| { | |
| "best_metric": 0.929384965831435, | |
| "best_model_checkpoint": "mobilenet_v2_1.0_224-cxr-view/checkpoint-2518", | |
| "epoch": 29.863013698630137, | |
| "global_step": 3270, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.5290519877675842e-07, | |
| "loss": 0.7183, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.0581039755351683e-07, | |
| "loss": 0.6605, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.587155963302753e-07, | |
| "loss": 0.6883, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.116207951070337e-07, | |
| "loss": 0.719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.645259938837921e-07, | |
| "loss": 0.6913, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.174311926605506e-07, | |
| "loss": 0.6944, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.070336391437309e-06, | |
| "loss": 0.6874, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.2232415902140673e-06, | |
| "loss": 0.7119, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.3761467889908258e-06, | |
| "loss": 0.7093, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.5290519877675841e-06, | |
| "loss": 0.7049, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.744874715261959, | |
| "eval_loss": 0.6746256351470947, | |
| "eval_runtime": 15.5928, | |
| "eval_samples_per_second": 28.154, | |
| "eval_steps_per_second": 7.055, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6819571865443426e-06, | |
| "loss": 0.6907, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.8348623853211011e-06, | |
| "loss": 0.6767, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.9877675840978594e-06, | |
| "loss": 0.6906, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.140672782874618e-06, | |
| "loss": 0.6775, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2935779816513764e-06, | |
| "loss": 0.6731, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.4464831804281347e-06, | |
| "loss": 0.6895, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.599388379204893e-06, | |
| "loss": 0.6679, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.7522935779816517e-06, | |
| "loss": 0.6846, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.90519877675841e-06, | |
| "loss": 0.6737, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.0581039755351682e-06, | |
| "loss": 0.6588, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.211009174311927e-06, | |
| "loss": 0.6565, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6742596810933941, | |
| "eval_loss": 0.6498312950134277, | |
| "eval_runtime": 15.6514, | |
| "eval_samples_per_second": 28.049, | |
| "eval_steps_per_second": 7.028, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.3639143730886852e-06, | |
| "loss": 0.6365, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.5168195718654435e-06, | |
| "loss": 0.6319, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.6697247706422022e-06, | |
| "loss": 0.613, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.8226299694189605e-06, | |
| "loss": 0.6312, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 3.975535168195719e-06, | |
| "loss": 0.631, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.128440366972478e-06, | |
| "loss": 0.6364, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.281345565749236e-06, | |
| "loss": 0.6092, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.4342507645259945e-06, | |
| "loss": 0.6348, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.587155963302753e-06, | |
| "loss": 0.6171, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.740061162079511e-06, | |
| "loss": 0.5771, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 4.892966360856269e-06, | |
| "loss": 0.5699, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7995444191343963, | |
| "eval_loss": 0.5730286836624146, | |
| "eval_runtime": 15.9142, | |
| "eval_samples_per_second": 27.586, | |
| "eval_steps_per_second": 6.912, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.994903160040775e-06, | |
| "loss": 0.5787, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.977913693510024e-06, | |
| "loss": 0.5584, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.960924226979273e-06, | |
| "loss": 0.5662, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 4.943934760448522e-06, | |
| "loss": 0.5853, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.926945293917771e-06, | |
| "loss": 0.5639, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 4.909955827387021e-06, | |
| "loss": 0.5507, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 4.892966360856269e-06, | |
| "loss": 0.5051, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 4.875976894325519e-06, | |
| "loss": 0.5559, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 4.858987427794767e-06, | |
| "loss": 0.5184, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.841997961264017e-06, | |
| "loss": 0.5453, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 4.825008494733266e-06, | |
| "loss": 0.5702, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8086560364464692, | |
| "eval_loss": 0.5119441747665405, | |
| "eval_runtime": 15.7264, | |
| "eval_samples_per_second": 27.915, | |
| "eval_steps_per_second": 6.995, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.808019028202515e-06, | |
| "loss": 0.4758, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.7910295616717635e-06, | |
| "loss": 0.52, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 4.774040095141013e-06, | |
| "loss": 0.5039, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.757050628610262e-06, | |
| "loss": 0.4593, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.740061162079511e-06, | |
| "loss": 0.5111, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 4.72307169554876e-06, | |
| "loss": 0.5149, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.706082229018009e-06, | |
| "loss": 0.4369, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 4.689092762487259e-06, | |
| "loss": 0.5214, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 4.672103295956507e-06, | |
| "loss": 0.4627, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 4.655113829425757e-06, | |
| "loss": 0.461, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 4.638124362895005e-06, | |
| "loss": 0.4849, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8678815489749431, | |
| "eval_loss": 0.43555235862731934, | |
| "eval_runtime": 15.6016, | |
| "eval_samples_per_second": 28.138, | |
| "eval_steps_per_second": 7.051, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.621134896364255e-06, | |
| "loss": 0.4744, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 4.604145429833503e-06, | |
| "loss": 0.4267, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 4.587155963302753e-06, | |
| "loss": 0.4546, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 4.570166496772001e-06, | |
| "loss": 0.3955, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 4.553177030241251e-06, | |
| "loss": 0.4499, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 4.5361875637104995e-06, | |
| "loss": 0.4315, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 4.519198097179749e-06, | |
| "loss": 0.4542, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 4.502208630648998e-06, | |
| "loss": 0.5297, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 4.485219164118247e-06, | |
| "loss": 0.4189, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 4.4682296975874964e-06, | |
| "loss": 0.43, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 4.451240231056745e-06, | |
| "loss": 0.356, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8086560364464692, | |
| "eval_loss": 0.4640910029411316, | |
| "eval_runtime": 15.7608, | |
| "eval_samples_per_second": 27.854, | |
| "eval_steps_per_second": 6.979, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 4.4342507645259945e-06, | |
| "loss": 0.4923, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 4.417261297995243e-06, | |
| "loss": 0.464, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 4.400271831464492e-06, | |
| "loss": 0.3965, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 4.383282364933741e-06, | |
| "loss": 0.4148, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 4.366292898402991e-06, | |
| "loss": 0.3874, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 4.349303431872239e-06, | |
| "loss": 0.3694, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 4.332313965341489e-06, | |
| "loss": 0.4263, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.315324498810738e-06, | |
| "loss": 0.3835, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 4.298335032279987e-06, | |
| "loss": 0.4637, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 4.281345565749236e-06, | |
| "loss": 0.3923, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 4.264356099218485e-06, | |
| "loss": 0.3713, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8678815489749431, | |
| "eval_loss": 0.3406853675842285, | |
| "eval_runtime": 15.6486, | |
| "eval_samples_per_second": 28.054, | |
| "eval_steps_per_second": 7.029, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 4.247366632687734e-06, | |
| "loss": 0.5575, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 4.230377166156983e-06, | |
| "loss": 0.4175, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 4.2133876996262315e-06, | |
| "loss": 0.4288, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 4.196398233095481e-06, | |
| "loss": 0.3972, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 4.17940876656473e-06, | |
| "loss": 0.354, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 4.162419300033979e-06, | |
| "loss": 0.3354, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 4.1454298335032285e-06, | |
| "loss": 0.3047, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 4.128440366972478e-06, | |
| "loss": 0.4096, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 4.1114509004417265e-06, | |
| "loss": 0.4209, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 4.094461433910976e-06, | |
| "loss": 0.3988, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 4.077471967380225e-06, | |
| "loss": 0.4571, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7813211845102506, | |
| "eval_loss": 0.48959481716156006, | |
| "eval_runtime": 15.6588, | |
| "eval_samples_per_second": 28.035, | |
| "eval_steps_per_second": 7.025, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 4.060482500849473e-06, | |
| "loss": 0.4078, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 4.043493034318723e-06, | |
| "loss": 0.3905, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.026503567787971e-06, | |
| "loss": 0.4258, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 4.009514101257221e-06, | |
| "loss": 0.3991, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 3.99252463472647e-06, | |
| "loss": 0.3783, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 3.975535168195719e-06, | |
| "loss": 0.4471, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 3.958545701664968e-06, | |
| "loss": 0.3437, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 3.941556235134218e-06, | |
| "loss": 0.3779, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 3.924566768603466e-06, | |
| "loss": 0.2581, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 3.907577302072715e-06, | |
| "loss": 0.3267, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 3.890587835541964e-06, | |
| "loss": 0.3896, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8883826879271071, | |
| "eval_loss": 0.3124327063560486, | |
| "eval_runtime": 15.6592, | |
| "eval_samples_per_second": 28.035, | |
| "eval_steps_per_second": 7.025, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 3.873598369011213e-06, | |
| "loss": 0.3471, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 3.8566089024804624e-06, | |
| "loss": 0.396, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 3.839619435949711e-06, | |
| "loss": 0.3502, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.8226299694189605e-06, | |
| "loss": 0.3685, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 3.80564050288821e-06, | |
| "loss": 0.3023, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 3.7886510363574586e-06, | |
| "loss": 0.3511, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 3.771661569826708e-06, | |
| "loss": 0.3186, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 3.7546721032959566e-06, | |
| "loss": 0.4063, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 3.7376826367652057e-06, | |
| "loss": 0.3553, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 3.720693170234455e-06, | |
| "loss": 0.3771, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.3422, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9271070615034168, | |
| "eval_loss": 0.27909907698631287, | |
| "eval_runtime": 15.6791, | |
| "eval_samples_per_second": 27.999, | |
| "eval_steps_per_second": 7.016, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 3.686714237172953e-06, | |
| "loss": 0.3242, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 3.6697247706422022e-06, | |
| "loss": 0.3179, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 3.6527353041114513e-06, | |
| "loss": 0.3971, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 3.6357458375807003e-06, | |
| "loss": 0.3813, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 3.6187563710499497e-06, | |
| "loss": 0.3048, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 3.6017669045191984e-06, | |
| "loss": 0.3852, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 3.5847774379884474e-06, | |
| "loss": 0.3157, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 3.5677879714576964e-06, | |
| "loss": 0.3868, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 3.5507985049269455e-06, | |
| "loss": 0.3309, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 3.533809038396195e-06, | |
| "loss": 0.3372, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 3.5168195718654435e-06, | |
| "loss": 0.3358, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8246013667425968, | |
| "eval_loss": 0.39981135725975037, | |
| "eval_runtime": 15.5765, | |
| "eval_samples_per_second": 28.183, | |
| "eval_steps_per_second": 7.062, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 3.499830105334693e-06, | |
| "loss": 0.2943, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 3.482840638803942e-06, | |
| "loss": 0.4242, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 3.4658511722731906e-06, | |
| "loss": 0.2678, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 3.44886170574244e-06, | |
| "loss": 0.3375, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 3.4318722392116887e-06, | |
| "loss": 0.3046, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 3.414882772680938e-06, | |
| "loss": 0.3193, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 3.397893306150187e-06, | |
| "loss": 0.3037, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 3.380903839619436e-06, | |
| "loss": 0.2976, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 3.3639143730886852e-06, | |
| "loss": 0.4232, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 3.3469249065579347e-06, | |
| "loss": 0.3512, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 3.3299354400271833e-06, | |
| "loss": 0.3658, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9066059225512528, | |
| "eval_loss": 0.27161121368408203, | |
| "eval_runtime": 15.5481, | |
| "eval_samples_per_second": 28.235, | |
| "eval_steps_per_second": 7.075, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 3.3129459734964323e-06, | |
| "loss": 0.2998, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 3.2959565069656818e-06, | |
| "loss": 0.3566, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 3.2789670404349304e-06, | |
| "loss": 0.39, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 3.26197757390418e-06, | |
| "loss": 0.2815, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 3.2449881073734285e-06, | |
| "loss": 0.2475, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 3.227998640842678e-06, | |
| "loss": 0.386, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 3.211009174311927e-06, | |
| "loss": 0.328, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 3.1940197077811756e-06, | |
| "loss": 0.355, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 3.177030241250425e-06, | |
| "loss": 0.3311, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 3.1600407747196745e-06, | |
| "loss": 0.3144, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 3.143051308188923e-06, | |
| "loss": 0.4547, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7972665148063781, | |
| "eval_loss": 0.5827615261077881, | |
| "eval_runtime": 15.5305, | |
| "eval_samples_per_second": 28.267, | |
| "eval_steps_per_second": 7.083, | |
| "step": 1423 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 3.126061841658172e-06, | |
| "loss": 0.3003, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 3.109072375127421e-06, | |
| "loss": 0.3906, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 3.09208290859667e-06, | |
| "loss": 0.2784, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.0750934420659196e-06, | |
| "loss": 0.2384, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 3.0581039755351682e-06, | |
| "loss": 0.4107, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 3.0411145090044177e-06, | |
| "loss": 0.3306, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 3.0241250424736667e-06, | |
| "loss": 0.3872, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 3.0071355759429153e-06, | |
| "loss": 0.3002, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 2.990146109412165e-06, | |
| "loss": 0.3406, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 2.973156642881414e-06, | |
| "loss": 0.3361, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 2.956167176350663e-06, | |
| "loss": 0.2615, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8542141230068337, | |
| "eval_loss": 0.34459054470062256, | |
| "eval_runtime": 14.8701, | |
| "eval_samples_per_second": 29.522, | |
| "eval_steps_per_second": 7.397, | |
| "step": 1533 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 2.939177709819912e-06, | |
| "loss": 0.2604, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 2.922188243289161e-06, | |
| "loss": 0.3445, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 2.90519877675841e-06, | |
| "loss": 0.3383, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 2.8882093102276594e-06, | |
| "loss": 0.4095, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 2.871219843696908e-06, | |
| "loss": 0.3362, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 2.854230377166157e-06, | |
| "loss": 0.2658, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 2.8372409106354065e-06, | |
| "loss": 0.2915, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 2.820251444104655e-06, | |
| "loss": 0.3663, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 2.8032619775739046e-06, | |
| "loss": 0.3091, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 2.786272511043153e-06, | |
| "loss": 0.3601, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 2.7692830445124026e-06, | |
| "loss": 0.377, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7312072892938497, | |
| "eval_loss": 0.6321907043457031, | |
| "eval_runtime": 15.6486, | |
| "eval_samples_per_second": 28.054, | |
| "eval_steps_per_second": 7.029, | |
| "step": 1642 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 2.7522935779816517e-06, | |
| "loss": 0.3173, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 2.7353041114509003e-06, | |
| "loss": 0.4798, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 2.7183146449201497e-06, | |
| "loss": 0.2549, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "learning_rate": 2.701325178389399e-06, | |
| "loss": 0.4005, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 2.684335711858648e-06, | |
| "loss": 0.3434, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 2.667346245327897e-06, | |
| "loss": 0.2837, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 2.6503567787971463e-06, | |
| "loss": 0.299, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 2.633367312266395e-06, | |
| "loss": 0.2967, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.6163778457356444e-06, | |
| "loss": 0.2949, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 2.599388379204893e-06, | |
| "loss": 0.3071, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 2.5823989126741424e-06, | |
| "loss": 0.2846, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9248291571753986, | |
| "eval_loss": 0.26208364963531494, | |
| "eval_runtime": 15.5182, | |
| "eval_samples_per_second": 28.289, | |
| "eval_steps_per_second": 7.088, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 2.5654094461433915e-06, | |
| "loss": 0.3589, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.54841997961264e-06, | |
| "loss": 0.3031, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 2.5314305130818895e-06, | |
| "loss": 0.4131, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 2.5144410465511385e-06, | |
| "loss": 0.2396, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 2.4974515800203876e-06, | |
| "loss": 0.31, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 2.4804621134896366e-06, | |
| "loss": 0.3869, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 2.4634726469588856e-06, | |
| "loss": 0.2514, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 2.4464831804281347e-06, | |
| "loss": 0.3087, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.4294937138973837e-06, | |
| "loss": 0.2488, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 2.412504247366633e-06, | |
| "loss": 0.3072, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 2.3955147808358818e-06, | |
| "loss": 0.3433, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8382687927107062, | |
| "eval_loss": 0.37089645862579346, | |
| "eval_runtime": 15.1226, | |
| "eval_samples_per_second": 29.029, | |
| "eval_steps_per_second": 7.274, | |
| "step": 1861 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 2.378525314305131e-06, | |
| "loss": 0.2911, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 2.36153584777438e-06, | |
| "loss": 0.2909, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 2.3445463812436293e-06, | |
| "loss": 0.3273, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 2.3275569147128783e-06, | |
| "loss": 0.2219, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 2.3105674481821274e-06, | |
| "loss": 0.4021, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 2.2935779816513764e-06, | |
| "loss": 0.3224, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 2.2765885151206254e-06, | |
| "loss": 0.4674, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 2.2595990485898745e-06, | |
| "loss": 0.382, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 2.2426095820591235e-06, | |
| "loss": 0.2151, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 2.2256201155283725e-06, | |
| "loss": 0.3831, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 2.2086306489976216e-06, | |
| "loss": 0.2851, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7312072892938497, | |
| "eval_loss": 0.8134105205535889, | |
| "eval_runtime": 15.5297, | |
| "eval_samples_per_second": 28.268, | |
| "eval_steps_per_second": 7.083, | |
| "step": 1971 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 2.1916411824668706e-06, | |
| "loss": 0.2192, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 2.1746517159361196e-06, | |
| "loss": 0.2858, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "learning_rate": 2.157662249405369e-06, | |
| "loss": 0.3613, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 2.140672782874618e-06, | |
| "loss": 0.2634, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 2.123683316343867e-06, | |
| "loss": 0.2932, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 2.1066938498131157e-06, | |
| "loss": 0.2533, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 2.089704383282365e-06, | |
| "loss": 0.3337, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.0727149167516142e-06, | |
| "loss": 0.4353, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 2.0557254502208633e-06, | |
| "loss": 0.3477, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 2.0387359836901123e-06, | |
| "loss": 0.2786, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.0217465171593613e-06, | |
| "loss": 0.2298, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8314350797266514, | |
| "eval_loss": 0.4324374198913574, | |
| "eval_runtime": 15.4736, | |
| "eval_samples_per_second": 28.371, | |
| "eval_steps_per_second": 7.109, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 2.0047570506286104e-06, | |
| "loss": 0.3369, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "learning_rate": 1.9877675840978594e-06, | |
| "loss": 0.3051, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 1.970778117567109e-06, | |
| "loss": 0.2775, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.9537886510363575e-06, | |
| "loss": 0.2708, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 1.9367991845056065e-06, | |
| "loss": 0.2424, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 1.9198097179748555e-06, | |
| "loss": 0.3806, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 1.902820251444105e-06, | |
| "loss": 0.3573, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 1.885830784913354e-06, | |
| "loss": 0.34, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 1.8688413183826028e-06, | |
| "loss": 0.3165, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.2916, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.8348623853211011e-06, | |
| "loss": 0.3916, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.835990888382688, | |
| "eval_loss": 0.3630986213684082, | |
| "eval_runtime": 15.5226, | |
| "eval_samples_per_second": 28.281, | |
| "eval_steps_per_second": 7.086, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 1.8178729187903501e-06, | |
| "loss": 0.2495, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 20.18, | |
| "learning_rate": 1.8008834522595992e-06, | |
| "loss": 0.3902, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 1.7838939857288482e-06, | |
| "loss": 0.3424, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 20.37, | |
| "learning_rate": 1.7669045191980975e-06, | |
| "loss": 0.3917, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 20.46, | |
| "learning_rate": 1.7499150526673465e-06, | |
| "loss": 0.3536, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 1.7329255861365953e-06, | |
| "loss": 0.4027, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 1.7159361196058443e-06, | |
| "loss": 0.3398, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 1.6989466530750936e-06, | |
| "loss": 0.2889, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "learning_rate": 1.6819571865443426e-06, | |
| "loss": 0.2609, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 20.91, | |
| "learning_rate": 1.6649677200135916e-06, | |
| "loss": 0.3049, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8633257403189066, | |
| "eval_loss": 0.34050509333610535, | |
| "eval_runtime": 15.539, | |
| "eval_samples_per_second": 28.251, | |
| "eval_steps_per_second": 7.079, | |
| "step": 2299 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.6479782534828409e-06, | |
| "loss": 0.3258, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 21.1, | |
| "learning_rate": 1.63098878695209e-06, | |
| "loss": 0.3284, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 1.613999320421339e-06, | |
| "loss": 0.2377, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 1.5970098538905878e-06, | |
| "loss": 0.2422, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 1.5800203873598372e-06, | |
| "loss": 0.3573, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 1.563030920829086e-06, | |
| "loss": 0.328, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 21.55, | |
| "learning_rate": 1.546041454298335e-06, | |
| "loss": 0.2921, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 1.5290519877675841e-06, | |
| "loss": 0.3243, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 21.74, | |
| "learning_rate": 1.5120625212368334e-06, | |
| "loss": 0.276, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 21.83, | |
| "learning_rate": 1.4950730547060824e-06, | |
| "loss": 0.4304, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.4780835881753314e-06, | |
| "loss": 0.3068, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9020501138952164, | |
| "eval_loss": 0.2584730386734009, | |
| "eval_runtime": 15.0297, | |
| "eval_samples_per_second": 29.209, | |
| "eval_steps_per_second": 7.319, | |
| "step": 2409 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 1.4610941216445805e-06, | |
| "loss": 0.2891, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 22.1, | |
| "learning_rate": 1.4441046551138297e-06, | |
| "loss": 0.2476, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 22.19, | |
| "learning_rate": 1.4271151885830785e-06, | |
| "loss": 0.4231, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 1.4101257220523276e-06, | |
| "loss": 0.3402, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 22.37, | |
| "learning_rate": 1.3931362555215766e-06, | |
| "loss": 0.2521, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "learning_rate": 1.3761467889908258e-06, | |
| "loss": 0.2561, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 1.3591573224600749e-06, | |
| "loss": 0.3374, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 22.65, | |
| "learning_rate": 1.342167855929324e-06, | |
| "loss": 0.2368, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 22.74, | |
| "learning_rate": 1.3251783893985731e-06, | |
| "loss": 0.2519, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 22.83, | |
| "learning_rate": 1.3081889228678222e-06, | |
| "loss": 0.3171, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "learning_rate": 1.2911994563370712e-06, | |
| "loss": 0.3091, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.929384965831435, | |
| "eval_loss": 0.22778519988059998, | |
| "eval_runtime": 15.3862, | |
| "eval_samples_per_second": 28.532, | |
| "eval_steps_per_second": 7.149, | |
| "step": 2518 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 1.27420998980632e-06, | |
| "loss": 0.3511, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 1.2572205232755693e-06, | |
| "loss": 0.3207, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.2402310567448183e-06, | |
| "loss": 0.2925, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 23.29, | |
| "learning_rate": 1.2232415902140673e-06, | |
| "loss": 0.2371, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 1.2062521236833166e-06, | |
| "loss": 0.291, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 1.1892626571525654e-06, | |
| "loss": 0.2599, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 23.56, | |
| "learning_rate": 1.1722731906218146e-06, | |
| "loss": 0.3854, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 23.65, | |
| "learning_rate": 1.1552837240910637e-06, | |
| "loss": 0.3169, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "learning_rate": 1.1382942575603127e-06, | |
| "loss": 0.2974, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.1213047910295617e-06, | |
| "loss": 0.3056, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 1.1043153244988108e-06, | |
| "loss": 0.2749, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9043280182232346, | |
| "eval_loss": 0.29632171988487244, | |
| "eval_runtime": 15.3925, | |
| "eval_samples_per_second": 28.52, | |
| "eval_steps_per_second": 7.146, | |
| "step": 2628 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 1.0873258579680598e-06, | |
| "loss": 0.2837, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 24.11, | |
| "learning_rate": 1.070336391437309e-06, | |
| "loss": 0.2906, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 1.0533469249065579e-06, | |
| "loss": 0.2831, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 1.0363574583758071e-06, | |
| "loss": 0.2712, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 24.38, | |
| "learning_rate": 1.0193679918450562e-06, | |
| "loss": 0.2971, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 24.47, | |
| "learning_rate": 1.0023785253143052e-06, | |
| "loss": 0.2782, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "learning_rate": 9.853890587835544e-07, | |
| "loss": 0.2694, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 24.66, | |
| "learning_rate": 9.683995922528032e-07, | |
| "loss": 0.3956, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 9.514101257220525e-07, | |
| "loss": 0.2838, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 9.344206591913014e-07, | |
| "loss": 0.3524, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 24.93, | |
| "learning_rate": 9.174311926605506e-07, | |
| "loss": 0.3543, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.89749430523918, | |
| "eval_loss": 0.2636982798576355, | |
| "eval_runtime": 15.4509, | |
| "eval_samples_per_second": 28.413, | |
| "eval_steps_per_second": 7.119, | |
| "step": 2737 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 9.004417261297996e-07, | |
| "loss": 0.2743, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 8.834522595990487e-07, | |
| "loss": 0.3054, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "learning_rate": 8.664627930682977e-07, | |
| "loss": 0.2331, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 8.494733265375468e-07, | |
| "loss": 0.2292, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 25.39, | |
| "learning_rate": 8.324838600067958e-07, | |
| "loss": 0.3069, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 25.48, | |
| "learning_rate": 8.15494393476045e-07, | |
| "loss": 0.3656, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 7.985049269452939e-07, | |
| "loss": 0.3221, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 25.66, | |
| "learning_rate": 7.81515460414543e-07, | |
| "loss": 0.2209, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 7.645259938837921e-07, | |
| "loss": 0.3988, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 25.84, | |
| "learning_rate": 7.475365273530412e-07, | |
| "loss": 0.2766, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "learning_rate": 7.305470608222902e-07, | |
| "loss": 0.3024, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8997722095671982, | |
| "eval_loss": 0.2966226637363434, | |
| "eval_runtime": 15.5278, | |
| "eval_samples_per_second": 28.272, | |
| "eval_steps_per_second": 7.084, | |
| "step": 2847 | |
| }, | |
| { | |
| "epoch": 26.03, | |
| "learning_rate": 7.135575942915393e-07, | |
| "loss": 0.2659, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 26.12, | |
| "learning_rate": 6.965681277607883e-07, | |
| "loss": 0.32, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 26.21, | |
| "learning_rate": 6.795786612300374e-07, | |
| "loss": 0.3336, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 26.3, | |
| "learning_rate": 6.625891946992866e-07, | |
| "loss": 0.2326, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 6.455997281685356e-07, | |
| "loss": 0.2657, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 26.48, | |
| "learning_rate": 6.286102616377846e-07, | |
| "loss": 0.3482, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "learning_rate": 6.116207951070337e-07, | |
| "loss": 0.3089, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 5.946313285762827e-07, | |
| "loss": 0.2407, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 5.776418620455318e-07, | |
| "loss": 0.2431, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 5.606523955147809e-07, | |
| "loss": 0.3574, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 5.436629289840299e-07, | |
| "loss": 0.2593, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8542141230068337, | |
| "eval_loss": 0.38415804505348206, | |
| "eval_runtime": 15.5444, | |
| "eval_samples_per_second": 28.242, | |
| "eval_steps_per_second": 7.077, | |
| "step": 2956 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 5.266734624532789e-07, | |
| "loss": 0.1965, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 27.12, | |
| "learning_rate": 5.096839959225281e-07, | |
| "loss": 0.3291, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "learning_rate": 4.926945293917772e-07, | |
| "loss": 0.3044, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 27.31, | |
| "learning_rate": 4.7570506286102625e-07, | |
| "loss": 0.238, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "learning_rate": 4.587155963302753e-07, | |
| "loss": 0.2551, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 27.49, | |
| "learning_rate": 4.4172612979952436e-07, | |
| "loss": 0.3306, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 4.247366632687734e-07, | |
| "loss": 0.3372, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 27.67, | |
| "learning_rate": 4.077471967380225e-07, | |
| "loss": 0.2652, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 3.907577302072715e-07, | |
| "loss": 0.2628, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 27.85, | |
| "learning_rate": 3.737682636765206e-07, | |
| "loss": 0.3093, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 3.5677879714576963e-07, | |
| "loss": 0.1979, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8883826879271071, | |
| "eval_loss": 0.2710832953453064, | |
| "eval_runtime": 15.5551, | |
| "eval_samples_per_second": 28.222, | |
| "eval_steps_per_second": 7.072, | |
| "step": 3066 | |
| }, | |
| { | |
| "epoch": 28.04, | |
| "learning_rate": 3.397893306150187e-07, | |
| "loss": 0.3079, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 28.13, | |
| "learning_rate": 3.227998640842678e-07, | |
| "loss": 0.2954, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 28.22, | |
| "learning_rate": 3.0581039755351683e-07, | |
| "loss": 0.2696, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 28.31, | |
| "learning_rate": 2.888209310227659e-07, | |
| "loss": 0.2861, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 2.7183146449201495e-07, | |
| "loss": 0.3212, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 28.49, | |
| "learning_rate": 2.5484199796126404e-07, | |
| "loss": 0.3397, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 28.58, | |
| "learning_rate": 2.3785253143051312e-07, | |
| "loss": 0.1939, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "learning_rate": 2.2086306489976218e-07, | |
| "loss": 0.258, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 28.77, | |
| "learning_rate": 2.0387359836901124e-07, | |
| "loss": 0.2138, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "learning_rate": 1.868841318382603e-07, | |
| "loss": 0.2533, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 1.6989466530750936e-07, | |
| "loss": 0.2549, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8633257403189066, | |
| "eval_loss": 0.3145107626914978, | |
| "eval_runtime": 15.5449, | |
| "eval_samples_per_second": 28.241, | |
| "eval_steps_per_second": 7.076, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 29.04, | |
| "learning_rate": 1.5290519877675842e-07, | |
| "loss": 0.3133, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 29.13, | |
| "learning_rate": 1.3591573224600748e-07, | |
| "loss": 0.2734, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "learning_rate": 1.1892626571525656e-07, | |
| "loss": 0.2771, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "learning_rate": 1.0193679918450562e-07, | |
| "loss": 0.292, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "learning_rate": 8.494733265375468e-08, | |
| "loss": 0.3424, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 6.795786612300374e-08, | |
| "loss": 0.282, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 29.59, | |
| "learning_rate": 5.096839959225281e-08, | |
| "loss": 0.2225, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 3.397893306150187e-08, | |
| "loss": 0.2768, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 29.77, | |
| "learning_rate": 1.6989466530750935e-08, | |
| "loss": 0.364, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.3216, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "eval_accuracy": 0.8154897494305239, | |
| "eval_loss": 0.4564669728279114, | |
| "eval_runtime": 15.3193, | |
| "eval_samples_per_second": 28.657, | |
| "eval_steps_per_second": 7.181, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "step": 3270, | |
| "total_flos": 2.1986190125590118e+18, | |
| "train_loss": 0.3750012589521729, | |
| "train_runtime": 3633.2931, | |
| "train_samples_per_second": 14.466, | |
| "train_steps_per_second": 0.9 | |
| } | |
| ], | |
| "max_steps": 3270, | |
| "num_train_epochs": 30, | |
| "total_flos": 2.1986190125590118e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |