| { | |
| "best_metric": 0.966893039049236, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-spa_saloon_classification/checkpoint-498", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 830, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.0120481927710846e-06, | |
| "loss": 1.9163, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.024096385542169e-06, | |
| "loss": 1.8781, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.036144578313253e-06, | |
| "loss": 1.7858, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.2048192771084338e-05, | |
| "loss": 1.7063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5060240963855424e-05, | |
| "loss": 1.5479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.8072289156626505e-05, | |
| "loss": 1.3958, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.1084337349397593e-05, | |
| "loss": 1.1757, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.4096385542168677e-05, | |
| "loss": 0.9676, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.7108433734939758e-05, | |
| "loss": 0.7777, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.012048192771085e-05, | |
| "loss": 0.6423, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.313253012048193e-05, | |
| "loss": 0.6183, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.614457831325301e-05, | |
| "loss": 0.5876, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.91566265060241e-05, | |
| "loss": 0.5514, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.2168674698795186e-05, | |
| "loss": 0.49, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.5180722891566266e-05, | |
| "loss": 0.4859, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.8192771084337354e-05, | |
| "loss": 0.4613, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8718166383701188, | |
| "eval_loss": 0.33570152521133423, | |
| "eval_runtime": 7.7999, | |
| "eval_samples_per_second": 151.027, | |
| "eval_steps_per_second": 4.744, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.98661311914324e-05, | |
| "loss": 0.4352, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.953145917001339e-05, | |
| "loss": 0.4174, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.919678714859438e-05, | |
| "loss": 0.4291, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.886211512717537e-05, | |
| "loss": 0.3423, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.8527443105756356e-05, | |
| "loss": 0.3444, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.8192771084337354e-05, | |
| "loss": 0.3321, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.7858099062918345e-05, | |
| "loss": 0.3671, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.7523427041499336e-05, | |
| "loss": 0.3157, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.718875502008032e-05, | |
| "loss": 0.3427, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.685408299866131e-05, | |
| "loss": 0.3368, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.651941097724231e-05, | |
| "loss": 0.3249, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.61847389558233e-05, | |
| "loss": 0.3338, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.5850066934404284e-05, | |
| "loss": 0.3542, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.5515394912985275e-05, | |
| "loss": 0.2853, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.5180722891566266e-05, | |
| "loss": 0.2825, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 4.484605087014726e-05, | |
| "loss": 0.3617, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.451137884872825e-05, | |
| "loss": 0.2908, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.931239388794567, | |
| "eval_loss": 0.18052884936332703, | |
| "eval_runtime": 7.8584, | |
| "eval_samples_per_second": 149.903, | |
| "eval_steps_per_second": 4.708, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.417670682730924e-05, | |
| "loss": 0.2903, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.384203480589023e-05, | |
| "loss": 0.2862, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.350736278447122e-05, | |
| "loss": 0.2783, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.317269076305221e-05, | |
| "loss": 0.2825, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.2838018741633203e-05, | |
| "loss": 0.2586, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.2503346720214194e-05, | |
| "loss": 0.2355, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 4.2168674698795186e-05, | |
| "loss": 0.236, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.183400267737617e-05, | |
| "loss": 0.2348, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.149933065595716e-05, | |
| "loss": 0.226, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.116465863453816e-05, | |
| "loss": 0.2765, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.082998661311915e-05, | |
| "loss": 0.2744, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.0495314591700134e-05, | |
| "loss": 0.293, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.0160642570281125e-05, | |
| "loss": 0.2416, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.9825970548862116e-05, | |
| "loss": 0.2864, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.949129852744311e-05, | |
| "loss": 0.2335, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.91566265060241e-05, | |
| "loss": 0.2341, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9516129032258065, | |
| "eval_loss": 0.14258885383605957, | |
| "eval_runtime": 8.0066, | |
| "eval_samples_per_second": 147.128, | |
| "eval_steps_per_second": 4.621, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.882195448460509e-05, | |
| "loss": 0.2439, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.848728246318608e-05, | |
| "loss": 0.2018, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.815261044176707e-05, | |
| "loss": 0.2394, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.781793842034806e-05, | |
| "loss": 0.2311, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.748326639892905e-05, | |
| "loss": 0.2649, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.7148594377510044e-05, | |
| "loss": 0.193, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.6813922356091035e-05, | |
| "loss": 0.2252, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 3.647925033467202e-05, | |
| "loss": 0.2396, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 3.614457831325301e-05, | |
| "loss": 0.1846, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 3.580990629183401e-05, | |
| "loss": 0.229, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.5475234270415e-05, | |
| "loss": 0.2665, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3.5140562248995983e-05, | |
| "loss": 0.2018, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.4805890227576974e-05, | |
| "loss": 0.195, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.4471218206157965e-05, | |
| "loss": 0.2759, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 3.413654618473896e-05, | |
| "loss": 0.2093, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.380187416331995e-05, | |
| "loss": 0.1952, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.346720214190094e-05, | |
| "loss": 0.1907, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9422750424448217, | |
| "eval_loss": 0.1471460461616516, | |
| "eval_runtime": 8.6212, | |
| "eval_samples_per_second": 136.639, | |
| "eval_steps_per_second": 4.292, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.313253012048193e-05, | |
| "loss": 0.1938, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 3.279785809906292e-05, | |
| "loss": 0.2388, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 3.246318607764391e-05, | |
| "loss": 0.1775, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 3.21285140562249e-05, | |
| "loss": 0.1725, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 3.1793842034805894e-05, | |
| "loss": 0.1386, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 3.1459170013386885e-05, | |
| "loss": 0.1675, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.112449799196787e-05, | |
| "loss": 0.2132, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.078982597054887e-05, | |
| "loss": 0.1938, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 3.0455153949129854e-05, | |
| "loss": 0.1983, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 3.012048192771085e-05, | |
| "loss": 0.1875, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.9785809906291833e-05, | |
| "loss": 0.1942, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 2.9451137884872827e-05, | |
| "loss": 0.2072, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.911646586345382e-05, | |
| "loss": 0.1521, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 2.878179384203481e-05, | |
| "loss": 0.2497, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.8447121820615797e-05, | |
| "loss": 0.2459, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.8112449799196788e-05, | |
| "loss": 0.2132, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1836, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9575551782682513, | |
| "eval_loss": 0.11771776527166367, | |
| "eval_runtime": 8.1927, | |
| "eval_samples_per_second": 143.787, | |
| "eval_steps_per_second": 4.516, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.7443105756358774e-05, | |
| "loss": 0.144, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.7108433734939758e-05, | |
| "loss": 0.167, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.6773761713520752e-05, | |
| "loss": 0.2127, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.6439089692101743e-05, | |
| "loss": 0.1836, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.6104417670682734e-05, | |
| "loss": 0.1848, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 2.5769745649263722e-05, | |
| "loss": 0.1538, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.5435073627844713e-05, | |
| "loss": 0.1658, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 2.5100401606425704e-05, | |
| "loss": 0.181, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.4765729585006695e-05, | |
| "loss": 0.1735, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 2.4431057563587686e-05, | |
| "loss": 0.1816, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.4096385542168677e-05, | |
| "loss": 0.1797, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 2.3761713520749668e-05, | |
| "loss": 0.1854, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 2.3427041499330656e-05, | |
| "loss": 0.1567, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 2.309236947791165e-05, | |
| "loss": 0.1433, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 2.2757697456492638e-05, | |
| "loss": 0.1793, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 2.242302543507363e-05, | |
| "loss": 0.1669, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.966893039049236, | |
| "eval_loss": 0.1130693331360817, | |
| "eval_runtime": 7.7073, | |
| "eval_samples_per_second": 152.841, | |
| "eval_steps_per_second": 4.801, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 2.208835341365462e-05, | |
| "loss": 0.1968, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 2.175368139223561e-05, | |
| "loss": 0.1459, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 2.1419009370816602e-05, | |
| "loss": 0.1908, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 2.1084337349397593e-05, | |
| "loss": 0.1881, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 2.074966532797858e-05, | |
| "loss": 0.1672, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 2.0414993306559575e-05, | |
| "loss": 0.1853, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 2.0080321285140562e-05, | |
| "loss": 0.1939, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 1.9745649263721553e-05, | |
| "loss": 0.1527, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.9410977242302544e-05, | |
| "loss": 0.1743, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.9076305220883535e-05, | |
| "loss": 0.1486, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 1.8741633199464527e-05, | |
| "loss": 0.1789, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 1.8406961178045518e-05, | |
| "loss": 0.1558, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.8072289156626505e-05, | |
| "loss": 0.141, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 1.77376171352075e-05, | |
| "loss": 0.1651, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.7402945113788487e-05, | |
| "loss": 0.1338, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 1.706827309236948e-05, | |
| "loss": 0.1594, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.673360107095047e-05, | |
| "loss": 0.152, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.966044142614601, | |
| "eval_loss": 0.10996944457292557, | |
| "eval_runtime": 7.967, | |
| "eval_samples_per_second": 147.861, | |
| "eval_steps_per_second": 4.644, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.639892904953146e-05, | |
| "loss": 0.1278, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 1.606425702811245e-05, | |
| "loss": 0.1326, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 1.5729585006693442e-05, | |
| "loss": 0.1364, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 1.5394912985274433e-05, | |
| "loss": 0.1292, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 1.5060240963855424e-05, | |
| "loss": 0.1808, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.4725568942436414e-05, | |
| "loss": 0.1673, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.4390896921017405e-05, | |
| "loss": 0.1472, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.4056224899598394e-05, | |
| "loss": 0.1286, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.3721552878179387e-05, | |
| "loss": 0.1349, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.3386880856760376e-05, | |
| "loss": 0.1959, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.3052208835341367e-05, | |
| "loss": 0.1359, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.2717536813922356e-05, | |
| "loss": 0.1466, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.2382864792503347e-05, | |
| "loss": 0.1386, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.2048192771084338e-05, | |
| "loss": 0.1352, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.1713520749665328e-05, | |
| "loss": 0.1608, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.1378848728246319e-05, | |
| "loss": 0.1666, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9626485568760611, | |
| "eval_loss": 0.11297179758548737, | |
| "eval_runtime": 8.3936, | |
| "eval_samples_per_second": 140.345, | |
| "eval_steps_per_second": 4.408, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.104417670682731e-05, | |
| "loss": 0.1379, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.0709504685408301e-05, | |
| "loss": 0.1651, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 1.037483266398929e-05, | |
| "loss": 0.1656, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 1.0040160642570281e-05, | |
| "loss": 0.1335, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 9.705488621151272e-06, | |
| "loss": 0.1281, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 9.370816599732263e-06, | |
| "loss": 0.1313, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 9.036144578313253e-06, | |
| "loss": 0.1376, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 8.701472556894244e-06, | |
| "loss": 0.1323, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 8.366800535475235e-06, | |
| "loss": 0.1513, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.032128514056226e-06, | |
| "loss": 0.1292, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 7.697456492637217e-06, | |
| "loss": 0.1118, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 7.362784471218207e-06, | |
| "loss": 0.1193, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 7.028112449799197e-06, | |
| "loss": 0.1559, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.693440428380188e-06, | |
| "loss": 0.148, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 6.358768406961178e-06, | |
| "loss": 0.116, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 6.024096385542169e-06, | |
| "loss": 0.1292, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 5.689424364123159e-06, | |
| "loss": 0.1374, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.966893039049236, | |
| "eval_loss": 0.1132010966539383, | |
| "eval_runtime": 8.4232, | |
| "eval_samples_per_second": 139.851, | |
| "eval_steps_per_second": 4.393, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 5.3547523427041504e-06, | |
| "loss": 0.1293, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 5.020080321285141e-06, | |
| "loss": 0.1217, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.685408299866132e-06, | |
| "loss": 0.1223, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 4.350736278447122e-06, | |
| "loss": 0.1539, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 4.016064257028113e-06, | |
| "loss": 0.1352, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 3.6813922356091034e-06, | |
| "loss": 0.1311, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.346720214190094e-06, | |
| "loss": 0.1168, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 3.0120481927710846e-06, | |
| "loss": 0.1216, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 2.6773761713520752e-06, | |
| "loss": 0.1102, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.342704149933066e-06, | |
| "loss": 0.1335, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 2.0080321285140564e-06, | |
| "loss": 0.1385, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.673360107095047e-06, | |
| "loss": 0.1303, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 1.3386880856760376e-06, | |
| "loss": 0.1314, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 1.0040160642570282e-06, | |
| "loss": 0.1317, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 6.693440428380188e-07, | |
| "loss": 0.1496, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 3.346720214190094e-07, | |
| "loss": 0.1334, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1278, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.965195246179966, | |
| "eval_loss": 0.10753227770328522, | |
| "eval_runtime": 8.2617, | |
| "eval_samples_per_second": 142.586, | |
| "eval_steps_per_second": 4.479, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 830, | |
| "total_flos": 2.6335377898183066e+18, | |
| "train_loss": 0.2811273262443313, | |
| "train_runtime": 1705.57, | |
| "train_samples_per_second": 62.114, | |
| "train_steps_per_second": 0.487 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 830, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.6335377898183066e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |