| { | |
| "best_metric": 0.9544419134396356, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-agrivision/checkpoint-186", | |
| "epoch": 30.0, | |
| "global_step": 930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 1.0346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.5829, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7266514806378133, | |
| "eval_loss": 0.7480179667472839, | |
| "eval_runtime": 8.3505, | |
| "eval_samples_per_second": 52.572, | |
| "eval_steps_per_second": 1.677, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.3181, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.2013, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.1199, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8246013667425968, | |
| "eval_loss": 0.4407329261302948, | |
| "eval_runtime": 8.4214, | |
| "eval_samples_per_second": 52.129, | |
| "eval_steps_per_second": 1.662, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.0682, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.0962, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.1028, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8246013667425968, | |
| "eval_loss": 0.4477098882198334, | |
| "eval_runtime": 8.5023, | |
| "eval_samples_per_second": 51.633, | |
| "eval_steps_per_second": 1.647, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.0575, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.0431, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.0533, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8291571753986332, | |
| "eval_loss": 0.4605787992477417, | |
| "eval_runtime": 8.4753, | |
| "eval_samples_per_second": 51.797, | |
| "eval_steps_per_second": 1.652, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.0374, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.0251, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.0411, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9179954441913439, | |
| "eval_loss": 0.24701963365077972, | |
| "eval_runtime": 8.3819, | |
| "eval_samples_per_second": 52.375, | |
| "eval_steps_per_second": 1.67, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.0336, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.0179, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.022, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9544419134396356, | |
| "eval_loss": 0.1568455845117569, | |
| "eval_runtime": 8.411, | |
| "eval_samples_per_second": 52.194, | |
| "eval_steps_per_second": 1.664, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.027, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.0116, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.0206, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8792710706150342, | |
| "eval_loss": 0.4187353849411011, | |
| "eval_runtime": 8.4199, | |
| "eval_samples_per_second": 52.139, | |
| "eval_steps_per_second": 1.663, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.017, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.0206, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.0069, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9202733485193622, | |
| "eval_loss": 0.24978817999362946, | |
| "eval_runtime": 8.4711, | |
| "eval_samples_per_second": 51.823, | |
| "eval_steps_per_second": 1.653, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.0189, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.0091, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.0053, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9225512528473804, | |
| "eval_loss": 0.26543566584587097, | |
| "eval_runtime": 8.3285, | |
| "eval_samples_per_second": 52.711, | |
| "eval_steps_per_second": 1.681, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.0195, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.0037, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.005, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0094, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9384965831435079, | |
| "eval_loss": 0.23431657254695892, | |
| "eval_runtime": 8.4865, | |
| "eval_samples_per_second": 51.729, | |
| "eval_steps_per_second": 1.65, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.0104, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.0125, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.0152, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9020501138952164, | |
| "eval_loss": 0.3421424627304077, | |
| "eval_runtime": 8.3148, | |
| "eval_samples_per_second": 52.798, | |
| "eval_steps_per_second": 1.684, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.0072, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.0092, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.0047, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8724373576309795, | |
| "eval_loss": 0.44937077164649963, | |
| "eval_runtime": 8.3634, | |
| "eval_samples_per_second": 52.49, | |
| "eval_steps_per_second": 1.674, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.0047, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.0029, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.0128, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8678815489749431, | |
| "eval_loss": 0.5359533429145813, | |
| "eval_runtime": 8.4935, | |
| "eval_samples_per_second": 51.687, | |
| "eval_steps_per_second": 1.648, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.0086, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.0041, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.0024, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9111617312072893, | |
| "eval_loss": 0.2775423526763916, | |
| "eval_runtime": 8.5462, | |
| "eval_samples_per_second": 51.368, | |
| "eval_steps_per_second": 1.638, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.005, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.0041, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.0127, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.89749430523918, | |
| "eval_loss": 0.29105421900749207, | |
| "eval_runtime": 8.44, | |
| "eval_samples_per_second": 52.014, | |
| "eval_steps_per_second": 1.659, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.0097, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.0003, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.0038, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.929384965831435, | |
| "eval_loss": 0.23365984857082367, | |
| "eval_runtime": 8.4714, | |
| "eval_samples_per_second": 51.821, | |
| "eval_steps_per_second": 1.653, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.0042, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.0008, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.0001, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9407744874715261, | |
| "eval_loss": 0.22065891325473785, | |
| "eval_runtime": 8.3769, | |
| "eval_samples_per_second": 52.406, | |
| "eval_steps_per_second": 1.671, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.0003, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.0004, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.0054, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9362186788154897, | |
| "eval_loss": 0.2506341338157654, | |
| "eval_runtime": 8.432, | |
| "eval_samples_per_second": 52.064, | |
| "eval_steps_per_second": 1.66, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.0002, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.0014, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.0011, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8952164009111617, | |
| "eval_loss": 0.37775158882141113, | |
| "eval_runtime": 8.3743, | |
| "eval_samples_per_second": 52.422, | |
| "eval_steps_per_second": 1.672, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.0006, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.0001, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.0001, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0002, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9407744874715261, | |
| "eval_loss": 0.23159268498420715, | |
| "eval_runtime": 8.4951, | |
| "eval_samples_per_second": 51.677, | |
| "eval_steps_per_second": 1.648, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.0039, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.0003, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.97, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.0003, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9430523917995444, | |
| "eval_loss": 0.21328049898147583, | |
| "eval_runtime": 8.4322, | |
| "eval_samples_per_second": 52.062, | |
| "eval_steps_per_second": 1.66, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.0008, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.61, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.0007, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.0009, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9339407744874715, | |
| "eval_loss": 0.25188666582107544, | |
| "eval_runtime": 8.3597, | |
| "eval_samples_per_second": 52.514, | |
| "eval_steps_per_second": 1.675, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 22.26, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.0018, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.58, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.0052, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.9, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.0004, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9202733485193622, | |
| "eval_loss": 0.2931215167045593, | |
| "eval_runtime": 8.3479, | |
| "eval_samples_per_second": 52.588, | |
| "eval_steps_per_second": 1.677, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.0005, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.87, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.0001, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9271070615034168, | |
| "eval_loss": 0.2847088575363159, | |
| "eval_runtime": 8.2725, | |
| "eval_samples_per_second": 53.067, | |
| "eval_steps_per_second": 1.692, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.0001, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.007, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.0003, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9316628701594533, | |
| "eval_loss": 0.28311699628829956, | |
| "eval_runtime": 8.4361, | |
| "eval_samples_per_second": 52.038, | |
| "eval_steps_per_second": 1.66, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 25.16, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.0001, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 25.48, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.0001, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.0008, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9271070615034168, | |
| "eval_loss": 0.2918652594089508, | |
| "eval_runtime": 8.3526, | |
| "eval_samples_per_second": 52.558, | |
| "eval_steps_per_second": 1.676, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 26.13, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.0001, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 26.45, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.004, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.77, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.0003, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9362186788154897, | |
| "eval_loss": 0.2797539532184601, | |
| "eval_runtime": 8.3259, | |
| "eval_samples_per_second": 52.727, | |
| "eval_steps_per_second": 1.681, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 27.1, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.0035, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 27.42, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.74, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.0008, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9362186788154897, | |
| "eval_loss": 0.28566640615463257, | |
| "eval_runtime": 8.5372, | |
| "eval_samples_per_second": 51.422, | |
| "eval_steps_per_second": 1.64, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.0002, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.39, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.0022, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.71, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.0008, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9362186788154897, | |
| "eval_loss": 0.2779512405395508, | |
| "eval_runtime": 8.4419, | |
| "eval_samples_per_second": 52.003, | |
| "eval_steps_per_second": 1.658, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.0001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.0004, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.0001, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0013, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9362186788154897, | |
| "eval_loss": 0.27828121185302734, | |
| "eval_runtime": 8.5464, | |
| "eval_samples_per_second": 51.367, | |
| "eval_steps_per_second": 1.638, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 930, | |
| "total_flos": 2.9462626978683494e+18, | |
| "train_loss": 0.04387470004151911, | |
| "train_runtime": 7100.0179, | |
| "train_samples_per_second": 16.694, | |
| "train_steps_per_second": 0.131 | |
| } | |
| ], | |
| "max_steps": 930, | |
| "num_train_epochs": 30, | |
| "total_flos": 2.9462626978683494e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |