |
| "loss": 0.0233, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.05290845325916072, | |
| "grad_norm": 0.25903263688087463, | |
| "learning_rate": 9.168888888888889e-06, | |
| "loss": 0.0237, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.054420123352279595, | |
| "grad_norm": 0.21435964107513428, | |
| "learning_rate": 9.113333333333335e-06, | |
| "loss": 0.0224, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.055931793445398476, | |
| "grad_norm": 0.23641858994960785, | |
| "learning_rate": 9.057777777777779e-06, | |
| "loss": 0.0217, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.057443463538517356, | |
| "grad_norm": 0.24842330813407898, | |
| "learning_rate": 9.002222222222223e-06, | |
| "loss": 0.0234, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.05895513363163623, | |
| "grad_norm": 0.2286524474620819, | |
| "learning_rate": 8.946666666666669e-06, | |
| "loss": 0.0228, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.06046680372475511, | |
| "grad_norm": 0.24313467741012573, | |
| "learning_rate": 8.891111111111111e-06, | |
| "loss": 0.0219, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06046680372475511, | |
| "eval_loss": 0.02475658990442753, | |
| "eval_runtime": 12970.4314, | |
| "eval_samples_per_second": 8.844, | |
| "eval_steps_per_second": 0.553, | |
| "eval_wer": 81.0296191819464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06197847381787399, | |
| "grad_norm": 0.21169662475585938, | |
| "learning_rate": 8.835555555555557e-06, | |
| "loss": 0.023, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.06349014391099286, | |
| "grad_norm": 0.2406071424484253, | |
| "learning_rate": 8.78e-06, | |
| "loss": 0.0235, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.06500181400411174, | |
| "grad_norm": 0.23690740764141083, | |
| "learning_rate": 8.724444444444445e-06, | |
| "loss": 0.0223, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.06651348409723062, | |
| "grad_norm": 0.2665939927101135, | |
| "learning_rate": 8.66888888888889e-06, | |
| "loss": 0.0223, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.0680251541903495, | |
| "grad_norm": 0.26822060346603394, | |
| "learning_rate": 8.613333333333333e-06, | |
| "loss": 0.0229, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.06953682428346837, | |
| "grad_norm": 0.23397238552570343, | |
| "learning_rate": 8.557777777777778e-06, | |
| "loss": 0.0217, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.07104849437658725, | |
| "grad_norm": 0.24292343854904175, | |
| "learning_rate": 8.502222222222223e-06, | |
| "loss": 0.0237, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.07256016446970613, | |
| "grad_norm": 0.21283379197120667, | |
| "learning_rate": 8.446666666666668e-06, | |
| "loss": 0.0229, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.07407183456282501, | |
| "grad_norm": 0.28053444623947144, | |
| "learning_rate": 8.391111111111112e-06, | |
| "loss": 0.0245, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.07558350465594389, | |
| "grad_norm": 0.24319562315940857, | |
| "learning_rate": 8.335555555555556e-06, | |
| "loss": 0.0222, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.07709517474906276, | |
| "grad_norm": 0.23033973574638367, | |
| "learning_rate": 8.28e-06, | |
| "loss": 0.0216, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.07860684484218164, | |
| "grad_norm": 0.2720530927181244, | |
| "learning_rate": 8.224444444444444e-06, | |
| "loss": 0.023, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.08011851493530052, | |
| "grad_norm": 0.27409815788269043, | |
| "learning_rate": 8.16888888888889e-06, | |
| "loss": 0.0228, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.0816301850284194, | |
| "grad_norm": 0.28669819235801697, | |
| "learning_rate": 8.113333333333334e-06, | |
| "loss": 0.0228, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.08314185512153828, | |
| "grad_norm": 0.24168507754802704, | |
| "learning_rate": 8.057777777777778e-06, | |
| "loss": 0.0233, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.08465352521465715, | |
| "grad_norm": 0.2719112038612366, | |
| "learning_rate": 8.002222222222222e-06, | |
| "loss": 0.0211, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.08616519530777603, | |
| "grad_norm": 0.2333834171295166, | |
| "learning_rate": 7.946666666666666e-06, | |
| "loss": 0.0222, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.08767686540089491, | |
| "grad_norm": 0.2352941334247589, | |
| "learning_rate": 7.891111111111112e-06, | |
| "loss": 0.0228, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.08918853549401379, | |
| "grad_norm": 0.258932888507843, | |
| "learning_rate": 7.835555555555556e-06, | |
| "loss": 0.0229, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.09070020558713267, | |
| "grad_norm": 0.23196369409561157, | |
| "learning_rate": 7.78e-06, | |
| "loss": 0.0218, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09221187568025155, | |
| "grad_norm": 0.24886886775493622, | |
| "learning_rate": 7.724444444444446e-06, | |
| "loss": 0.0224, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.09372354577337041, | |
| "grad_norm": 0.2534898817539215, | |
| "learning_rate": 7.66888888888889e-06, | |
| "loss": 0.0213, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.0952352158664893, | |
| "grad_norm": 0.24856404960155487, | |
| "learning_rate": 7.613333333333334e-06, | |
| "loss": 0.0217, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.09674688595960818, | |
| "grad_norm": 0.2615777552127838, | |
| "learning_rate": 7.557777777777779e-06, | |
| "loss": 0.0209, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.09825855605272706, | |
| "grad_norm": 0.293625146150589, | |
| "learning_rate": 7.502222222222223e-06, | |
| "loss": 0.0232, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.09977022614584594, | |
| "grad_norm": 0.21186749637126923, | |
| "learning_rate": 7.446666666666668e-06, | |
| "loss": 0.0214, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.1012818962389648, | |
| "grad_norm": 0.2184201329946518, | |
| "learning_rate": 7.3911111111111125e-06, | |
| "loss": 0.0226, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.10279356633208368, | |
| "grad_norm": 0.23249119520187378, | |
| "learning_rate": 7.335555555555556e-06, | |
| "loss": 0.0229, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.10430523642520256, | |
| "grad_norm": 0.23204003274440765, | |
| "learning_rate": 7.280000000000001e-06, | |
| "loss": 0.022, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.10581690651832144, | |
| "grad_norm": 0.23885048925876617, | |
| "learning_rate": 7.224444444444445e-06, | |
| "loss": 0.0223, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.10732857661144032, | |
| "grad_norm": 0.2814381718635559, | |
| "learning_rate": 7.1688888888888895e-06, | |
| "loss": 0.0213, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.10884024670455919, | |
| "grad_norm": 0.21481429040431976, | |
| "learning_rate": 7.113333333333334e-06, | |
| "loss": 0.0209, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.11035191679767807, | |
| "grad_norm": 0.3092924654483795, | |
| "learning_rate": 7.057777777777778e-06, | |
| "loss": 0.0237, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.11186358689079695, | |
| "grad_norm": 0.25033241510391235, | |
| "learning_rate": 7.0022222222222225e-06, | |
| "loss": 0.0212, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.11337525698391583, | |
| "grad_norm": 0.20690016448497772, | |
| "learning_rate": 6.946666666666667e-06, | |
| "loss": 0.0226, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.11488692707703471, | |
| "grad_norm": 0.216666117310524, | |
| "learning_rate": 6.891111111111111e-06, | |
| "loss": 0.0225, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.11639859717015359, | |
| "grad_norm": 0.2532588243484497, | |
| "learning_rate": 6.835555555555556e-06, | |
| "loss": 0.0219, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.11791026726327246, | |
| "grad_norm": 0.23438499867916107, | |
| "learning_rate": 6.780000000000001e-06, | |
| "loss": 0.0215, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.11942193735639134, | |
| "grad_norm": 0.2752824127674103, | |
| "learning_rate": 6.724444444444444e-06, | |
| "loss": 0.0216, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.12093360744951022, | |
| "grad_norm": 0.2573551535606384, | |
| "learning_rate": 6.668888888888889e-06, | |
| "loss": 0.0217, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.12093360744951022, | |
| "eval_loss": 0.023528048768639565, | |
| "eval_runtime": 13684.2124, | |
| "eval_samples_per_second": 8.383, | |
| "eval_steps_per_second": 0.524, | |
| "eval_wer": 79.85773738006931, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1224452775426291, | |
| "grad_norm": 0.19551323354244232, | |
| "learning_rate": 6.613333333333334e-06, | |
| "loss": 0.0209, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.12395694763574798, | |
| "grad_norm": 0.24706204235553741, | |
| "learning_rate": 6.557777777777778e-06, | |
| "loss": 0.0215, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.12546861772886686, | |
| "grad_norm": 0.23044320940971375, | |
| "learning_rate": 6.502222222222223e-06, | |
| "loss": 0.0225, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.12698028782198573, | |
| "grad_norm": 0.23613490164279938, | |
| "learning_rate": 6.446666666666668e-06, | |
| "loss": 0.021, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.12849195791510462, | |
| "grad_norm": 0.21719467639923096, | |
| "learning_rate": 6.391111111111111e-06, | |
| "loss": 0.0221, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.1300036280082235, | |
| "grad_norm": 0.22605890035629272, | |
| "learning_rate": 6.335555555555556e-06, | |
| "loss": 0.0212, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.13151529810134235, | |
| "grad_norm": 0.27460452914237976, | |
| "learning_rate": 6.280000000000001e-06, | |
| "loss": 0.0241, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.13302696819446125, | |
| "grad_norm": 0.26805680990219116, | |
| "learning_rate": 6.224444444444445e-06, | |
| "loss": 0.0215, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.13453863828758011, | |
| "grad_norm": 0.2031622678041458, | |
| "learning_rate": 6.16888888888889e-06, | |
| "loss": 0.0211, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.136050308380699, | |
| "grad_norm": 0.33984532952308655, | |
| "learning_rate": 6.113333333333333e-06, | |
| "loss": 0.0217, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.13756197847381788, | |
| "grad_norm": 0.2332555651664734, | |
| "learning_rate": 6.057777777777778e-06, | |
| "loss": 0.0213, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.13907364856693674, | |
| "grad_norm": 0.2189512699842453, | |
| "learning_rate": 6.002222222222223e-06, | |
| "loss": 0.0212, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.14058531866005564, | |
| "grad_norm": 0.21263238787651062, | |
| "learning_rate": 5.946666666666668e-06, | |
| "loss": 0.0224, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.1420969887531745, | |
| "grad_norm": 0.23778782784938812, | |
| "learning_rate": 5.891111111111112e-06, | |
| "loss": 0.0233, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.1436086588462934, | |
| "grad_norm": 0.2161298543214798, | |
| "learning_rate": 5.8355555555555565e-06, | |
| "loss": 0.0222, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.14512032893941226, | |
| "grad_norm": 0.22459618747234344, | |
| "learning_rate": 5.78e-06, | |
| "loss": 0.0216, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.14663199903253113, | |
| "grad_norm": 0.24907240271568298, | |
| "learning_rate": 5.724444444444445e-06, | |
| "loss": 0.0217, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.14814366912565002, | |
| "grad_norm": 0.2513597011566162, | |
| "learning_rate": 5.6688888888888895e-06, | |
| "loss": 0.0218, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.1496553392187689, | |
| "grad_norm": 0.2687082588672638, | |
| "learning_rate": 5.613333333333334e-06, | |
| "loss": 0.0227, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.15116700931188778, | |
| "grad_norm": 0.22070540487766266, | |
| "learning_rate": 5.557777777777778e-06, | |
| "loss": 0.0223, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.15267867940500665, | |
| "grad_norm": 0.2508254945278168, | |
| "learning_rate": 5.5022222222222224e-06, | |
| "loss": 0.0205, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.15419034949812552, | |
| "grad_norm": 0.22595292329788208, | |
| "learning_rate": 5.4466666666666665e-06, | |
| "loss": 0.0217, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.1557020195912444, | |
| "grad_norm": 0.2362944632768631, | |
| "learning_rate": 5.391111111111111e-06, | |
| "loss": 0.0216, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.15721368968436328, | |
| "grad_norm": 0.2035423070192337, | |
| "learning_rate": 5.335555555555556e-06, | |
| "loss": 0.0206, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.15872535977748217, | |
| "grad_norm": 0.22915472090244293, | |
| "learning_rate": 5.28e-06, | |
| "loss": 0.0208, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.16023702987060104, | |
| "grad_norm": 0.20232254266738892, | |
| "learning_rate": 5.224444444444445e-06, | |
| "loss": 0.0214, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.1617486999637199, | |
| "grad_norm": 0.21948222815990448, | |
| "learning_rate": 5.168888888888889e-06, | |
| "loss": 0.0208, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.1632603700568388, | |
| "grad_norm": 0.2563857138156891, | |
| "learning_rate": 5.113333333333333e-06, | |
| "loss": 0.0207, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.16477204014995767, | |
| "grad_norm": 0.2101213037967682, | |
| "learning_rate": 5.057777777777778e-06, | |
| "loss": 0.0201, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.16628371024307656, | |
| "grad_norm": 0.2433857023715973, | |
| "learning_rate": 5.002222222222223e-06, | |
| "loss": 0.021, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.16779538033619543, | |
| "grad_norm": 0.21939025819301605, | |
| "learning_rate": 4.946666666666667e-06, | |
| "loss": 0.0228, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.1693070504293143, | |
| "grad_norm": 0.21120359003543854, | |
| "learning_rate": 4.891111111111111e-06, | |
| "loss": 0.0225, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.1708187205224332, | |
| "grad_norm": 0.19768129289150238, | |
| "learning_rate": 4.835555555555556e-06, | |
| "loss": 0.0206, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.17233039061555205, | |
| "grad_norm": 0.2555268704891205, | |
| "learning_rate": 4.78e-06, | |
| "loss": 0.0217, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.17384206070867095, | |
| "grad_norm": 0.2393975704908371, | |
| "learning_rate": 4.724444444444445e-06, | |
| "loss": 0.0204, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.17535373080178981, | |
| "grad_norm": 0.23027943074703217, | |
| "learning_rate": 4.66888888888889e-06, | |
| "loss": 0.0214, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.1768654008949087, | |
| "grad_norm": 0.2525699734687805, | |
| "learning_rate": 4.613333333333334e-06, | |
| "loss": 0.0206, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.17837707098802758, | |
| "grad_norm": 0.2413048893213272, | |
| "learning_rate": 4.557777777777778e-06, | |
| "loss": 0.0189, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.17988874108114644, | |
| "grad_norm": 0.2660181224346161, | |
| "learning_rate": 4.502222222222223e-06, | |
| "loss": 0.0214, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.18140041117426534, | |
| "grad_norm": 0.21868810057640076, | |
| "learning_rate": 4.446666666666667e-06, | |
| "loss": 0.0221, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.18140041117426534, | |
| "eval_loss": 0.02285671979188919, | |
| "eval_runtime": 14051.4519, | |
| "eval_samples_per_second": 8.164, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 79.02540528304515, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.1829120812673842, | |
| "grad_norm": 0.23031719028949738, | |
| "learning_rate": 4.391111111111112e-06, | |
| "loss": 0.0206, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.1844237513605031, | |
| "grad_norm": 0.26470455527305603, | |
| "learning_rate": 4.3355555555555565e-06, | |
| "loss": 0.021, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.18593542145362196, | |
| "grad_norm": 0.2614658772945404, | |
| "learning_rate": 4.2800000000000005e-06, | |
| "loss": 0.0213, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.18744709154674083, | |
| "grad_norm": 0.2713329792022705, | |
| "learning_rate": 4.2244444444444446e-06, | |
| "loss": 0.0207, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.18895876163985972, | |
| "grad_norm": 0.20872850716114044, | |
| "learning_rate": 4.168888888888889e-06, | |
| "loss": 0.0216, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.1904704317329786, | |
| "grad_norm": 0.22996503114700317, | |
| "learning_rate": 4.1133333333333335e-06, | |
| "loss": 0.0219, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.19198210182609748, | |
| "grad_norm": 0.23216116428375244, | |
| "learning_rate": 4.057777777777778e-06, | |
| "loss": 0.0209, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.19349377191921635, | |
| "grad_norm": 0.22368553280830383, | |
| "learning_rate": 4.002222222222222e-06, | |
| "loss": 0.0195, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.19500544201233522, | |
| "grad_norm": 0.2579832971096039, | |
| "learning_rate": 3.946666666666667e-06, | |
| "loss": 0.0205, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.1965171121054541, | |
| "grad_norm": 0.21672658622264862, | |
| "learning_rate": 3.891111111111111e-06, | |
| "loss": 0.0214, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.19802878219857298, | |
| "grad_norm": 0.2356463521718979, | |
| "learning_rate": 3.835555555555555e-06, | |
| "loss": 0.0199, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.19954045229169187, | |
| "grad_norm": 0.240219384431839, | |
| "learning_rate": 3.7800000000000002e-06, | |
| "loss": 0.0203, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.20105212238481074, | |
| "grad_norm": 0.20598304271697998, | |
| "learning_rate": 3.724444444444445e-06, | |
| "loss": 0.0218, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.2025637924779296, | |
| "grad_norm": 0.21276068687438965, | |
| "learning_rate": 3.668888888888889e-06, | |
| "loss": 0.0202, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.2040754625710485, | |
| "grad_norm": 0.234477698802948, | |
| "learning_rate": 3.6133333333333336e-06, | |
| "loss": 0.0213, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.20558713266416737, | |
| "grad_norm": 0.22812841832637787, | |
| "learning_rate": 3.5577777777777785e-06, | |
| "loss": 0.0193, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.20709880275728626, | |
| "grad_norm": 0.2191910743713379, | |
| "learning_rate": 3.5022222222222225e-06, | |
| "loss": 0.0218, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 0.20861047285040513, | |
| "grad_norm": 0.21586079895496368, | |
| "learning_rate": 3.446666666666667e-06, | |
| "loss": 0.022, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.210122142943524, | |
| "grad_norm": 0.29229211807250977, | |
| "learning_rate": 3.391111111111111e-06, | |
| "loss": 0.0221, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 0.2116338130366429, | |
| "grad_norm": 0.2535618245601654, | |
| "learning_rate": 3.335555555555556e-06, | |
| "loss": 0.0209, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.21314548312976175, | |
| "grad_norm": 0.23379455506801605, | |
| "learning_rate": 3.2800000000000004e-06, | |
| "loss": 0.0215, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 0.21465715322288065, | |
| "grad_norm": 0.20163771510124207, | |
| "learning_rate": 3.2244444444444444e-06, | |
| "loss": 0.0197, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.21616882331599951, | |
| "grad_norm": 0.22687122225761414, | |
| "learning_rate": 3.1688888888888893e-06, | |
| "loss": 0.0202, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 0.21768049340911838, | |
| "grad_norm": 0.2215571254491806, | |
| "learning_rate": 3.1133333333333337e-06, | |
| "loss": 0.0213, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.21919216350223727, | |
| "grad_norm": 0.25743547081947327, | |
| "learning_rate": 3.0577777777777778e-06, | |
| "loss": 0.0194, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 0.22070383359535614, | |
| "grad_norm": 0.23957869410514832, | |
| "learning_rate": 3.0022222222222227e-06, | |
| "loss": 0.02, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.22221550368847504, | |
| "grad_norm": 0.24700717628002167, | |
| "learning_rate": 2.946666666666667e-06, | |
| "loss": 0.0212, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 0.2237271737815939, | |
| "grad_norm": 0.2590341567993164, | |
| "learning_rate": 2.891111111111111e-06, | |
| "loss": 0.02, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.2252388438747128, | |
| "grad_norm": 0.2064068615436554, | |
| "learning_rate": 2.835555555555556e-06, | |
| "loss": 0.0212, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 0.22675051396783166, | |
| "grad_norm": 0.25424307584762573, | |
| "learning_rate": 2.7800000000000005e-06, | |
| "loss": 0.022, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.22826218406095053, | |
| "grad_norm": 0.25873327255249023, | |
| "learning_rate": 2.7244444444444445e-06, | |
| "loss": 0.0211, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 0.22977385415406942, | |
| "grad_norm": 0.2244931161403656, | |
| "learning_rate": 2.6688888888888894e-06, | |
| "loss": 0.021, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.2312855242471883, | |
| "grad_norm": 0.23963423073291779, | |
| "learning_rate": 2.6133333333333334e-06, | |
| "loss": 0.0207, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 0.23279719434030718, | |
| "grad_norm": 0.22690649330615997, | |
| "learning_rate": 2.557777777777778e-06, | |
| "loss": 0.0207, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.23430886443342605, | |
| "grad_norm": 0.19450053572654724, | |
| "learning_rate": 2.5022222222222224e-06, | |
| "loss": 0.0191, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 0.23582053452654492, | |
| "grad_norm": 0.23574170470237732, | |
| "learning_rate": 2.446666666666667e-06, | |
| "loss": 0.0206, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.2373322046196638, | |
| "grad_norm": 0.21273107826709747, | |
| "learning_rate": 2.3911111111111113e-06, | |
| "loss": 0.0198, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 0.23884387471278268, | |
| "grad_norm": 0.20970465242862701, | |
| "learning_rate": 2.3355555555555557e-06, | |
| "loss": 0.0191, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.24035554480590157, | |
| "grad_norm": 0.2582346796989441, | |
| "learning_rate": 2.28e-06, | |
| "loss": 0.0223, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 0.24186721489902044, | |
| "grad_norm": 0.25113871693611145, | |
| "learning_rate": 2.2244444444444447e-06, | |
| "loss": 0.0213, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.24186721489902044, | |
| "eval_loss": 0.022349417209625244, | |
| "eval_runtime": 12773.0468, | |
| "eval_samples_per_second": 8.981, | |
| "eval_steps_per_second": 0.561, | |
| "eval_wer": 78.43598182103119, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2433788849921393, | |
| "grad_norm": 0.21822433173656464, | |
| "learning_rate": 2.168888888888889e-06, | |
| "loss": 0.0204, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 0.2448905550852582, | |
| "grad_norm": 0.2285871058702469, | |
| "learning_rate": 2.1133333333333336e-06, | |
| "loss": 0.0203, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.24640222517837707, | |
| "grad_norm": 0.28536123037338257, | |
| "learning_rate": 2.057777777777778e-06, | |
| "loss": 0.0217, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 0.24791389527149596, | |
| "grad_norm": 0.24871906638145447, | |
| "learning_rate": 2.0022222222222225e-06, | |
| "loss": 0.0212, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.24942556536461483, | |
| "grad_norm": 0.23168586194515228, | |
| "learning_rate": 1.9466666666666665e-06, | |
| "loss": 0.0194, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 0.2509372354577337, | |
| "grad_norm": 0.26161977648735046, | |
| "learning_rate": 1.8911111111111114e-06, | |
| "loss": 0.0209, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.2524489055508526, | |
| "grad_norm": 0.23529359698295593, | |
| "learning_rate": 1.8355555555555557e-06, | |
| "loss": 0.02, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 0.25396057564397145, | |
| "grad_norm": 0.2294083535671234, | |
| "learning_rate": 1.7800000000000001e-06, | |
| "loss": 0.0196, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.2554722457370903, | |
| "grad_norm": 0.237132266163826, | |
| "learning_rate": 1.7244444444444448e-06, | |
| "loss": 0.0203, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 0.25698391583020924, | |
| "grad_norm": 0.2331571727991104, | |
| "learning_rate": 1.668888888888889e-06, | |
| "loss": 0.0203, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.2584955859233281, | |
| "grad_norm": 0.22561855614185333, | |
| "learning_rate": 1.6133333333333335e-06, | |
| "loss": 0.0192, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 0.260007256016447, | |
| "grad_norm": 0.22706526517868042, | |
| "learning_rate": 1.5577777777777777e-06, | |
| "loss": 0.0209, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.26151892610956584, | |
| "grad_norm": 0.21990585327148438, | |
| "learning_rate": 1.5022222222222224e-06, | |
| "loss": 0.0203, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 0.2630305962026847, | |
| "grad_norm": 0.21273785829544067, | |
| "learning_rate": 1.4466666666666669e-06, | |
| "loss": 0.0196, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.26454226629580363, | |
| "grad_norm": 0.232136532664299, | |
| "learning_rate": 1.3911111111111111e-06, | |
| "loss": 0.0198, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 0.2660539363889225, | |
| "grad_norm": 0.21890687942504883, | |
| "learning_rate": 1.3355555555555558e-06, | |
| "loss": 0.0211, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.26756560648204136, | |
| "grad_norm": 0.2208709567785263, | |
| "learning_rate": 1.28e-06, | |
| "loss": 0.0213, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 0.26907727657516023, | |
| "grad_norm": 0.20006310939788818, | |
| "learning_rate": 1.2244444444444445e-06, | |
| "loss": 0.0197, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.2705889466682791, | |
| "grad_norm": 0.20703347027301788, | |
| "learning_rate": 1.168888888888889e-06, | |
| "loss": 0.02, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 0.272100616761398, | |
| "grad_norm": 0.24182920157909393, | |
| "learning_rate": 1.1133333333333334e-06, | |
| "loss": 0.0215, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.2736122868545169, | |
| "grad_norm": 0.2219599187374115, | |
| "learning_rate": 1.0577777777777779e-06, | |
| "loss": 0.0224, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 0.27512395694763575, | |
| "grad_norm": 0.22244104743003845, | |
| "learning_rate": 1.0022222222222223e-06, | |
| "loss": 0.0198, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.2766356270407546, | |
| "grad_norm": 0.23590952157974243, | |
| "learning_rate": 9.466666666666667e-07, | |
| "loss": 0.0211, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 0.2781472971338735, | |
| "grad_norm": 0.19948144257068634, | |
| "learning_rate": 8.911111111111112e-07, | |
| "loss": 0.0209, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.2796589672269924, | |
| "grad_norm": 0.2427368015050888, | |
| "learning_rate": 8.355555555555556e-07, | |
| "loss": 0.0197, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 0.28117063732011127, | |
| "grad_norm": 0.20901180803775787, | |
| "learning_rate": 7.8e-07, | |
| "loss": 0.0209, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.28268230741323014, | |
| "grad_norm": 0.2242818921804428, | |
| "learning_rate": 7.244444444444446e-07, | |
| "loss": 0.0193, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 0.284193977506349, | |
| "grad_norm": 0.2646438181400299, | |
| "learning_rate": 6.68888888888889e-07, | |
| "loss": 0.0201, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.28570564759946787, | |
| "grad_norm": 0.22899940609931946, | |
| "learning_rate": 6.133333333333333e-07, | |
| "loss": 0.0205, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 0.2872173176925868, | |
| "grad_norm": 0.23318634927272797, | |
| "learning_rate": 5.577777777777779e-07, | |
| "loss": 0.0204, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.28872898778570566, | |
| "grad_norm": 0.25688520073890686, | |
| "learning_rate": 5.022222222222222e-07, | |
| "loss": 0.0202, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 0.2902406578788245, | |
| "grad_norm": 0.2177484780550003, | |
| "learning_rate": 4.466666666666667e-07, | |
| "loss": 0.0209, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.2917523279719434, | |
| "grad_norm": 0.22160756587982178, | |
| "learning_rate": 3.9111111111111115e-07, | |
| "loss": 0.0205, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 0.29326399806506226, | |
| "grad_norm": 0.18207120895385742, | |
| "learning_rate": 3.3555555555555556e-07, | |
| "loss": 0.0191, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.2947756681581812, | |
| "grad_norm": 0.23712973296642303, | |
| "learning_rate": 2.8e-07, | |
| "loss": 0.0201, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 0.29628733825130005, | |
| "grad_norm": 0.2736773192882538, | |
| "learning_rate": 2.2444444444444445e-07, | |
| "loss": 0.0208, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.2977990083444189, | |
| "grad_norm": 0.22754475474357605, | |
| "learning_rate": 1.6888888888888888e-07, | |
| "loss": 0.0194, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 0.2993106784375378, | |
| "grad_norm": 0.21516871452331543, | |
| "learning_rate": 1.1333333333333336e-07, | |
| "loss": 0.0205, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.30082234853065665, | |
| "grad_norm": 0.21580274403095245, | |
| "learning_rate": 5.777777777777778e-08, | |
| "loss": 0.0204, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 0.30233401862377557, | |
| "grad_norm": 0.2437376081943512, | |
| "learning_rate": 2.2222222222222225e-09, | |
| "loss": 0.0211, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.30233401862377557, | |
| "eval_loss": 0.02213170751929283, | |
| "eval_runtime": 12800.0788, | |
| "eval_samples_per_second": 8.962, | |
| "eval_steps_per_second": 0.56, | |
| "eval_wer": 78.11993940343729, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.61736640512e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |