| { | |
| "best_metric": 0.9592959295929593, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1227", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1227, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 8.624119758605957, | |
| "learning_rate": 4.0650406504065046e-06, | |
| "loss": 1.1456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 10.445067405700684, | |
| "learning_rate": 8.130081300813009e-06, | |
| "loss": 1.0943, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 8.588050842285156, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 1.0114, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 13.745179176330566, | |
| "learning_rate": 1.6260162601626018e-05, | |
| "loss": 0.9088, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 16.390989303588867, | |
| "learning_rate": 2.032520325203252e-05, | |
| "loss": 0.8678, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 23.49904441833496, | |
| "learning_rate": 2.4390243902439026e-05, | |
| "loss": 0.6711, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 15.184337615966797, | |
| "learning_rate": 2.8455284552845528e-05, | |
| "loss": 0.5926, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 31.39984703063965, | |
| "learning_rate": 3.2520325203252037e-05, | |
| "loss": 0.5689, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 11.041800498962402, | |
| "learning_rate": 3.6585365853658535e-05, | |
| "loss": 0.5543, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 23.220727920532227, | |
| "learning_rate": 4.065040650406504e-05, | |
| "loss": 0.4727, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 7.919190406799316, | |
| "learning_rate": 4.4715447154471546e-05, | |
| "loss": 0.4859, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 17.01369285583496, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 0.4051, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 7.333168983459473, | |
| "learning_rate": 4.968297101449276e-05, | |
| "loss": 0.4138, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 11.308248519897461, | |
| "learning_rate": 4.9230072463768114e-05, | |
| "loss": 0.4285, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 15.314751625061035, | |
| "learning_rate": 4.8777173913043476e-05, | |
| "loss": 0.3061, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 30.280778884887695, | |
| "learning_rate": 4.8324275362318844e-05, | |
| "loss": 0.4037, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 9.863381385803223, | |
| "learning_rate": 4.7871376811594205e-05, | |
| "loss": 0.2954, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 25.285860061645508, | |
| "learning_rate": 4.741847826086957e-05, | |
| "loss": 0.3745, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 9.545634269714355, | |
| "learning_rate": 4.696557971014493e-05, | |
| "loss": 0.4062, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 20.92987060546875, | |
| "learning_rate": 4.651268115942029e-05, | |
| "loss": 0.365, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 9.27026081085205, | |
| "learning_rate": 4.6059782608695657e-05, | |
| "loss": 0.2602, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 12.594367980957031, | |
| "learning_rate": 4.560688405797102e-05, | |
| "loss": 0.3196, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 18.245967864990234, | |
| "learning_rate": 4.515398550724638e-05, | |
| "loss": 0.3375, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 22.912260055541992, | |
| "learning_rate": 4.470108695652174e-05, | |
| "loss": 0.2464, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 18.069555282592773, | |
| "learning_rate": 4.42481884057971e-05, | |
| "loss": 0.5225, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 4.701681613922119, | |
| "learning_rate": 4.379528985507246e-05, | |
| "loss": 0.4517, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 8.533316612243652, | |
| "learning_rate": 4.334239130434783e-05, | |
| "loss": 0.3102, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 13.00133991241455, | |
| "learning_rate": 4.288949275362319e-05, | |
| "loss": 0.2733, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 11.808174133300781, | |
| "learning_rate": 4.243659420289855e-05, | |
| "loss": 0.3279, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 3.255472183227539, | |
| "learning_rate": 4.1983695652173914e-05, | |
| "loss": 0.2222, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 18.238956451416016, | |
| "learning_rate": 4.1530797101449276e-05, | |
| "loss": 0.2738, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 6.426773548126221, | |
| "learning_rate": 4.1077898550724644e-05, | |
| "loss": 0.2553, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 11.917569160461426, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 0.3049, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 8.527942657470703, | |
| "learning_rate": 4.017210144927536e-05, | |
| "loss": 0.3218, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 12.122479438781738, | |
| "learning_rate": 3.971920289855073e-05, | |
| "loss": 0.2399, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 9.603090286254883, | |
| "learning_rate": 3.926630434782609e-05, | |
| "loss": 0.2811, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 5.066426753997803, | |
| "learning_rate": 3.881340579710145e-05, | |
| "loss": 0.2594, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 18.739673614501953, | |
| "learning_rate": 3.836050724637682e-05, | |
| "loss": 0.244, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 17.591327667236328, | |
| "learning_rate": 3.790760869565217e-05, | |
| "loss": 0.3675, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 12.923001289367676, | |
| "learning_rate": 3.745471014492754e-05, | |
| "loss": 0.3065, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9471947194719472, | |
| "eval_loss": 0.15252229571342468, | |
| "eval_runtime": 6.4388, | |
| "eval_samples_per_second": 141.175, | |
| "eval_steps_per_second": 28.266, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.585595607757568, | |
| "learning_rate": 3.70018115942029e-05, | |
| "loss": 0.2302, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 9.591753005981445, | |
| "learning_rate": 3.654891304347826e-05, | |
| "loss": 0.2185, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 18.43389320373535, | |
| "learning_rate": 3.6096014492753624e-05, | |
| "loss": 0.1938, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 13.575929641723633, | |
| "learning_rate": 3.5643115942028985e-05, | |
| "loss": 0.2622, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 18.06717300415039, | |
| "learning_rate": 3.5190217391304346e-05, | |
| "loss": 0.4565, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 8.216936111450195, | |
| "learning_rate": 3.4737318840579714e-05, | |
| "loss": 0.2695, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 9.777605056762695, | |
| "learning_rate": 3.4284420289855076e-05, | |
| "loss": 0.2196, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 14.722864151000977, | |
| "learning_rate": 3.383152173913044e-05, | |
| "loss": 0.3281, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 6.793803691864014, | |
| "learning_rate": 3.33786231884058e-05, | |
| "loss": 0.2514, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 12.138315200805664, | |
| "learning_rate": 3.292572463768116e-05, | |
| "loss": 0.2029, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 9.416603088378906, | |
| "learning_rate": 3.247282608695653e-05, | |
| "loss": 0.2635, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 9.601762771606445, | |
| "learning_rate": 3.201992753623189e-05, | |
| "loss": 0.1661, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 5.231688022613525, | |
| "learning_rate": 3.156702898550725e-05, | |
| "loss": 0.2205, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 6.3703532218933105, | |
| "learning_rate": 3.111413043478261e-05, | |
| "loss": 0.2531, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 14.850451469421387, | |
| "learning_rate": 3.066123188405797e-05, | |
| "loss": 0.1995, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 14.940292358398438, | |
| "learning_rate": 3.0208333333333334e-05, | |
| "loss": 0.2991, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 18.384620666503906, | |
| "learning_rate": 2.9755434782608698e-05, | |
| "loss": 0.1576, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 8.814579963684082, | |
| "learning_rate": 2.930253623188406e-05, | |
| "loss": 0.2447, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 9.285147666931152, | |
| "learning_rate": 2.884963768115942e-05, | |
| "loss": 0.1615, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 7.262125015258789, | |
| "learning_rate": 2.8396739130434785e-05, | |
| "loss": 0.1979, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 1.0271364450454712, | |
| "learning_rate": 2.7943840579710146e-05, | |
| "loss": 0.18, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 15.003844261169434, | |
| "learning_rate": 2.749094202898551e-05, | |
| "loss": 0.1752, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 25.77374267578125, | |
| "learning_rate": 2.7038043478260872e-05, | |
| "loss": 0.1326, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 33.20709228515625, | |
| "learning_rate": 2.6585144927536234e-05, | |
| "loss": 0.3093, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 11.408818244934082, | |
| "learning_rate": 2.6132246376811598e-05, | |
| "loss": 0.2182, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 2.7263596057891846, | |
| "learning_rate": 2.567934782608696e-05, | |
| "loss": 0.1294, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 3.28471302986145, | |
| "learning_rate": 2.5226449275362317e-05, | |
| "loss": 0.2335, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 9.495030403137207, | |
| "learning_rate": 2.4773550724637682e-05, | |
| "loss": 0.191, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 15.677921295166016, | |
| "learning_rate": 2.4320652173913043e-05, | |
| "loss": 0.201, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 10.669686317443848, | |
| "learning_rate": 2.3867753623188408e-05, | |
| "loss": 0.2334, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 22.738924026489258, | |
| "learning_rate": 2.341485507246377e-05, | |
| "loss": 0.2054, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 13.700279235839844, | |
| "learning_rate": 2.296195652173913e-05, | |
| "loss": 0.2358, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 8.795063018798828, | |
| "learning_rate": 2.2509057971014495e-05, | |
| "loss": 0.2259, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 13.257553100585938, | |
| "learning_rate": 2.2056159420289856e-05, | |
| "loss": 0.2174, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 16.352462768554688, | |
| "learning_rate": 2.1603260869565217e-05, | |
| "loss": 0.1939, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 9.414634704589844, | |
| "learning_rate": 2.1150362318840582e-05, | |
| "loss": 0.1856, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 12.655200958251953, | |
| "learning_rate": 2.0697463768115943e-05, | |
| "loss": 0.2237, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 8.855188369750977, | |
| "learning_rate": 2.0244565217391308e-05, | |
| "loss": 0.2063, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.29552894830703735, | |
| "learning_rate": 1.9791666666666665e-05, | |
| "loss": 0.1005, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 2.12908935546875, | |
| "learning_rate": 1.933876811594203e-05, | |
| "loss": 0.1538, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 8.586709022521973, | |
| "learning_rate": 1.888586956521739e-05, | |
| "loss": 0.1745, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9570957095709571, | |
| "eval_loss": 0.12920857965946198, | |
| "eval_runtime": 6.4383, | |
| "eval_samples_per_second": 141.187, | |
| "eval_steps_per_second": 28.268, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 20.99432373046875, | |
| "learning_rate": 1.8432971014492756e-05, | |
| "loss": 0.2031, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 11.791101455688477, | |
| "learning_rate": 1.7980072463768117e-05, | |
| "loss": 0.1351, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 4.006465435028076, | |
| "learning_rate": 1.752717391304348e-05, | |
| "loss": 0.1164, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 5.286161422729492, | |
| "learning_rate": 1.7074275362318843e-05, | |
| "loss": 0.1593, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 5.119263648986816, | |
| "learning_rate": 1.66213768115942e-05, | |
| "loss": 0.0819, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 7.2655253410339355, | |
| "learning_rate": 1.6168478260869565e-05, | |
| "loss": 0.0936, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 21.422300338745117, | |
| "learning_rate": 1.571557971014493e-05, | |
| "loss": 0.1586, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 20.841064453125, | |
| "learning_rate": 1.526268115942029e-05, | |
| "loss": 0.2057, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 5.252929210662842, | |
| "learning_rate": 1.4809782608695653e-05, | |
| "loss": 0.1781, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 23.310047149658203, | |
| "learning_rate": 1.4356884057971015e-05, | |
| "loss": 0.1749, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 2.4795796871185303, | |
| "learning_rate": 1.3903985507246378e-05, | |
| "loss": 0.2178, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 8.616735458374023, | |
| "learning_rate": 1.3451086956521738e-05, | |
| "loss": 0.2184, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 11.104738235473633, | |
| "learning_rate": 1.2998188405797101e-05, | |
| "loss": 0.088, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 11.91581916809082, | |
| "learning_rate": 1.2545289855072464e-05, | |
| "loss": 0.2445, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 1.7576195001602173, | |
| "learning_rate": 1.2092391304347827e-05, | |
| "loss": 0.1298, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 9.120392799377441, | |
| "learning_rate": 1.163949275362319e-05, | |
| "loss": 0.1935, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 13.665518760681152, | |
| "learning_rate": 1.1186594202898551e-05, | |
| "loss": 0.1689, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 19.75223731994629, | |
| "learning_rate": 1.0733695652173914e-05, | |
| "loss": 0.142, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 8.352010726928711, | |
| "learning_rate": 1.0280797101449275e-05, | |
| "loss": 0.2239, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 21.5345516204834, | |
| "learning_rate": 9.827898550724638e-06, | |
| "loss": 0.2238, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 8.045764923095703, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.1246, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 8.87646770477295, | |
| "learning_rate": 8.922101449275362e-06, | |
| "loss": 0.0863, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 11.654149055480957, | |
| "learning_rate": 8.469202898550725e-06, | |
| "loss": 0.0846, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 0.8430119156837463, | |
| "learning_rate": 8.016304347826086e-06, | |
| "loss": 0.1514, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 1.686838984489441, | |
| "learning_rate": 7.56340579710145e-06, | |
| "loss": 0.0937, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 31.7119140625, | |
| "learning_rate": 7.110507246376811e-06, | |
| "loss": 0.1698, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 12.519082069396973, | |
| "learning_rate": 6.657608695652175e-06, | |
| "loss": 0.1635, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 0.5338079333305359, | |
| "learning_rate": 6.204710144927536e-06, | |
| "loss": 0.0695, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "grad_norm": 22.285619735717773, | |
| "learning_rate": 5.751811594202898e-06, | |
| "loss": 0.1957, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 9.996444702148438, | |
| "learning_rate": 5.298913043478261e-06, | |
| "loss": 0.2182, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 5.337853908538818, | |
| "learning_rate": 4.846014492753623e-06, | |
| "loss": 0.089, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 6.16534948348999, | |
| "learning_rate": 4.393115942028985e-06, | |
| "loss": 0.1833, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 0.6340013742446899, | |
| "learning_rate": 3.940217391304348e-06, | |
| "loss": 0.1684, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 17.78191375732422, | |
| "learning_rate": 3.4873188405797104e-06, | |
| "loss": 0.211, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 6.65162992477417, | |
| "learning_rate": 3.0344202898550725e-06, | |
| "loss": 0.1569, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 14.574379920959473, | |
| "learning_rate": 2.581521739130435e-06, | |
| "loss": 0.1173, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 6.665879249572754, | |
| "learning_rate": 2.1286231884057975e-06, | |
| "loss": 0.1795, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "grad_norm": 2.035705327987671, | |
| "learning_rate": 1.6757246376811596e-06, | |
| "loss": 0.201, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 5.481184482574463, | |
| "learning_rate": 1.2228260869565218e-06, | |
| "loss": 0.127, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 19.509849548339844, | |
| "learning_rate": 7.699275362318841e-07, | |
| "loss": 0.1226, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 9.846253395080566, | |
| "learning_rate": 3.170289855072464e-07, | |
| "loss": 0.1562, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9592959295929593, | |
| "eval_loss": 0.11152195930480957, | |
| "eval_runtime": 6.4385, | |
| "eval_samples_per_second": 141.182, | |
| "eval_steps_per_second": 28.267, | |
| "step": 1227 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1227, | |
| "total_flos": 6.096847334287933e+17, | |
| "train_loss": 0.2716238140671255, | |
| "train_runtime": 385.934, | |
| "train_samples_per_second": 63.555, | |
| "train_steps_per_second": 3.179 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1227, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 6.096847334287933e+17, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |