| { | |
| "best_metric": 0.004692578222602606, | |
| "best_model_checkpoint": "Rashed-vit-model/checkpoint-600", | |
| "epoch": 50.0, | |
| "eval_steps": 200, | |
| "global_step": 5250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 3.151090621948242, | |
| "learning_rate": 0.00019961904761904765, | |
| "loss": 1.47, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 2.2249441146850586, | |
| "learning_rate": 0.00019923809523809523, | |
| "loss": 0.9259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 2.3258259296417236, | |
| "learning_rate": 0.00019885714285714287, | |
| "loss": 0.5066, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.8246334791183472, | |
| "learning_rate": 0.00019847619047619049, | |
| "loss": 0.3211, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 1.0330042839050293, | |
| "learning_rate": 0.0001980952380952381, | |
| "loss": 0.2825, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.533070981502533, | |
| "learning_rate": 0.0001977142857142857, | |
| "loss": 0.1851, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.3683183789253235, | |
| "learning_rate": 0.00019733333333333335, | |
| "loss": 0.2643, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.4011370837688446, | |
| "learning_rate": 0.00019695238095238096, | |
| "loss": 0.0848, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.23413445055484772, | |
| "learning_rate": 0.00019657142857142858, | |
| "loss": 0.068, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.2093656063079834, | |
| "learning_rate": 0.0001961904761904762, | |
| "loss": 0.1753, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 0.20530113577842712, | |
| "learning_rate": 0.00019580952380952383, | |
| "loss": 0.1503, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.14346353709697723, | |
| "learning_rate": 0.00019542857142857144, | |
| "loss": 0.0481, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 0.16548611223697662, | |
| "learning_rate": 0.00019504761904761905, | |
| "loss": 0.0371, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 17.316226959228516, | |
| "learning_rate": 0.0001946666666666667, | |
| "loss": 0.4116, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.159288689494133, | |
| "learning_rate": 0.0001942857142857143, | |
| "loss": 0.1922, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.19125591218471527, | |
| "learning_rate": 0.00019390476190476192, | |
| "loss": 0.0333, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.14799736440181732, | |
| "learning_rate": 0.00019352380952380953, | |
| "loss": 0.0291, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.11259680241346359, | |
| "learning_rate": 0.00019314285714285717, | |
| "loss": 0.0253, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.10623053461313248, | |
| "learning_rate": 0.00019276190476190475, | |
| "loss": 0.0452, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.09414517134428024, | |
| "learning_rate": 0.0001923809523809524, | |
| "loss": 0.2279, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "eval_accuracy": 0.9111111111111111, | |
| "eval_loss": 0.4485446512699127, | |
| "eval_runtime": 1.9474, | |
| "eval_samples_per_second": 46.216, | |
| "eval_steps_per_second": 6.162, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.09659522771835327, | |
| "learning_rate": 0.000192, | |
| "loss": 0.1118, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.09789349138736725, | |
| "learning_rate": 0.00019161904761904764, | |
| "loss": 0.022, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.07943525165319443, | |
| "learning_rate": 0.00019123809523809523, | |
| "loss": 0.0205, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.07477983087301254, | |
| "learning_rate": 0.00019085714285714287, | |
| "loss": 0.105, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.0683838427066803, | |
| "learning_rate": 0.00019047619047619048, | |
| "loss": 0.0162, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.06366163492202759, | |
| "learning_rate": 0.0001900952380952381, | |
| "loss": 0.1493, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.0778714045882225, | |
| "learning_rate": 0.00018971428571428573, | |
| "loss": 0.0188, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.06921613961458206, | |
| "learning_rate": 0.00018933333333333335, | |
| "loss": 0.0153, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.051817458122968674, | |
| "learning_rate": 0.00018895238095238096, | |
| "loss": 0.055, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.061549894511699677, | |
| "learning_rate": 0.00018857142857142857, | |
| "loss": 0.1511, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.11534985899925232, | |
| "learning_rate": 0.0001881904761904762, | |
| "loss": 0.0752, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.06578890234231949, | |
| "learning_rate": 0.00018780952380952382, | |
| "loss": 0.1233, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.051225241273641586, | |
| "learning_rate": 0.00018742857142857143, | |
| "loss": 0.0166, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.09599129110574722, | |
| "learning_rate": 0.00018704761904761905, | |
| "loss": 0.148, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.06939754635095596, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 0.2817, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.042554907500743866, | |
| "learning_rate": 0.0001862857142857143, | |
| "loss": 0.0129, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 2.854532480239868, | |
| "learning_rate": 0.0001859047619047619, | |
| "loss": 0.1371, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.05842894688248634, | |
| "learning_rate": 0.00018552380952380952, | |
| "loss": 0.0104, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.05560528114438057, | |
| "learning_rate": 0.00018514285714285716, | |
| "loss": 0.0116, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.0371054969727993, | |
| "learning_rate": 0.00018476190476190478, | |
| "loss": 0.1335, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.06801649928092957, | |
| "eval_runtime": 1.8418, | |
| "eval_samples_per_second": 48.866, | |
| "eval_steps_per_second": 6.515, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 21.256444931030273, | |
| "learning_rate": 0.0001843809523809524, | |
| "loss": 0.0255, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.133376806974411, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.1109, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 77.70124816894531, | |
| "learning_rate": 0.0001836190476190476, | |
| "loss": 0.0305, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 19.103601455688477, | |
| "learning_rate": 0.00018323809523809525, | |
| "loss": 0.1215, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.07738764584064484, | |
| "learning_rate": 0.00018285714285714286, | |
| "loss": 0.4973, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.058076005429029465, | |
| "learning_rate": 0.00018247619047619048, | |
| "loss": 0.3185, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.30883753299713135, | |
| "learning_rate": 0.0001820952380952381, | |
| "loss": 0.0147, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.07073301821947098, | |
| "learning_rate": 0.00018171428571428573, | |
| "loss": 0.01, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 6.756577968597412, | |
| "learning_rate": 0.00018133333333333334, | |
| "loss": 0.1395, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.029586009681224823, | |
| "learning_rate": 0.00018095238095238095, | |
| "loss": 0.134, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.03238486498594284, | |
| "learning_rate": 0.00018057142857142857, | |
| "loss": 0.0085, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.02708561345934868, | |
| "learning_rate": 0.0001801904761904762, | |
| "loss": 0.0794, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.028597068041563034, | |
| "learning_rate": 0.00017980952380952382, | |
| "loss": 0.0057, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.02428688295185566, | |
| "learning_rate": 0.00017942857142857143, | |
| "loss": 0.0053, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.032420895993709564, | |
| "learning_rate": 0.00017904761904761907, | |
| "loss": 0.0316, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.028093505650758743, | |
| "learning_rate": 0.00017866666666666668, | |
| "loss": 0.1435, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.02392229624092579, | |
| "learning_rate": 0.0001782857142857143, | |
| "loss": 0.0061, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.021767552942037582, | |
| "learning_rate": 0.0001779047619047619, | |
| "loss": 0.0061, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.01894824393093586, | |
| "learning_rate": 0.00017752380952380955, | |
| "loss": 0.0051, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.022082213312387466, | |
| "learning_rate": 0.00017714285714285713, | |
| "loss": 0.0061, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004692578222602606, | |
| "eval_runtime": 1.875, | |
| "eval_samples_per_second": 47.999, | |
| "eval_steps_per_second": 6.4, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 3.34830379486084, | |
| "learning_rate": 0.00017676190476190477, | |
| "loss": 0.1888, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.02342985011637211, | |
| "learning_rate": 0.00017638095238095238, | |
| "loss": 0.1323, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.020382458344101906, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.0066, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.0335586741566658, | |
| "learning_rate": 0.0001756190476190476, | |
| "loss": 0.0052, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.01792135089635849, | |
| "learning_rate": 0.00017523809523809525, | |
| "loss": 0.0747, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.028133902698755264, | |
| "learning_rate": 0.0001748571428571429, | |
| "loss": 0.0043, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.025317130610346794, | |
| "learning_rate": 0.00017447619047619047, | |
| "loss": 0.011, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.01567469723522663, | |
| "learning_rate": 0.0001740952380952381, | |
| "loss": 0.0041, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.013765121810138226, | |
| "learning_rate": 0.00017371428571428572, | |
| "loss": 0.0038, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.016870710998773575, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 0.0049, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.761904761904762, | |
| "grad_norm": 0.01623779535293579, | |
| "learning_rate": 0.00017295238095238095, | |
| "loss": 0.0031, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "grad_norm": 0.019678007811307907, | |
| "learning_rate": 0.0001725714285714286, | |
| "loss": 0.0033, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.9523809523809526, | |
| "grad_norm": 0.011731904931366444, | |
| "learning_rate": 0.0001721904761904762, | |
| "loss": 0.003, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.0476190476190474, | |
| "grad_norm": 0.013695590198040009, | |
| "learning_rate": 0.0001718095238095238, | |
| "loss": 0.0029, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.142857142857143, | |
| "grad_norm": 0.01363290473818779, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.0034, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.238095238095238, | |
| "grad_norm": 0.013888081535696983, | |
| "learning_rate": 0.00017104761904761906, | |
| "loss": 0.0028, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.333333333333333, | |
| "grad_norm": 0.010832449421286583, | |
| "learning_rate": 0.00017066666666666668, | |
| "loss": 0.0027, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.428571428571429, | |
| "grad_norm": 0.010716166347265244, | |
| "learning_rate": 0.0001702857142857143, | |
| "loss": 0.0026, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.523809523809524, | |
| "grad_norm": 0.01541854813694954, | |
| "learning_rate": 0.00016990476190476193, | |
| "loss": 0.0026, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.619047619047619, | |
| "grad_norm": 0.011363111436367035, | |
| "learning_rate": 0.00016952380952380954, | |
| "loss": 0.0025, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.619047619047619, | |
| "eval_accuracy": 0.9777777777777777, | |
| "eval_loss": 0.06062322109937668, | |
| "eval_runtime": 1.8362, | |
| "eval_samples_per_second": 49.014, | |
| "eval_steps_per_second": 6.535, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.714285714285714, | |
| "grad_norm": 0.014184274710714817, | |
| "learning_rate": 0.00016914285714285715, | |
| "loss": 0.0023, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.809523809523809, | |
| "grad_norm": 0.01366434432566166, | |
| "learning_rate": 0.00016876190476190477, | |
| "loss": 0.0023, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.904761904761905, | |
| "grad_norm": 0.01652826927602291, | |
| "learning_rate": 0.0001683809523809524, | |
| "loss": 0.1665, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.011341558769345284, | |
| "learning_rate": 0.000168, | |
| "loss": 0.1514, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.095238095238095, | |
| "grad_norm": 0.031734924763441086, | |
| "learning_rate": 0.00016761904761904763, | |
| "loss": 0.18, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.19047619047619, | |
| "grad_norm": 0.010504876263439655, | |
| "learning_rate": 0.00016723809523809524, | |
| "loss": 0.0258, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.285714285714286, | |
| "grad_norm": 0.012300320900976658, | |
| "learning_rate": 0.00016685714285714285, | |
| "loss": 0.0039, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.380952380952381, | |
| "grad_norm": 0.01060554664582014, | |
| "learning_rate": 0.00016647619047619047, | |
| "loss": 0.0179, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.476190476190476, | |
| "grad_norm": 0.01102207601070404, | |
| "learning_rate": 0.0001660952380952381, | |
| "loss": 0.1408, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 0.013715389184653759, | |
| "learning_rate": 0.00016571428571428575, | |
| "loss": 0.0027, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.666666666666666, | |
| "grad_norm": 0.012824783101677895, | |
| "learning_rate": 0.00016533333333333333, | |
| "loss": 0.0022, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.761904761904763, | |
| "grad_norm": 0.01925630122423172, | |
| "learning_rate": 0.00016495238095238097, | |
| "loss": 0.0031, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.857142857142858, | |
| "grad_norm": 0.010483276098966599, | |
| "learning_rate": 0.00016457142857142858, | |
| "loss": 0.3219, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.952380952380953, | |
| "grad_norm": 0.011007868684828281, | |
| "learning_rate": 0.0001641904761904762, | |
| "loss": 0.1958, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.047619047619047, | |
| "grad_norm": 27.257503509521484, | |
| "learning_rate": 0.0001638095238095238, | |
| "loss": 0.0081, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.142857142857142, | |
| "grad_norm": 0.01049420703202486, | |
| "learning_rate": 0.00016342857142857145, | |
| "loss": 0.0279, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.238095238095237, | |
| "grad_norm": 8.397236824035645, | |
| "learning_rate": 0.00016304761904761906, | |
| "loss": 0.0356, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.333333333333334, | |
| "grad_norm": 0.01408300455659628, | |
| "learning_rate": 0.00016266666666666667, | |
| "loss": 0.3159, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.428571428571429, | |
| "grad_norm": 0.028697043657302856, | |
| "learning_rate": 0.00016228571428571428, | |
| "loss": 0.0055, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.523809523809524, | |
| "grad_norm": 1.159379482269287, | |
| "learning_rate": 0.00016190476190476192, | |
| "loss": 0.0624, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.523809523809524, | |
| "eval_accuracy": 0.9555555555555556, | |
| "eval_loss": 0.24998384714126587, | |
| "eval_runtime": 1.8372, | |
| "eval_samples_per_second": 48.989, | |
| "eval_steps_per_second": 6.532, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.619047619047619, | |
| "grad_norm": 0.012321503832936287, | |
| "learning_rate": 0.0001615238095238095, | |
| "loss": 0.1389, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "grad_norm": 0.025649460032582283, | |
| "learning_rate": 0.00016114285714285715, | |
| "loss": 0.298, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.80952380952381, | |
| "grad_norm": 0.015477406792342663, | |
| "learning_rate": 0.0001607619047619048, | |
| "loss": 0.0025, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.904761904761905, | |
| "grad_norm": 0.009345958940684795, | |
| "learning_rate": 0.0001603809523809524, | |
| "loss": 0.0036, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.01423055212944746, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0025, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.095238095238095, | |
| "grad_norm": 0.0170315932482481, | |
| "learning_rate": 0.00015961904761904763, | |
| "loss": 0.0023, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 10.19047619047619, | |
| "grad_norm": 0.01108589582145214, | |
| "learning_rate": 0.00015923809523809526, | |
| "loss": 0.002, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.285714285714286, | |
| "grad_norm": 0.0083020543679595, | |
| "learning_rate": 0.00015885714285714285, | |
| "loss": 0.0053, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.380952380952381, | |
| "grad_norm": 0.010092386044561863, | |
| "learning_rate": 0.0001584761904761905, | |
| "loss": 0.0953, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 10.476190476190476, | |
| "grad_norm": 0.0312843881547451, | |
| "learning_rate": 0.0001580952380952381, | |
| "loss": 0.1219, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.571428571428571, | |
| "grad_norm": 0.007704514544457197, | |
| "learning_rate": 0.00015771428571428571, | |
| "loss": 0.002, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.666666666666666, | |
| "grad_norm": 0.007466526702046394, | |
| "learning_rate": 0.00015733333333333333, | |
| "loss": 0.0017, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.761904761904763, | |
| "grad_norm": 0.008785136975347996, | |
| "learning_rate": 0.00015695238095238097, | |
| "loss": 0.0017, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "grad_norm": 0.0070278337225317955, | |
| "learning_rate": 0.00015657142857142858, | |
| "loss": 0.0015, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.952380952380953, | |
| "grad_norm": 0.006687019020318985, | |
| "learning_rate": 0.0001561904761904762, | |
| "loss": 0.0016, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.047619047619047, | |
| "grad_norm": 0.007705973461270332, | |
| "learning_rate": 0.00015580952380952383, | |
| "loss": 0.0015, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 11.142857142857142, | |
| "grad_norm": 0.005592050030827522, | |
| "learning_rate": 0.00015542857142857144, | |
| "loss": 0.0014, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 11.238095238095237, | |
| "grad_norm": 0.005734533537179232, | |
| "learning_rate": 0.00015504761904761906, | |
| "loss": 0.0014, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 11.333333333333334, | |
| "grad_norm": 0.009775955229997635, | |
| "learning_rate": 0.00015466666666666667, | |
| "loss": 0.0013, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 0.00592830590903759, | |
| "learning_rate": 0.0001542857142857143, | |
| "loss": 0.0013, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.08676379919052124, | |
| "eval_runtime": 1.8128, | |
| "eval_samples_per_second": 49.648, | |
| "eval_steps_per_second": 6.62, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.523809523809524, | |
| "grad_norm": 0.007258219178766012, | |
| "learning_rate": 0.00015390476190476192, | |
| "loss": 0.0013, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 11.619047619047619, | |
| "grad_norm": 0.008449223823845387, | |
| "learning_rate": 0.00015352380952380953, | |
| "loss": 0.0013, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 11.714285714285714, | |
| "grad_norm": 0.006206180434674025, | |
| "learning_rate": 0.00015314285714285714, | |
| "loss": 0.0012, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 11.80952380952381, | |
| "grad_norm": 0.007200263906270266, | |
| "learning_rate": 0.00015276190476190478, | |
| "loss": 0.0012, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.904761904761905, | |
| "grad_norm": 0.006314568221569061, | |
| "learning_rate": 0.00015238095238095237, | |
| "loss": 0.0012, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.006546263117343187, | |
| "learning_rate": 0.000152, | |
| "loss": 0.0012, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 12.095238095238095, | |
| "grad_norm": 0.008106805384159088, | |
| "learning_rate": 0.00015161904761904762, | |
| "loss": 0.0011, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 12.19047619047619, | |
| "grad_norm": 0.0055976384319365025, | |
| "learning_rate": 0.00015123809523809523, | |
| "loss": 0.0011, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 12.285714285714286, | |
| "grad_norm": 0.0060087935999035835, | |
| "learning_rate": 0.00015085714285714287, | |
| "loss": 0.0011, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 12.380952380952381, | |
| "grad_norm": 0.0049287304282188416, | |
| "learning_rate": 0.00015047619047619048, | |
| "loss": 0.0011, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 12.476190476190476, | |
| "grad_norm": 0.0059693050570786, | |
| "learning_rate": 0.00015009523809523812, | |
| "loss": 0.0011, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "grad_norm": 0.005779750179499388, | |
| "learning_rate": 0.0001497142857142857, | |
| "loss": 0.0011, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 12.666666666666666, | |
| "grad_norm": 0.005393909756094217, | |
| "learning_rate": 0.00014933333333333335, | |
| "loss": 0.0011, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 12.761904761904763, | |
| "grad_norm": 0.004382868763059378, | |
| "learning_rate": 0.00014895238095238096, | |
| "loss": 0.001, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 12.857142857142858, | |
| "grad_norm": 0.004925265908241272, | |
| "learning_rate": 0.00014857142857142857, | |
| "loss": 0.001, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 12.952380952380953, | |
| "grad_norm": 0.006973223760724068, | |
| "learning_rate": 0.00014819047619047619, | |
| "loss": 0.001, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 13.047619047619047, | |
| "grad_norm": 0.004812673199921846, | |
| "learning_rate": 0.00014780952380952383, | |
| "loss": 0.001, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 13.142857142857142, | |
| "grad_norm": 0.004308717790991068, | |
| "learning_rate": 0.00014742857142857144, | |
| "loss": 0.001, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 13.238095238095237, | |
| "grad_norm": 0.005545957013964653, | |
| "learning_rate": 0.00014704761904761905, | |
| "loss": 0.001, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 0.005481696221977472, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 0.001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.09084086120128632, | |
| "eval_runtime": 1.857, | |
| "eval_samples_per_second": 48.466, | |
| "eval_steps_per_second": 6.462, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.428571428571429, | |
| "grad_norm": 0.004818524233996868, | |
| "learning_rate": 0.0001462857142857143, | |
| "loss": 0.0009, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 13.523809523809524, | |
| "grad_norm": 0.004527853336185217, | |
| "learning_rate": 0.00014590476190476191, | |
| "loss": 0.0009, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 13.619047619047619, | |
| "grad_norm": 0.004231444094330072, | |
| "learning_rate": 0.00014552380952380953, | |
| "loss": 0.0009, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "grad_norm": 0.0044059534557163715, | |
| "learning_rate": 0.00014514285714285717, | |
| "loss": 0.0009, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 13.80952380952381, | |
| "grad_norm": 0.00579995010048151, | |
| "learning_rate": 0.00014476190476190475, | |
| "loss": 0.0009, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 13.904761904761905, | |
| "grad_norm": 0.0056099193170666695, | |
| "learning_rate": 0.0001443809523809524, | |
| "loss": 0.0009, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.004670779220759869, | |
| "learning_rate": 0.000144, | |
| "loss": 0.0009, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 14.095238095238095, | |
| "grad_norm": 0.004188599996268749, | |
| "learning_rate": 0.00014361904761904764, | |
| "loss": 0.0009, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 14.19047619047619, | |
| "grad_norm": 0.004746088758111, | |
| "learning_rate": 0.00014323809523809523, | |
| "loss": 0.0009, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 14.285714285714286, | |
| "grad_norm": 0.00368096143938601, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.0008, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.380952380952381, | |
| "grad_norm": 0.005118837580084801, | |
| "learning_rate": 0.00014247619047619048, | |
| "loss": 0.0008, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 14.476190476190476, | |
| "grad_norm": 0.004199205432087183, | |
| "learning_rate": 0.0001420952380952381, | |
| "loss": 0.0008, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 14.571428571428571, | |
| "grad_norm": 0.004467179533094168, | |
| "learning_rate": 0.0001417142857142857, | |
| "loss": 0.0008, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 14.666666666666666, | |
| "grad_norm": 0.003941674251109362, | |
| "learning_rate": 0.00014133333333333334, | |
| "loss": 0.0008, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 14.761904761904763, | |
| "grad_norm": 0.0038668368943035603, | |
| "learning_rate": 0.00014095238095238096, | |
| "loss": 0.0008, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "grad_norm": 0.0032947659492492676, | |
| "learning_rate": 0.00014057142857142857, | |
| "loss": 0.0008, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 14.952380952380953, | |
| "grad_norm": 0.004051734693348408, | |
| "learning_rate": 0.0001401904761904762, | |
| "loss": 0.0008, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 15.047619047619047, | |
| "grad_norm": 0.0038156399969011545, | |
| "learning_rate": 0.00013980952380952382, | |
| "loss": 0.0008, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 15.142857142857142, | |
| "grad_norm": 0.003167238784953952, | |
| "learning_rate": 0.00013942857142857143, | |
| "loss": 0.0008, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 15.238095238095237, | |
| "grad_norm": 0.004244392737746239, | |
| "learning_rate": 0.00013904761904761905, | |
| "loss": 0.0008, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 15.238095238095237, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.09350696206092834, | |
| "eval_runtime": 1.8245, | |
| "eval_samples_per_second": 49.327, | |
| "eval_steps_per_second": 6.577, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 15.333333333333334, | |
| "grad_norm": 0.0033419239334762096, | |
| "learning_rate": 0.00013866666666666669, | |
| "loss": 0.0008, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 15.428571428571429, | |
| "grad_norm": 0.00397316413000226, | |
| "learning_rate": 0.0001382857142857143, | |
| "loss": 0.0007, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 15.523809523809524, | |
| "grad_norm": 0.0039126453921198845, | |
| "learning_rate": 0.0001379047619047619, | |
| "loss": 0.0007, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 15.619047619047619, | |
| "grad_norm": 0.004549206700176001, | |
| "learning_rate": 0.00013752380952380952, | |
| "loss": 0.0007, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 15.714285714285714, | |
| "grad_norm": 0.0037825647741556168, | |
| "learning_rate": 0.00013714285714285716, | |
| "loss": 0.0007, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 15.80952380952381, | |
| "grad_norm": 0.0035358979366719723, | |
| "learning_rate": 0.00013676190476190475, | |
| "loss": 0.0007, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 15.904761904761905, | |
| "grad_norm": 0.00303203659132123, | |
| "learning_rate": 0.0001363809523809524, | |
| "loss": 0.0007, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.0034562856890261173, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.0007, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 16.095238095238095, | |
| "grad_norm": 0.003765418427065015, | |
| "learning_rate": 0.0001356190476190476, | |
| "loss": 0.0007, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 16.19047619047619, | |
| "grad_norm": 0.004050769843161106, | |
| "learning_rate": 0.00013523809523809525, | |
| "loss": 0.0007, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 16.285714285714285, | |
| "grad_norm": 0.003430079435929656, | |
| "learning_rate": 0.00013485714285714286, | |
| "loss": 0.0007, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 16.38095238095238, | |
| "grad_norm": 0.0034265487920492887, | |
| "learning_rate": 0.00013447619047619048, | |
| "loss": 0.0007, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 16.476190476190474, | |
| "grad_norm": 0.0035600378178060055, | |
| "learning_rate": 0.0001340952380952381, | |
| "loss": 0.0007, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "grad_norm": 0.0035557844676077366, | |
| "learning_rate": 0.00013371428571428573, | |
| "loss": 0.0006, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 0.003414078615605831, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0007, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 16.761904761904763, | |
| "grad_norm": 0.003397165797650814, | |
| "learning_rate": 0.00013295238095238095, | |
| "loss": 0.0006, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 16.857142857142858, | |
| "grad_norm": 0.004645552486181259, | |
| "learning_rate": 0.00013257142857142856, | |
| "loss": 0.0006, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 16.952380952380953, | |
| "grad_norm": 0.003458562307059765, | |
| "learning_rate": 0.0001321904761904762, | |
| "loss": 0.0006, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 17.047619047619047, | |
| "grad_norm": 0.0031132667791098356, | |
| "learning_rate": 0.00013180952380952382, | |
| "loss": 0.0006, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 0.003444332629442215, | |
| "learning_rate": 0.00013142857142857143, | |
| "loss": 0.0006, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.09595004469156265, | |
| "eval_runtime": 1.8604, | |
| "eval_samples_per_second": 48.378, | |
| "eval_steps_per_second": 6.45, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 17.238095238095237, | |
| "grad_norm": 0.003377641784027219, | |
| "learning_rate": 0.00013104761904761907, | |
| "loss": 0.0006, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 17.333333333333332, | |
| "grad_norm": 0.002931503811851144, | |
| "learning_rate": 0.00013066666666666668, | |
| "loss": 0.0006, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 17.428571428571427, | |
| "grad_norm": 0.0025878995656967163, | |
| "learning_rate": 0.0001302857142857143, | |
| "loss": 0.0006, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 17.523809523809526, | |
| "grad_norm": 0.0029362973291426897, | |
| "learning_rate": 0.0001299047619047619, | |
| "loss": 0.0006, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 17.61904761904762, | |
| "grad_norm": 0.0031627302523702383, | |
| "learning_rate": 0.00012952380952380954, | |
| "loss": 0.0006, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "grad_norm": 0.002626455621793866, | |
| "learning_rate": 0.00012914285714285713, | |
| "loss": 0.0006, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 17.80952380952381, | |
| "grad_norm": 0.003233458148315549, | |
| "learning_rate": 0.00012876190476190477, | |
| "loss": 0.0006, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 17.904761904761905, | |
| "grad_norm": 0.0029100878164172173, | |
| "learning_rate": 0.00012838095238095238, | |
| "loss": 0.0006, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 0.003953940235078335, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.0006, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 18.095238095238095, | |
| "grad_norm": 0.002800758695229888, | |
| "learning_rate": 0.0001276190476190476, | |
| "loss": 0.0006, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 18.19047619047619, | |
| "grad_norm": 0.0032456107437610626, | |
| "learning_rate": 0.00012723809523809525, | |
| "loss": 0.0006, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 18.285714285714285, | |
| "grad_norm": 0.0030850470066070557, | |
| "learning_rate": 0.00012685714285714286, | |
| "loss": 0.0006, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 18.38095238095238, | |
| "grad_norm": 0.0023274675477296114, | |
| "learning_rate": 0.00012647619047619047, | |
| "loss": 0.0005, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 18.476190476190474, | |
| "grad_norm": 0.0024060842115432024, | |
| "learning_rate": 0.0001260952380952381, | |
| "loss": 0.0005, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 18.571428571428573, | |
| "grad_norm": 0.0024556380230933428, | |
| "learning_rate": 0.00012571428571428572, | |
| "loss": 0.0005, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 18.666666666666668, | |
| "grad_norm": 0.002316309604793787, | |
| "learning_rate": 0.00012533333333333334, | |
| "loss": 0.0005, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 18.761904761904763, | |
| "grad_norm": 0.0026871436275541782, | |
| "learning_rate": 0.00012495238095238095, | |
| "loss": 0.0005, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "grad_norm": 0.0027834640350192785, | |
| "learning_rate": 0.0001245714285714286, | |
| "loss": 0.0005, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 18.952380952380953, | |
| "grad_norm": 0.0026347485836595297, | |
| "learning_rate": 0.0001241904761904762, | |
| "loss": 0.0005, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 19.047619047619047, | |
| "grad_norm": 0.0023498283699154854, | |
| "learning_rate": 0.0001238095238095238, | |
| "loss": 0.0005, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 19.047619047619047, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.09789697080850601, | |
| "eval_runtime": 1.8414, | |
| "eval_samples_per_second": 48.876, | |
| "eval_steps_per_second": 6.517, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 19.142857142857142, | |
| "grad_norm": 0.00248084613122046, | |
| "learning_rate": 0.00012342857142857142, | |
| "loss": 0.0005, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 19.238095238095237, | |
| "grad_norm": 0.002750256797298789, | |
| "learning_rate": 0.00012304761904761906, | |
| "loss": 0.0005, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 19.333333333333332, | |
| "grad_norm": 0.002614253666251898, | |
| "learning_rate": 0.00012266666666666668, | |
| "loss": 0.0005, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 19.428571428571427, | |
| "grad_norm": 0.0027343921829015017, | |
| "learning_rate": 0.0001222857142857143, | |
| "loss": 0.0005, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 19.523809523809526, | |
| "grad_norm": 0.003097172826528549, | |
| "learning_rate": 0.00012190476190476193, | |
| "loss": 0.0005, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 19.61904761904762, | |
| "grad_norm": 0.0023109845351427794, | |
| "learning_rate": 0.00012152380952380953, | |
| "loss": 0.0005, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 19.714285714285715, | |
| "grad_norm": 0.002156308153644204, | |
| "learning_rate": 0.00012114285714285715, | |
| "loss": 0.0005, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 19.80952380952381, | |
| "grad_norm": 0.0034764858428388834, | |
| "learning_rate": 0.00012076190476190476, | |
| "loss": 0.0005, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 19.904761904761905, | |
| "grad_norm": 0.002348085166886449, | |
| "learning_rate": 0.00012038095238095239, | |
| "loss": 0.0005, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.002654197858646512, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0005, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 20.095238095238095, | |
| "grad_norm": 0.002493527252227068, | |
| "learning_rate": 0.00011961904761904763, | |
| "loss": 0.0005, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 20.19047619047619, | |
| "grad_norm": 0.0028157392516732216, | |
| "learning_rate": 0.00011923809523809524, | |
| "loss": 0.0005, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 20.285714285714285, | |
| "grad_norm": 0.002257339423522353, | |
| "learning_rate": 0.00011885714285714287, | |
| "loss": 0.0005, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 20.38095238095238, | |
| "grad_norm": 0.0019334362586960196, | |
| "learning_rate": 0.00011847619047619048, | |
| "loss": 0.0005, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 20.476190476190474, | |
| "grad_norm": 0.0025482685305178165, | |
| "learning_rate": 0.0001180952380952381, | |
| "loss": 0.0005, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "grad_norm": 0.0025490294210612774, | |
| "learning_rate": 0.0001177142857142857, | |
| "loss": 0.0004, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 20.666666666666668, | |
| "grad_norm": 0.002070168498903513, | |
| "learning_rate": 0.00011733333333333334, | |
| "loss": 0.0004, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 20.761904761904763, | |
| "grad_norm": 0.0026253170799463987, | |
| "learning_rate": 0.00011695238095238097, | |
| "loss": 0.0004, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 20.857142857142858, | |
| "grad_norm": 0.0019473080756142735, | |
| "learning_rate": 0.00011657142857142858, | |
| "loss": 0.0004, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 20.952380952380953, | |
| "grad_norm": 0.002398025244474411, | |
| "learning_rate": 0.00011619047619047621, | |
| "loss": 0.0004, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 20.952380952380953, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.09959948062896729, | |
| "eval_runtime": 1.8394, | |
| "eval_samples_per_second": 48.929, | |
| "eval_steps_per_second": 6.524, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 21.047619047619047, | |
| "grad_norm": 0.0024668213445693254, | |
| "learning_rate": 0.00011580952380952381, | |
| "loss": 0.0004, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 21.142857142857142, | |
| "grad_norm": 0.0021500024013221264, | |
| "learning_rate": 0.00011542857142857145, | |
| "loss": 0.0004, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 21.238095238095237, | |
| "grad_norm": 0.0024119997397065163, | |
| "learning_rate": 0.00011504761904761905, | |
| "loss": 0.0004, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 21.333333333333332, | |
| "grad_norm": 0.00240101246163249, | |
| "learning_rate": 0.00011466666666666667, | |
| "loss": 0.0004, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 21.428571428571427, | |
| "grad_norm": 0.0020979908294975758, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.0004, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 21.523809523809526, | |
| "grad_norm": 0.0018657994223758578, | |
| "learning_rate": 0.00011390476190476191, | |
| "loss": 0.0004, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 21.61904761904762, | |
| "grad_norm": 0.0022507307585328817, | |
| "learning_rate": 0.00011352380952380952, | |
| "loss": 0.0004, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "grad_norm": 0.00310464296489954, | |
| "learning_rate": 0.00011314285714285715, | |
| "loss": 0.0004, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 21.80952380952381, | |
| "grad_norm": 0.0022059795446693897, | |
| "learning_rate": 0.00011276190476190476, | |
| "loss": 0.0004, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 21.904761904761905, | |
| "grad_norm": 0.0018011420033872128, | |
| "learning_rate": 0.00011238095238095239, | |
| "loss": 0.0004, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 0.0022507570683956146, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.0004, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 22.095238095238095, | |
| "grad_norm": 0.0020354469306766987, | |
| "learning_rate": 0.00011161904761904762, | |
| "loss": 0.0004, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 22.19047619047619, | |
| "grad_norm": 0.002128103282302618, | |
| "learning_rate": 0.00011123809523809525, | |
| "loss": 0.0004, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 22.285714285714285, | |
| "grad_norm": 0.0021601992193609476, | |
| "learning_rate": 0.00011085714285714286, | |
| "loss": 0.0004, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 22.38095238095238, | |
| "grad_norm": 0.002009602030739188, | |
| "learning_rate": 0.00011047619047619049, | |
| "loss": 0.0004, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 22.476190476190474, | |
| "grad_norm": 0.00177257158793509, | |
| "learning_rate": 0.0001100952380952381, | |
| "loss": 0.0004, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 22.571428571428573, | |
| "grad_norm": 0.001979637425392866, | |
| "learning_rate": 0.00010971428571428573, | |
| "loss": 0.0004, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 22.666666666666668, | |
| "grad_norm": 0.002127070678398013, | |
| "learning_rate": 0.00010933333333333333, | |
| "loss": 0.0004, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 22.761904761904763, | |
| "grad_norm": 0.0027517336420714855, | |
| "learning_rate": 0.00010895238095238097, | |
| "loss": 0.0004, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 0.002378536155447364, | |
| "learning_rate": 0.00010857142857142856, | |
| "loss": 0.0004, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10131306201219559, | |
| "eval_runtime": 1.831, | |
| "eval_samples_per_second": 49.154, | |
| "eval_steps_per_second": 6.554, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 22.952380952380953, | |
| "grad_norm": 0.0018193406285718083, | |
| "learning_rate": 0.0001081904761904762, | |
| "loss": 0.0004, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 23.047619047619047, | |
| "grad_norm": 0.0021576720755547285, | |
| "learning_rate": 0.0001078095238095238, | |
| "loss": 0.0004, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 23.142857142857142, | |
| "grad_norm": 0.001894907676614821, | |
| "learning_rate": 0.00010742857142857143, | |
| "loss": 0.0004, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 23.238095238095237, | |
| "grad_norm": 0.002026046859100461, | |
| "learning_rate": 0.00010704761904761907, | |
| "loss": 0.0004, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 23.333333333333332, | |
| "grad_norm": 0.0020676099229604006, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 0.0004, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 23.428571428571427, | |
| "grad_norm": 0.0020323486533015966, | |
| "learning_rate": 0.0001062857142857143, | |
| "loss": 0.0004, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 23.523809523809526, | |
| "grad_norm": 0.0020114111248403788, | |
| "learning_rate": 0.0001059047619047619, | |
| "loss": 0.0004, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 23.61904761904762, | |
| "grad_norm": 0.0015946037601679564, | |
| "learning_rate": 0.00010552380952380953, | |
| "loss": 0.0004, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 23.714285714285715, | |
| "grad_norm": 0.0025066270027309656, | |
| "learning_rate": 0.00010514285714285714, | |
| "loss": 0.0004, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 23.80952380952381, | |
| "grad_norm": 0.0017767308745533228, | |
| "learning_rate": 0.00010476190476190477, | |
| "loss": 0.0003, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 23.904761904761905, | |
| "grad_norm": 0.0017650197260081768, | |
| "learning_rate": 0.00010438095238095238, | |
| "loss": 0.0003, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.0021189264953136444, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.0003, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 24.095238095238095, | |
| "grad_norm": 0.0019698874093592167, | |
| "learning_rate": 0.00010361904761904762, | |
| "loss": 0.0003, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 24.19047619047619, | |
| "grad_norm": 0.0017098532989621162, | |
| "learning_rate": 0.00010323809523809525, | |
| "loss": 0.0003, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 24.285714285714285, | |
| "grad_norm": 0.0015597473829984665, | |
| "learning_rate": 0.00010285714285714286, | |
| "loss": 0.0003, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 24.38095238095238, | |
| "grad_norm": 0.0017549317562952638, | |
| "learning_rate": 0.00010247619047619048, | |
| "loss": 0.0003, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 24.476190476190474, | |
| "grad_norm": 0.0018130100797861814, | |
| "learning_rate": 0.00010209523809523811, | |
| "loss": 0.0003, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "grad_norm": 0.001496152370236814, | |
| "learning_rate": 0.00010171428571428572, | |
| "loss": 0.0003, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 24.666666666666668, | |
| "grad_norm": 0.0016472706338390708, | |
| "learning_rate": 0.00010133333333333335, | |
| "loss": 0.0003, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 24.761904761904763, | |
| "grad_norm": 0.0015423197764903307, | |
| "learning_rate": 0.00010095238095238096, | |
| "loss": 0.0003, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 24.761904761904763, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10273335874080658, | |
| "eval_runtime": 1.8975, | |
| "eval_samples_per_second": 47.431, | |
| "eval_steps_per_second": 6.324, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 24.857142857142858, | |
| "grad_norm": 0.0019110334105789661, | |
| "learning_rate": 0.00010057142857142859, | |
| "loss": 0.0003, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 24.952380952380953, | |
| "grad_norm": 0.0018585320794954896, | |
| "learning_rate": 0.00010019047619047619, | |
| "loss": 0.0003, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 25.047619047619047, | |
| "grad_norm": 0.0013858104357495904, | |
| "learning_rate": 9.980952380952382e-05, | |
| "loss": 0.0003, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 25.142857142857142, | |
| "grad_norm": 0.001535033225081861, | |
| "learning_rate": 9.942857142857144e-05, | |
| "loss": 0.0003, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 25.238095238095237, | |
| "grad_norm": 0.0017087319865822792, | |
| "learning_rate": 9.904761904761905e-05, | |
| "loss": 0.0003, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 25.333333333333332, | |
| "grad_norm": 0.0017350006382912397, | |
| "learning_rate": 9.866666666666668e-05, | |
| "loss": 0.0003, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 25.428571428571427, | |
| "grad_norm": 0.0017070028698071837, | |
| "learning_rate": 9.828571428571429e-05, | |
| "loss": 0.0003, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 25.523809523809526, | |
| "grad_norm": 0.001386874821037054, | |
| "learning_rate": 9.790476190476191e-05, | |
| "loss": 0.0003, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 25.61904761904762, | |
| "grad_norm": 0.001825571060180664, | |
| "learning_rate": 9.752380952380953e-05, | |
| "loss": 0.0003, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "grad_norm": 0.002032818039879203, | |
| "learning_rate": 9.714285714285715e-05, | |
| "loss": 0.0003, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 25.80952380952381, | |
| "grad_norm": 0.001751041621901095, | |
| "learning_rate": 9.676190476190476e-05, | |
| "loss": 0.0003, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 25.904761904761905, | |
| "grad_norm": 0.0013650762848556042, | |
| "learning_rate": 9.638095238095238e-05, | |
| "loss": 0.0003, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 0.0017085983417928219, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0003, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 26.095238095238095, | |
| "grad_norm": 0.0019595788326114416, | |
| "learning_rate": 9.561904761904761e-05, | |
| "loss": 0.0003, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 26.19047619047619, | |
| "grad_norm": 0.0015648071421310306, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.0003, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 26.285714285714285, | |
| "grad_norm": 0.0013588843867182732, | |
| "learning_rate": 9.485714285714287e-05, | |
| "loss": 0.0003, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 26.38095238095238, | |
| "grad_norm": 0.0018747361609712243, | |
| "learning_rate": 9.447619047619048e-05, | |
| "loss": 0.0003, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 26.476190476190474, | |
| "grad_norm": 0.001690955483354628, | |
| "learning_rate": 9.40952380952381e-05, | |
| "loss": 0.0003, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 26.571428571428573, | |
| "grad_norm": 0.0013384738704189658, | |
| "learning_rate": 9.371428571428572e-05, | |
| "loss": 0.0003, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 0.0014853357570245862, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.0003, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10395906120538712, | |
| "eval_runtime": 1.8227, | |
| "eval_samples_per_second": 49.376, | |
| "eval_steps_per_second": 6.584, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 26.761904761904763, | |
| "grad_norm": 0.0016543471720069647, | |
| "learning_rate": 9.295238095238096e-05, | |
| "loss": 0.0003, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "grad_norm": 0.0017920717364177108, | |
| "learning_rate": 9.257142857142858e-05, | |
| "loss": 0.0003, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 26.952380952380953, | |
| "grad_norm": 0.001780999475158751, | |
| "learning_rate": 9.21904761904762e-05, | |
| "loss": 0.0003, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 27.047619047619047, | |
| "grad_norm": 0.0017571296775713563, | |
| "learning_rate": 9.18095238095238e-05, | |
| "loss": 0.0003, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 27.142857142857142, | |
| "grad_norm": 0.001608196529559791, | |
| "learning_rate": 9.142857142857143e-05, | |
| "loss": 0.0003, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 27.238095238095237, | |
| "grad_norm": 0.0012196486350148916, | |
| "learning_rate": 9.104761904761904e-05, | |
| "loss": 0.0003, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 27.333333333333332, | |
| "grad_norm": 0.0016817754367366433, | |
| "learning_rate": 9.066666666666667e-05, | |
| "loss": 0.0003, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 27.428571428571427, | |
| "grad_norm": 0.0013980488292872906, | |
| "learning_rate": 9.028571428571428e-05, | |
| "loss": 0.0003, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 27.523809523809526, | |
| "grad_norm": 0.0014381955843418837, | |
| "learning_rate": 8.990476190476191e-05, | |
| "loss": 0.0003, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 27.61904761904762, | |
| "grad_norm": 0.0017193375388160348, | |
| "learning_rate": 8.952380952380953e-05, | |
| "loss": 0.0003, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 27.714285714285715, | |
| "grad_norm": 0.0014679852174594998, | |
| "learning_rate": 8.914285714285715e-05, | |
| "loss": 0.0003, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 27.80952380952381, | |
| "grad_norm": 0.0015112061519175768, | |
| "learning_rate": 8.876190476190477e-05, | |
| "loss": 0.0003, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 27.904761904761905, | |
| "grad_norm": 0.001384653733111918, | |
| "learning_rate": 8.838095238095239e-05, | |
| "loss": 0.0003, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "grad_norm": 0.0013816114515066147, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0003, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 28.095238095238095, | |
| "grad_norm": 0.0016994256293401122, | |
| "learning_rate": 8.761904761904762e-05, | |
| "loss": 0.0003, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 28.19047619047619, | |
| "grad_norm": 0.0019262159476056695, | |
| "learning_rate": 8.723809523809524e-05, | |
| "loss": 0.0003, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 28.285714285714285, | |
| "grad_norm": 0.0013534968020394444, | |
| "learning_rate": 8.685714285714286e-05, | |
| "loss": 0.0003, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 28.38095238095238, | |
| "grad_norm": 0.0019154124893248081, | |
| "learning_rate": 8.647619047619047e-05, | |
| "loss": 0.0003, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 28.476190476190474, | |
| "grad_norm": 0.0012145413784310222, | |
| "learning_rate": 8.60952380952381e-05, | |
| "loss": 0.0003, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 0.0014412440359592438, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.0003, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10537426918745041, | |
| "eval_runtime": 1.835, | |
| "eval_samples_per_second": 49.046, | |
| "eval_steps_per_second": 6.54, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 28.666666666666668, | |
| "grad_norm": 0.0013919365592300892, | |
| "learning_rate": 8.533333333333334e-05, | |
| "loss": 0.0003, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 28.761904761904763, | |
| "grad_norm": 0.0014765893574804068, | |
| "learning_rate": 8.495238095238096e-05, | |
| "loss": 0.0003, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 28.857142857142858, | |
| "grad_norm": 0.0014301234623417258, | |
| "learning_rate": 8.457142857142858e-05, | |
| "loss": 0.0003, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 28.952380952380953, | |
| "grad_norm": 0.001199308899231255, | |
| "learning_rate": 8.41904761904762e-05, | |
| "loss": 0.0002, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 29.047619047619047, | |
| "grad_norm": 0.0016072203870862722, | |
| "learning_rate": 8.380952380952382e-05, | |
| "loss": 0.0003, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 29.142857142857142, | |
| "grad_norm": 0.0013589338632300496, | |
| "learning_rate": 8.342857142857143e-05, | |
| "loss": 0.0003, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 29.238095238095237, | |
| "grad_norm": 0.0013709213817492127, | |
| "learning_rate": 8.304761904761905e-05, | |
| "loss": 0.0002, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 29.333333333333332, | |
| "grad_norm": 0.0014178252313286066, | |
| "learning_rate": 8.266666666666667e-05, | |
| "loss": 0.0002, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 29.428571428571427, | |
| "grad_norm": 0.0011131716892123222, | |
| "learning_rate": 8.228571428571429e-05, | |
| "loss": 0.0002, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 29.523809523809526, | |
| "grad_norm": 0.0012747022556141019, | |
| "learning_rate": 8.19047619047619e-05, | |
| "loss": 0.0002, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 29.61904761904762, | |
| "grad_norm": 0.0012651210417971015, | |
| "learning_rate": 8.152380952380953e-05, | |
| "loss": 0.0002, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "grad_norm": 0.0010486384853720665, | |
| "learning_rate": 8.114285714285714e-05, | |
| "loss": 0.0002, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 29.80952380952381, | |
| "grad_norm": 0.0010458205360919237, | |
| "learning_rate": 8.076190476190475e-05, | |
| "loss": 0.0002, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 29.904761904761905, | |
| "grad_norm": 0.0015383816789835691, | |
| "learning_rate": 8.03809523809524e-05, | |
| "loss": 0.0002, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.0014080354012548923, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0002, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 30.095238095238095, | |
| "grad_norm": 0.0013429720420390368, | |
| "learning_rate": 7.961904761904763e-05, | |
| "loss": 0.0002, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 30.19047619047619, | |
| "grad_norm": 0.0015557792503386736, | |
| "learning_rate": 7.923809523809524e-05, | |
| "loss": 0.0002, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 30.285714285714285, | |
| "grad_norm": 0.0013127701822668314, | |
| "learning_rate": 7.885714285714286e-05, | |
| "loss": 0.0002, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 30.38095238095238, | |
| "grad_norm": 0.0010757596464827657, | |
| "learning_rate": 7.847619047619048e-05, | |
| "loss": 0.0002, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 30.476190476190474, | |
| "grad_norm": 0.0013349753571674228, | |
| "learning_rate": 7.80952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 30.476190476190474, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10645116865634918, | |
| "eval_runtime": 1.8718, | |
| "eval_samples_per_second": 48.081, | |
| "eval_steps_per_second": 6.411, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 30.571428571428573, | |
| "grad_norm": 0.0013240899424999952, | |
| "learning_rate": 7.771428571428572e-05, | |
| "loss": 0.0002, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 30.666666666666668, | |
| "grad_norm": 0.001013773726299405, | |
| "learning_rate": 7.733333333333333e-05, | |
| "loss": 0.0002, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 30.761904761904763, | |
| "grad_norm": 0.0014196832198649645, | |
| "learning_rate": 7.695238095238096e-05, | |
| "loss": 0.0002, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "grad_norm": 0.0012821616837754846, | |
| "learning_rate": 7.657142857142857e-05, | |
| "loss": 0.0002, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 30.952380952380953, | |
| "grad_norm": 0.0012715483317151666, | |
| "learning_rate": 7.619047619047618e-05, | |
| "loss": 0.0002, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 31.047619047619047, | |
| "grad_norm": 0.0011925731087103486, | |
| "learning_rate": 7.580952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 31.142857142857142, | |
| "grad_norm": 0.0010031798155978322, | |
| "learning_rate": 7.542857142857144e-05, | |
| "loss": 0.0002, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 31.238095238095237, | |
| "grad_norm": 0.0012696062913164496, | |
| "learning_rate": 7.504761904761906e-05, | |
| "loss": 0.0002, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 31.333333333333332, | |
| "grad_norm": 0.001149684889242053, | |
| "learning_rate": 7.466666666666667e-05, | |
| "loss": 0.0002, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 31.428571428571427, | |
| "grad_norm": 0.001153462566435337, | |
| "learning_rate": 7.428571428571429e-05, | |
| "loss": 0.0002, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 31.523809523809526, | |
| "grad_norm": 0.0012225596001371741, | |
| "learning_rate": 7.390476190476191e-05, | |
| "loss": 0.0002, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 31.61904761904762, | |
| "grad_norm": 0.0014577023684978485, | |
| "learning_rate": 7.352380952380953e-05, | |
| "loss": 0.0002, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 31.714285714285715, | |
| "grad_norm": 0.0013582691317424178, | |
| "learning_rate": 7.314285714285715e-05, | |
| "loss": 0.0002, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 31.80952380952381, | |
| "grad_norm": 0.0012123368214815855, | |
| "learning_rate": 7.276190476190476e-05, | |
| "loss": 0.0002, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 31.904761904761905, | |
| "grad_norm": 0.0010037291795015335, | |
| "learning_rate": 7.238095238095238e-05, | |
| "loss": 0.0002, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 0.0009882493177428842, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0002, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 32.095238095238095, | |
| "grad_norm": 0.0012192854192107916, | |
| "learning_rate": 7.161904761904761e-05, | |
| "loss": 0.0002, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 32.19047619047619, | |
| "grad_norm": 0.0009681668598204851, | |
| "learning_rate": 7.123809523809524e-05, | |
| "loss": 0.0002, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 32.285714285714285, | |
| "grad_norm": 0.0011292980052530766, | |
| "learning_rate": 7.085714285714285e-05, | |
| "loss": 0.0002, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 32.38095238095238, | |
| "grad_norm": 0.0011293385177850723, | |
| "learning_rate": 7.047619047619048e-05, | |
| "loss": 0.0002, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 32.38095238095238, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10757561773061752, | |
| "eval_runtime": 1.8354, | |
| "eval_samples_per_second": 49.035, | |
| "eval_steps_per_second": 6.538, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 32.476190476190474, | |
| "grad_norm": 0.0009184961672872305, | |
| "learning_rate": 7.00952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "grad_norm": 0.0011140161659568548, | |
| "learning_rate": 6.971428571428572e-05, | |
| "loss": 0.0002, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 32.666666666666664, | |
| "grad_norm": 0.0012074244441464543, | |
| "learning_rate": 6.933333333333334e-05, | |
| "loss": 0.0002, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 32.76190476190476, | |
| "grad_norm": 0.0012676432961598039, | |
| "learning_rate": 6.895238095238095e-05, | |
| "loss": 0.0002, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 32.857142857142854, | |
| "grad_norm": 0.0009437103872187436, | |
| "learning_rate": 6.857142857142858e-05, | |
| "loss": 0.0002, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 32.95238095238095, | |
| "grad_norm": 0.001345638302154839, | |
| "learning_rate": 6.81904761904762e-05, | |
| "loss": 0.0002, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 33.04761904761905, | |
| "grad_norm": 0.00113866466563195, | |
| "learning_rate": 6.78095238095238e-05, | |
| "loss": 0.0002, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 33.142857142857146, | |
| "grad_norm": 0.0009679365321062505, | |
| "learning_rate": 6.742857142857143e-05, | |
| "loss": 0.0002, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 33.23809523809524, | |
| "grad_norm": 0.0012656382750719786, | |
| "learning_rate": 6.704761904761904e-05, | |
| "loss": 0.0002, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 33.333333333333336, | |
| "grad_norm": 0.001031440100632608, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0002, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 33.42857142857143, | |
| "grad_norm": 0.001157620339654386, | |
| "learning_rate": 6.628571428571428e-05, | |
| "loss": 0.0002, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 33.523809523809526, | |
| "grad_norm": 0.0010731277288869023, | |
| "learning_rate": 6.590476190476191e-05, | |
| "loss": 0.0002, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 33.61904761904762, | |
| "grad_norm": 0.0011366941034793854, | |
| "learning_rate": 6.552380952380953e-05, | |
| "loss": 0.0002, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "grad_norm": 0.0013157216599211097, | |
| "learning_rate": 6.514285714285715e-05, | |
| "loss": 0.0002, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 33.80952380952381, | |
| "grad_norm": 0.0010640494292601943, | |
| "learning_rate": 6.476190476190477e-05, | |
| "loss": 0.0002, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 33.904761904761905, | |
| "grad_norm": 0.0012097526341676712, | |
| "learning_rate": 6.438095238095238e-05, | |
| "loss": 0.0002, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "grad_norm": 0.0012352203484624624, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0002, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 34.095238095238095, | |
| "grad_norm": 0.001014663022942841, | |
| "learning_rate": 6.361904761904762e-05, | |
| "loss": 0.0002, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 34.19047619047619, | |
| "grad_norm": 0.000992208020761609, | |
| "learning_rate": 6.323809523809524e-05, | |
| "loss": 0.0002, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 0.0012252111919224262, | |
| "learning_rate": 6.285714285714286e-05, | |
| "loss": 0.0002, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.10851490497589111, | |
| "eval_runtime": 1.8318, | |
| "eval_samples_per_second": 49.133, | |
| "eval_steps_per_second": 6.551, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 34.38095238095238, | |
| "grad_norm": 0.0012392353964969516, | |
| "learning_rate": 6.247619047619047e-05, | |
| "loss": 0.0002, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 34.476190476190474, | |
| "grad_norm": 0.0008700903854332864, | |
| "learning_rate": 6.20952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 34.57142857142857, | |
| "grad_norm": 0.0009972532279789448, | |
| "learning_rate": 6.171428571428571e-05, | |
| "loss": 0.0002, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 34.666666666666664, | |
| "grad_norm": 0.0014592469669878483, | |
| "learning_rate": 6.133333333333334e-05, | |
| "loss": 0.0002, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 34.76190476190476, | |
| "grad_norm": 0.0011641691671684384, | |
| "learning_rate": 6.0952380952380964e-05, | |
| "loss": 0.0002, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "grad_norm": 0.0009100461611524224, | |
| "learning_rate": 6.0571428571428576e-05, | |
| "loss": 0.0002, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 34.95238095238095, | |
| "grad_norm": 0.0011103765573352575, | |
| "learning_rate": 6.0190476190476195e-05, | |
| "loss": 0.0002, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 35.04761904761905, | |
| "grad_norm": 0.0011417733039706945, | |
| "learning_rate": 5.9809523809523814e-05, | |
| "loss": 0.0002, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 35.142857142857146, | |
| "grad_norm": 0.0008825441473163664, | |
| "learning_rate": 5.9428571428571434e-05, | |
| "loss": 0.0002, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 35.23809523809524, | |
| "grad_norm": 0.0008468070300295949, | |
| "learning_rate": 5.904761904761905e-05, | |
| "loss": 0.0002, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 35.333333333333336, | |
| "grad_norm": 0.0014315639855340123, | |
| "learning_rate": 5.866666666666667e-05, | |
| "loss": 0.0002, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 35.42857142857143, | |
| "grad_norm": 0.0010620001703500748, | |
| "learning_rate": 5.828571428571429e-05, | |
| "loss": 0.0002, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 35.523809523809526, | |
| "grad_norm": 0.00082821847172454, | |
| "learning_rate": 5.7904761904761903e-05, | |
| "loss": 0.0002, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 35.61904761904762, | |
| "grad_norm": 0.000930080539546907, | |
| "learning_rate": 5.752380952380952e-05, | |
| "loss": 0.0002, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 35.714285714285715, | |
| "grad_norm": 0.000944595318287611, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.0002, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 35.80952380952381, | |
| "grad_norm": 0.0010321176378056407, | |
| "learning_rate": 5.676190476190476e-05, | |
| "loss": 0.0002, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 35.904761904761905, | |
| "grad_norm": 0.0009443181334063411, | |
| "learning_rate": 5.638095238095238e-05, | |
| "loss": 0.0002, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "grad_norm": 0.0008352543227374554, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0002, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 36.095238095238095, | |
| "grad_norm": 0.0007994563202373683, | |
| "learning_rate": 5.5619047619047625e-05, | |
| "loss": 0.0002, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 36.19047619047619, | |
| "grad_norm": 0.0008572720107622445, | |
| "learning_rate": 5.5238095238095244e-05, | |
| "loss": 0.0002, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 36.19047619047619, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.1094062477350235, | |
| "eval_runtime": 1.8295, | |
| "eval_samples_per_second": 49.193, | |
| "eval_steps_per_second": 6.559, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 36.285714285714285, | |
| "grad_norm": 0.0009728225413709879, | |
| "learning_rate": 5.485714285714286e-05, | |
| "loss": 0.0002, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 36.38095238095238, | |
| "grad_norm": 0.0011266552610322833, | |
| "learning_rate": 5.447619047619048e-05, | |
| "loss": 0.0002, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 36.476190476190474, | |
| "grad_norm": 0.0009526413050480187, | |
| "learning_rate": 5.40952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "grad_norm": 0.0007942409138195217, | |
| "learning_rate": 5.3714285714285714e-05, | |
| "loss": 0.0002, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 36.666666666666664, | |
| "grad_norm": 0.0009218246559612453, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.0002, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 36.76190476190476, | |
| "grad_norm": 0.0008944288128986955, | |
| "learning_rate": 5.295238095238095e-05, | |
| "loss": 0.0002, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 36.857142857142854, | |
| "grad_norm": 0.0008252193219959736, | |
| "learning_rate": 5.257142857142857e-05, | |
| "loss": 0.0002, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 36.95238095238095, | |
| "grad_norm": 0.0009241864900104702, | |
| "learning_rate": 5.219047619047619e-05, | |
| "loss": 0.0002, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 37.04761904761905, | |
| "grad_norm": 0.0007993332110345364, | |
| "learning_rate": 5.180952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 37.142857142857146, | |
| "grad_norm": 0.0009513382683508098, | |
| "learning_rate": 5.142857142857143e-05, | |
| "loss": 0.0002, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 37.23809523809524, | |
| "grad_norm": 0.0008134011295624077, | |
| "learning_rate": 5.1047619047619055e-05, | |
| "loss": 0.0002, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 37.333333333333336, | |
| "grad_norm": 0.0007803480257280171, | |
| "learning_rate": 5.0666666666666674e-05, | |
| "loss": 0.0002, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 37.42857142857143, | |
| "grad_norm": 0.0008066293084993958, | |
| "learning_rate": 5.028571428571429e-05, | |
| "loss": 0.0002, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 37.523809523809526, | |
| "grad_norm": 0.0008810302242636681, | |
| "learning_rate": 4.990476190476191e-05, | |
| "loss": 0.0002, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 37.61904761904762, | |
| "grad_norm": 0.0008202865719795227, | |
| "learning_rate": 4.9523809523809525e-05, | |
| "loss": 0.0002, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "grad_norm": 0.0007757614948786795, | |
| "learning_rate": 4.9142857142857144e-05, | |
| "loss": 0.0002, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 37.80952380952381, | |
| "grad_norm": 0.0009324646671302617, | |
| "learning_rate": 4.876190476190476e-05, | |
| "loss": 0.0002, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 37.904761904761905, | |
| "grad_norm": 0.0007676425157114863, | |
| "learning_rate": 4.838095238095238e-05, | |
| "loss": 0.0002, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "grad_norm": 0.0008473495254293084, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0002, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 38.095238095238095, | |
| "grad_norm": 0.0007627870072610676, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.0002, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 38.095238095238095, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.11017631739377975, | |
| "eval_runtime": 1.8465, | |
| "eval_samples_per_second": 48.741, | |
| "eval_steps_per_second": 6.499, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 38.19047619047619, | |
| "grad_norm": 0.0007254486554302275, | |
| "learning_rate": 4.723809523809524e-05, | |
| "loss": 0.0002, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 38.285714285714285, | |
| "grad_norm": 0.0008534742519259453, | |
| "learning_rate": 4.685714285714286e-05, | |
| "loss": 0.0002, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 38.38095238095238, | |
| "grad_norm": 0.0007635552901774645, | |
| "learning_rate": 4.647619047619048e-05, | |
| "loss": 0.0002, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 38.476190476190474, | |
| "grad_norm": 0.0010159806115552783, | |
| "learning_rate": 4.60952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 38.57142857142857, | |
| "grad_norm": 0.0007377223810181022, | |
| "learning_rate": 4.5714285714285716e-05, | |
| "loss": 0.0002, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 38.666666666666664, | |
| "grad_norm": 0.0010273950174450874, | |
| "learning_rate": 4.5333333333333335e-05, | |
| "loss": 0.0002, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 38.76190476190476, | |
| "grad_norm": 0.000953736191149801, | |
| "learning_rate": 4.4952380952380954e-05, | |
| "loss": 0.0002, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "grad_norm": 0.0009074874105863273, | |
| "learning_rate": 4.4571428571428574e-05, | |
| "loss": 0.0002, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 38.95238095238095, | |
| "grad_norm": 0.0007781241438351572, | |
| "learning_rate": 4.419047619047619e-05, | |
| "loss": 0.0002, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 39.04761904761905, | |
| "grad_norm": 0.0009704057010821998, | |
| "learning_rate": 4.380952380952381e-05, | |
| "loss": 0.0002, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 39.142857142857146, | |
| "grad_norm": 0.0009193214937113225, | |
| "learning_rate": 4.342857142857143e-05, | |
| "loss": 0.0002, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 39.23809523809524, | |
| "grad_norm": 0.0008385624387301505, | |
| "learning_rate": 4.304761904761905e-05, | |
| "loss": 0.0002, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 39.333333333333336, | |
| "grad_norm": 0.0007323011523112655, | |
| "learning_rate": 4.266666666666667e-05, | |
| "loss": 0.0002, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 39.42857142857143, | |
| "grad_norm": 0.0008326193783432245, | |
| "learning_rate": 4.228571428571429e-05, | |
| "loss": 0.0002, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 39.523809523809526, | |
| "grad_norm": 0.0008311218698509037, | |
| "learning_rate": 4.190476190476191e-05, | |
| "loss": 0.0002, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 39.61904761904762, | |
| "grad_norm": 0.0007343490142375231, | |
| "learning_rate": 4.152380952380953e-05, | |
| "loss": 0.0002, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 39.714285714285715, | |
| "grad_norm": 0.0009105184581130743, | |
| "learning_rate": 4.1142857142857146e-05, | |
| "loss": 0.0002, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 39.80952380952381, | |
| "grad_norm": 0.0007879959302954376, | |
| "learning_rate": 4.0761904761904765e-05, | |
| "loss": 0.0002, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 39.904761904761905, | |
| "grad_norm": 0.0007109796861186624, | |
| "learning_rate": 4.038095238095238e-05, | |
| "loss": 0.0002, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.0007509748684242368, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0002, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.11086996644735336, | |
| "eval_runtime": 1.8475, | |
| "eval_samples_per_second": 48.714, | |
| "eval_steps_per_second": 6.495, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 40.095238095238095, | |
| "grad_norm": 0.0010089341085404158, | |
| "learning_rate": 3.961904761904762e-05, | |
| "loss": 0.0002, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 40.19047619047619, | |
| "grad_norm": 0.0007556586642749608, | |
| "learning_rate": 3.923809523809524e-05, | |
| "loss": 0.0002, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 40.285714285714285, | |
| "grad_norm": 0.0007263517472893, | |
| "learning_rate": 3.885714285714286e-05, | |
| "loss": 0.0002, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 40.38095238095238, | |
| "grad_norm": 0.0008545771706849337, | |
| "learning_rate": 3.847619047619048e-05, | |
| "loss": 0.0002, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 40.476190476190474, | |
| "grad_norm": 0.0008646562346257269, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.0002, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "grad_norm": 0.0007060840725898743, | |
| "learning_rate": 3.771428571428572e-05, | |
| "loss": 0.0002, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 40.666666666666664, | |
| "grad_norm": 0.0007277781842276454, | |
| "learning_rate": 3.733333333333334e-05, | |
| "loss": 0.0002, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 40.76190476190476, | |
| "grad_norm": 0.0010175186907872558, | |
| "learning_rate": 3.6952380952380956e-05, | |
| "loss": 0.0001, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 40.857142857142854, | |
| "grad_norm": 0.0009386471356265247, | |
| "learning_rate": 3.6571428571428576e-05, | |
| "loss": 0.0001, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 40.95238095238095, | |
| "grad_norm": 0.0007330653606913984, | |
| "learning_rate": 3.619047619047619e-05, | |
| "loss": 0.0002, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 41.04761904761905, | |
| "grad_norm": 0.0008852286846376956, | |
| "learning_rate": 3.580952380952381e-05, | |
| "loss": 0.0001, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 41.142857142857146, | |
| "grad_norm": 0.0009342824923805892, | |
| "learning_rate": 3.5428571428571426e-05, | |
| "loss": 0.0001, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 41.23809523809524, | |
| "grad_norm": 0.0008903538691811264, | |
| "learning_rate": 3.504761904761905e-05, | |
| "loss": 0.0002, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 41.333333333333336, | |
| "grad_norm": 0.0006828682380728424, | |
| "learning_rate": 3.466666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 41.42857142857143, | |
| "grad_norm": 0.000780183938331902, | |
| "learning_rate": 3.428571428571429e-05, | |
| "loss": 0.0001, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 41.523809523809526, | |
| "grad_norm": 0.0009877218399196863, | |
| "learning_rate": 3.39047619047619e-05, | |
| "loss": 0.0001, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 41.61904761904762, | |
| "grad_norm": 0.0007818534504622221, | |
| "learning_rate": 3.352380952380952e-05, | |
| "loss": 0.0001, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "grad_norm": 0.0006546444492414594, | |
| "learning_rate": 3.314285714285714e-05, | |
| "loss": 0.0001, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 41.80952380952381, | |
| "grad_norm": 0.0007944191456772387, | |
| "learning_rate": 3.276190476190477e-05, | |
| "loss": 0.0001, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 41.904761904761905, | |
| "grad_norm": 0.0006942673353478312, | |
| "learning_rate": 3.2380952380952386e-05, | |
| "loss": 0.0001, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 41.904761904761905, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.11148204654455185, | |
| "eval_runtime": 1.8434, | |
| "eval_samples_per_second": 48.823, | |
| "eval_steps_per_second": 6.51, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "grad_norm": 0.0008669897215440869, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0001, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 42.095238095238095, | |
| "grad_norm": 0.0007241725688800216, | |
| "learning_rate": 3.161904761904762e-05, | |
| "loss": 0.0001, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 42.19047619047619, | |
| "grad_norm": 0.0008397718193009496, | |
| "learning_rate": 3.123809523809524e-05, | |
| "loss": 0.0001, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 42.285714285714285, | |
| "grad_norm": 0.0007834116113372147, | |
| "learning_rate": 3.0857142857142856e-05, | |
| "loss": 0.0001, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 42.38095238095238, | |
| "grad_norm": 0.0009772803168743849, | |
| "learning_rate": 3.0476190476190482e-05, | |
| "loss": 0.0001, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 42.476190476190474, | |
| "grad_norm": 0.0007001584745012224, | |
| "learning_rate": 3.0095238095238098e-05, | |
| "loss": 0.0001, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 42.57142857142857, | |
| "grad_norm": 0.0008121193968690932, | |
| "learning_rate": 2.9714285714285717e-05, | |
| "loss": 0.0001, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 42.666666666666664, | |
| "grad_norm": 0.0006435776012949646, | |
| "learning_rate": 2.9333333333333336e-05, | |
| "loss": 0.0001, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 42.76190476190476, | |
| "grad_norm": 0.0010832067346200347, | |
| "learning_rate": 2.8952380952380952e-05, | |
| "loss": 0.0001, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "grad_norm": 0.0006701053935103118, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0001, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 42.95238095238095, | |
| "grad_norm": 0.0007622128468938172, | |
| "learning_rate": 2.819047619047619e-05, | |
| "loss": 0.0001, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 43.04761904761905, | |
| "grad_norm": 0.0007341467426158488, | |
| "learning_rate": 2.7809523809523813e-05, | |
| "loss": 0.0001, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 43.142857142857146, | |
| "grad_norm": 0.0007610942702740431, | |
| "learning_rate": 2.742857142857143e-05, | |
| "loss": 0.0001, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 43.23809523809524, | |
| "grad_norm": 0.0007467956165783107, | |
| "learning_rate": 2.704761904761905e-05, | |
| "loss": 0.0001, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 43.333333333333336, | |
| "grad_norm": 0.0007558921934105456, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 43.42857142857143, | |
| "grad_norm": 0.0008046693401411176, | |
| "learning_rate": 2.6285714285714286e-05, | |
| "loss": 0.0001, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 43.523809523809526, | |
| "grad_norm": 0.0007924986421130598, | |
| "learning_rate": 2.5904761904761905e-05, | |
| "loss": 0.0001, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 43.61904761904762, | |
| "grad_norm": 0.0011153355007991195, | |
| "learning_rate": 2.5523809523809527e-05, | |
| "loss": 0.0001, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 43.714285714285715, | |
| "grad_norm": 0.0007819057791493833, | |
| "learning_rate": 2.5142857142857147e-05, | |
| "loss": 0.0001, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 43.80952380952381, | |
| "grad_norm": 0.0006839752313680947, | |
| "learning_rate": 2.4761904761904762e-05, | |
| "loss": 0.0001, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 43.80952380952381, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.11195480823516846, | |
| "eval_runtime": 1.8452, | |
| "eval_samples_per_second": 48.775, | |
| "eval_steps_per_second": 6.503, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 43.904761904761905, | |
| "grad_norm": 0.0006490392261184752, | |
| "learning_rate": 2.438095238095238e-05, | |
| "loss": 0.0001, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "grad_norm": 0.0006691650487482548, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0001, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 44.095238095238095, | |
| "grad_norm": 0.0006612730794586241, | |
| "learning_rate": 2.361904761904762e-05, | |
| "loss": 0.0001, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 44.19047619047619, | |
| "grad_norm": 0.0006687341374345124, | |
| "learning_rate": 2.323809523809524e-05, | |
| "loss": 0.0001, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 44.285714285714285, | |
| "grad_norm": 0.000751995830796659, | |
| "learning_rate": 2.2857142857142858e-05, | |
| "loss": 0.0001, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 44.38095238095238, | |
| "grad_norm": 0.0009191849385388196, | |
| "learning_rate": 2.2476190476190477e-05, | |
| "loss": 0.0001, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 44.476190476190474, | |
| "grad_norm": 0.0008872562320902944, | |
| "learning_rate": 2.2095238095238096e-05, | |
| "loss": 0.0001, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "grad_norm": 0.000788130157161504, | |
| "learning_rate": 2.1714285714285715e-05, | |
| "loss": 0.0001, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 44.666666666666664, | |
| "grad_norm": 0.0007296500261873007, | |
| "learning_rate": 2.1333333333333335e-05, | |
| "loss": 0.0001, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 44.76190476190476, | |
| "grad_norm": 0.0008190677035599947, | |
| "learning_rate": 2.0952380952380954e-05, | |
| "loss": 0.0001, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 44.857142857142854, | |
| "grad_norm": 0.0009061350137926638, | |
| "learning_rate": 2.0571428571428573e-05, | |
| "loss": 0.0001, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 44.95238095238095, | |
| "grad_norm": 0.0007253763033077121, | |
| "learning_rate": 2.019047619047619e-05, | |
| "loss": 0.0001, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 45.04761904761905, | |
| "grad_norm": 0.0006586099625565112, | |
| "learning_rate": 1.980952380952381e-05, | |
| "loss": 0.0001, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 45.142857142857146, | |
| "grad_norm": 0.0007679408881813288, | |
| "learning_rate": 1.942857142857143e-05, | |
| "loss": 0.0001, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 45.23809523809524, | |
| "grad_norm": 0.0009877935517579317, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.0001, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 45.333333333333336, | |
| "grad_norm": 0.0008212144020944834, | |
| "learning_rate": 1.866666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 45.42857142857143, | |
| "grad_norm": 0.0006325696012936532, | |
| "learning_rate": 1.8285714285714288e-05, | |
| "loss": 0.0001, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 45.523809523809526, | |
| "grad_norm": 0.0007727151387371123, | |
| "learning_rate": 1.7904761904761904e-05, | |
| "loss": 0.0001, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 45.61904761904762, | |
| "grad_norm": 0.0006608827970921993, | |
| "learning_rate": 1.7523809523809526e-05, | |
| "loss": 0.0001, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 0.0008016705978661776, | |
| "learning_rate": 1.7142857142857145e-05, | |
| "loss": 0.0001, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.11235320568084717, | |
| "eval_runtime": 1.8079, | |
| "eval_samples_per_second": 49.781, | |
| "eval_steps_per_second": 6.637, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 45.80952380952381, | |
| "grad_norm": 0.0008740043849684298, | |
| "learning_rate": 1.676190476190476e-05, | |
| "loss": 0.0001, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 45.904761904761905, | |
| "grad_norm": 0.0009258101927116513, | |
| "learning_rate": 1.6380952380952384e-05, | |
| "loss": 0.0001, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "grad_norm": 0.0007650377810932696, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0001, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 46.095238095238095, | |
| "grad_norm": 0.0007820361643098295, | |
| "learning_rate": 1.561904761904762e-05, | |
| "loss": 0.0001, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 46.19047619047619, | |
| "grad_norm": 0.0006327033624984324, | |
| "learning_rate": 1.5238095238095241e-05, | |
| "loss": 0.0001, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 46.285714285714285, | |
| "grad_norm": 0.0007727622287347913, | |
| "learning_rate": 1.4857142857142858e-05, | |
| "loss": 0.0001, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 46.38095238095238, | |
| "grad_norm": 0.0006060252198949456, | |
| "learning_rate": 1.4476190476190476e-05, | |
| "loss": 0.0001, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 46.476190476190474, | |
| "grad_norm": 0.000793405924923718, | |
| "learning_rate": 1.4095238095238095e-05, | |
| "loss": 0.0001, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 46.57142857142857, | |
| "grad_norm": 0.0007343300967477262, | |
| "learning_rate": 1.3714285714285716e-05, | |
| "loss": 0.0001, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 46.666666666666664, | |
| "grad_norm": 0.0009806802263483405, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0001, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 46.76190476190476, | |
| "grad_norm": 0.0006576115265488625, | |
| "learning_rate": 1.2952380952380952e-05, | |
| "loss": 0.0001, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "grad_norm": 0.0007760386797599494, | |
| "learning_rate": 1.2571428571428573e-05, | |
| "loss": 0.0001, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 46.95238095238095, | |
| "grad_norm": 0.0007948974962346256, | |
| "learning_rate": 1.219047619047619e-05, | |
| "loss": 0.0001, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 47.04761904761905, | |
| "grad_norm": 0.0008850232698023319, | |
| "learning_rate": 1.180952380952381e-05, | |
| "loss": 0.0001, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 47.142857142857146, | |
| "grad_norm": 0.0007019540062174201, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.0001, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 47.23809523809524, | |
| "grad_norm": 0.0007577179931104183, | |
| "learning_rate": 1.1047619047619048e-05, | |
| "loss": 0.0001, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 47.333333333333336, | |
| "grad_norm": 0.0007162214606069028, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 47.42857142857143, | |
| "grad_norm": 0.000699568830896169, | |
| "learning_rate": 1.0285714285714286e-05, | |
| "loss": 0.0001, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 47.523809523809526, | |
| "grad_norm": 0.000961513607762754, | |
| "learning_rate": 9.904761904761906e-06, | |
| "loss": 0.0001, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 47.61904761904762, | |
| "grad_norm": 0.0005918592214584351, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.0001, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 47.61904761904762, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.11264392733573914, | |
| "eval_runtime": 1.8561, | |
| "eval_samples_per_second": 48.488, | |
| "eval_steps_per_second": 6.465, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 47.714285714285715, | |
| "grad_norm": 0.0006434314418584108, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 0.0001, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 47.80952380952381, | |
| "grad_norm": 0.0006416920805349946, | |
| "learning_rate": 8.761904761904763e-06, | |
| "loss": 0.0001, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 47.904761904761905, | |
| "grad_norm": 0.0007464751834049821, | |
| "learning_rate": 8.38095238095238e-06, | |
| "loss": 0.0001, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "grad_norm": 0.000763778924010694, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 48.095238095238095, | |
| "grad_norm": 0.0008269811514765024, | |
| "learning_rate": 7.6190476190476205e-06, | |
| "loss": 0.0001, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 48.19047619047619, | |
| "grad_norm": 0.0006118237506598234, | |
| "learning_rate": 7.238095238095238e-06, | |
| "loss": 0.0001, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 48.285714285714285, | |
| "grad_norm": 0.0008503893623128533, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 0.0001, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 48.38095238095238, | |
| "grad_norm": 0.0006232542800717056, | |
| "learning_rate": 6.476190476190476e-06, | |
| "loss": 0.0001, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 48.476190476190474, | |
| "grad_norm": 0.000681752513628453, | |
| "learning_rate": 6.095238095238095e-06, | |
| "loss": 0.0001, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "grad_norm": 0.000718344992492348, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.0001, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 48.666666666666664, | |
| "grad_norm": 0.0007572112372145057, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 48.76190476190476, | |
| "grad_norm": 0.0008033942431211472, | |
| "learning_rate": 4.952380952380953e-06, | |
| "loss": 0.0001, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 48.857142857142854, | |
| "grad_norm": 0.000867675116751343, | |
| "learning_rate": 4.571428571428572e-06, | |
| "loss": 0.0001, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 48.95238095238095, | |
| "grad_norm": 0.0007653015200048685, | |
| "learning_rate": 4.19047619047619e-06, | |
| "loss": 0.0001, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 49.04761904761905, | |
| "grad_norm": 0.0006012205849401653, | |
| "learning_rate": 3.8095238095238102e-06, | |
| "loss": 0.0001, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 49.142857142857146, | |
| "grad_norm": 0.0005881601828150451, | |
| "learning_rate": 3.428571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 49.23809523809524, | |
| "grad_norm": 0.0008206645725294948, | |
| "learning_rate": 3.0476190476190477e-06, | |
| "loss": 0.0001, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 49.333333333333336, | |
| "grad_norm": 0.0007485048263333738, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 49.42857142857143, | |
| "grad_norm": 0.0005919121904298663, | |
| "learning_rate": 2.285714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 49.523809523809526, | |
| "grad_norm": 0.0006956812576390803, | |
| "learning_rate": 1.9047619047619051e-06, | |
| "loss": 0.0001, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 49.523809523809526, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_loss": 0.1127605214715004, | |
| "eval_runtime": 1.808, | |
| "eval_samples_per_second": 49.78, | |
| "eval_steps_per_second": 6.637, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 49.61904761904762, | |
| "grad_norm": 0.0008306634263135493, | |
| "learning_rate": 1.5238095238095238e-06, | |
| "loss": 0.0001, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "grad_norm": 0.0006198016344569623, | |
| "learning_rate": 1.142857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 49.80952380952381, | |
| "grad_norm": 0.0007093180320225656, | |
| "learning_rate": 7.619047619047619e-07, | |
| "loss": 0.0001, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 49.904761904761905, | |
| "grad_norm": 0.0008815843611955643, | |
| "learning_rate": 3.8095238095238096e-07, | |
| "loss": 0.0001, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 0.000766765559092164, | |
| "learning_rate": 0.0, | |
| "loss": 0.0001, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 5250, | |
| "total_flos": 1.62739012294656e+18, | |
| "train_loss": 0.02240182710744973, | |
| "train_runtime": 1187.3846, | |
| "train_samples_per_second": 17.686, | |
| "train_steps_per_second": 4.421 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.62739012294656e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |