| { | |
| "best_metric": 0.9992215879605605, | |
| "best_model_checkpoint": "resnet-50-finetuned-imageclds/checkpoint-964", | |
| "epoch": 5.0, | |
| "global_step": 1205, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.132231404958678e-06, | |
| "loss": 1.3966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.264462809917356e-06, | |
| "loss": 1.3918, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.2396694214876034e-05, | |
| "loss": 1.3847, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.652892561983471e-05, | |
| "loss": 1.374, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.066115702479339e-05, | |
| "loss": 1.3608, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.479338842975207e-05, | |
| "loss": 1.344, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.8925619834710744e-05, | |
| "loss": 1.3164, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.305785123966942e-05, | |
| "loss": 1.2815, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.71900826446281e-05, | |
| "loss": 1.2428, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.132231404958678e-05, | |
| "loss": 1.1914, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 1.1237, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.958677685950414e-05, | |
| "loss": 1.035, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.9584870848708485e-05, | |
| "loss": 0.9447, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.912361623616236e-05, | |
| "loss": 0.8677, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.8662361623616234e-05, | |
| "loss": 0.7542, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.820110701107011e-05, | |
| "loss": 0.6596, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.773985239852399e-05, | |
| "loss": 0.5725, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.727859778597786e-05, | |
| "loss": 0.4902, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.681734317343174e-05, | |
| "loss": 0.4151, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.6356088560885616e-05, | |
| "loss": 0.3381, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.589483394833948e-05, | |
| "loss": 0.2991, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.543357933579336e-05, | |
| "loss": 0.2588, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.4972324723247236e-05, | |
| "loss": 0.2071, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.451107011070111e-05, | |
| "loss": 0.177, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9941619097042034, | |
| "eval_loss": 0.08304398506879807, | |
| "eval_runtime": 95.802, | |
| "eval_samples_per_second": 80.458, | |
| "eval_steps_per_second": 2.516, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.4049815498154985e-05, | |
| "loss": 0.1509, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.3588560885608856e-05, | |
| "loss": 0.1255, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.3127306273062734e-05, | |
| "loss": 0.1235, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.266605166051661e-05, | |
| "loss": 0.1293, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.220479704797048e-05, | |
| "loss": 0.0997, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.1743542435424353e-05, | |
| "loss": 0.0962, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.128228782287823e-05, | |
| "loss": 0.103, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.08210332103321e-05, | |
| "loss": 0.0942, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.035977859778598e-05, | |
| "loss": 0.0892, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.989852398523986e-05, | |
| "loss": 0.0882, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.943726937269373e-05, | |
| "loss": 0.0736, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3.897601476014761e-05, | |
| "loss": 0.0835, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.851476014760148e-05, | |
| "loss": 0.0747, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 3.805350553505535e-05, | |
| "loss": 0.08, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.7592250922509227e-05, | |
| "loss": 0.0633, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.71309963099631e-05, | |
| "loss": 0.0733, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.6669741697416975e-05, | |
| "loss": 0.0687, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.620848708487085e-05, | |
| "loss": 0.0588, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.5747232472324724e-05, | |
| "loss": 0.0752, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.52859778597786e-05, | |
| "loss": 0.0647, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.482472324723247e-05, | |
| "loss": 0.0573, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.4363468634686344e-05, | |
| "loss": 0.0552, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.390221402214022e-05, | |
| "loss": 0.0545, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 3.34409594095941e-05, | |
| "loss": 0.0597, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9981837052413077, | |
| "eval_loss": 0.010696413926780224, | |
| "eval_runtime": 95.8742, | |
| "eval_samples_per_second": 80.397, | |
| "eval_steps_per_second": 2.514, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.297970479704797e-05, | |
| "loss": 0.0513, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.251845018450185e-05, | |
| "loss": 0.054, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.205719557195572e-05, | |
| "loss": 0.0486, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.15959409594096e-05, | |
| "loss": 0.0472, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.113468634686347e-05, | |
| "loss": 0.0519, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.067343173431734e-05, | |
| "loss": 0.0458, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.0212177121771217e-05, | |
| "loss": 0.0467, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.975092250922509e-05, | |
| "loss": 0.0549, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.928966789667897e-05, | |
| "loss": 0.0409, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.8828413284132844e-05, | |
| "loss": 0.0451, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.8367158671586718e-05, | |
| "loss": 0.0599, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.7905904059040593e-05, | |
| "loss": 0.0559, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.7444649446494464e-05, | |
| "loss": 0.0417, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.6983394833948338e-05, | |
| "loss": 0.0584, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.6522140221402213e-05, | |
| "loss": 0.0427, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.606088560885609e-05, | |
| "loss": 0.0446, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.5599630996309965e-05, | |
| "loss": 0.0486, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.513837638376384e-05, | |
| "loss": 0.0481, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.4677121771217714e-05, | |
| "loss": 0.0433, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.4215867158671588e-05, | |
| "loss": 0.0528, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.3754612546125462e-05, | |
| "loss": 0.0503, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.3293357933579337e-05, | |
| "loss": 0.041, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2.283210332103321e-05, | |
| "loss": 0.0391, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.2370848708487086e-05, | |
| "loss": 0.0387, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9988323819408407, | |
| "eval_loss": 0.006782455835491419, | |
| "eval_runtime": 95.7091, | |
| "eval_samples_per_second": 80.536, | |
| "eval_steps_per_second": 2.518, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.190959409594096e-05, | |
| "loss": 0.0358, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 2.1448339483394835e-05, | |
| "loss": 0.0386, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.098708487084871e-05, | |
| "loss": 0.0354, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 2.0525830258302583e-05, | |
| "loss": 0.0443, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.0064575645756458e-05, | |
| "loss": 0.0456, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.9603321033210336e-05, | |
| "loss": 0.0409, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.9142066420664207e-05, | |
| "loss": 0.039, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.868081180811808e-05, | |
| "loss": 0.042, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.8219557195571955e-05, | |
| "loss": 0.0392, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.7758302583025833e-05, | |
| "loss": 0.0465, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.7297047970479704e-05, | |
| "loss": 0.043, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.683579335793358e-05, | |
| "loss": 0.0433, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.6374538745387457e-05, | |
| "loss": 0.0506, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.591328413284133e-05, | |
| "loss": 0.0307, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.5452029520295202e-05, | |
| "loss": 0.0393, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.4990774907749078e-05, | |
| "loss": 0.0394, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.4529520295202952e-05, | |
| "loss": 0.0522, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.4068265682656829e-05, | |
| "loss": 0.04, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.3607011070110701e-05, | |
| "loss": 0.05, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.3145756457564576e-05, | |
| "loss": 0.0519, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.2684501845018452e-05, | |
| "loss": 0.0415, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.2223247232472325e-05, | |
| "loss": 0.04, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.17619926199262e-05, | |
| "loss": 0.0416, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.1300738007380073e-05, | |
| "loss": 0.0381, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9992215879605605, | |
| "eval_loss": 0.004435474518686533, | |
| "eval_runtime": 95.7502, | |
| "eval_samples_per_second": 80.501, | |
| "eval_steps_per_second": 2.517, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1.083948339483395e-05, | |
| "loss": 0.0469, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.0378228782287822e-05, | |
| "loss": 0.0381, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 9.916974169741698e-06, | |
| "loss": 0.0312, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.455719557195573e-06, | |
| "loss": 0.0299, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 8.994464944649447e-06, | |
| "loss": 0.0374, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 8.533210332103322e-06, | |
| "loss": 0.0348, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 8.071955719557196e-06, | |
| "loss": 0.0392, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.6107011070110704e-06, | |
| "loss": 0.0292, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 7.149446494464946e-06, | |
| "loss": 0.0401, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.688191881918819e-06, | |
| "loss": 0.0319, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 6.2269372693726945e-06, | |
| "loss": 0.0345, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 5.765682656826569e-06, | |
| "loss": 0.0399, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 5.304428044280443e-06, | |
| "loss": 0.0347, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.843173431734318e-06, | |
| "loss": 0.046, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 4.381918819188192e-06, | |
| "loss": 0.0382, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 3.920664206642067e-06, | |
| "loss": 0.0371, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 3.4594095940959415e-06, | |
| "loss": 0.0303, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.9981549815498154e-06, | |
| "loss": 0.045, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.5369003690036903e-06, | |
| "loss": 0.0442, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.0756457564575647e-06, | |
| "loss": 0.0453, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.6143911439114391e-06, | |
| "loss": 0.0382, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.1531365313653137e-06, | |
| "loss": 0.0276, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 6.918819188191883e-07, | |
| "loss": 0.0472, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 2.3062730627306274e-07, | |
| "loss": 0.0361, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9990918526206539, | |
| "eval_loss": 0.00399142038077116, | |
| "eval_runtime": 99.5709, | |
| "eval_samples_per_second": 77.412, | |
| "eval_steps_per_second": 2.42, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1205, | |
| "total_flos": 3.2740079756783616e+18, | |
| "train_loss": 0.22034260028378103, | |
| "train_runtime": 2871.3129, | |
| "train_samples_per_second": 53.686, | |
| "train_steps_per_second": 0.42 | |
| } | |
| ], | |
| "max_steps": 1205, | |
| "num_train_epochs": 5, | |
| "total_flos": 3.2740079756783616e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |