| { | |
| "best_metric": 0.9609375, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-60", | |
| "epoch": 40.0, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8515625, | |
| "eval_loss": 0.4862026572227478, | |
| "eval_runtime": 11.5152, | |
| "eval_samples_per_second": 11.116, | |
| "eval_steps_per_second": 0.347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8828125, | |
| "eval_loss": 0.41026031970977783, | |
| "eval_runtime": 10.9773, | |
| "eval_samples_per_second": 11.66, | |
| "eval_steps_per_second": 0.364, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.4518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8984375, | |
| "eval_loss": 0.3210464119911194, | |
| "eval_runtime": 11.059, | |
| "eval_samples_per_second": 11.574, | |
| "eval_steps_per_second": 0.362, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9375, | |
| "eval_loss": 0.2052571028470993, | |
| "eval_runtime": 11.5695, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 0.346, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.2909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9453125, | |
| "eval_loss": 0.16745075583457947, | |
| "eval_runtime": 11.0604, | |
| "eval_samples_per_second": 11.573, | |
| "eval_steps_per_second": 0.362, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.14394168555736542, | |
| "eval_runtime": 11.4729, | |
| "eval_samples_per_second": 11.157, | |
| "eval_steps_per_second": 0.349, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9296875, | |
| "eval_loss": 0.1447799652814865, | |
| "eval_runtime": 10.9705, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.365, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.1492, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1797824651002884, | |
| "eval_runtime": 11.56, | |
| "eval_samples_per_second": 11.073, | |
| "eval_steps_per_second": 0.346, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9453125, | |
| "eval_loss": 0.13595758378505707, | |
| "eval_runtime": 10.9633, | |
| "eval_samples_per_second": 11.675, | |
| "eval_steps_per_second": 0.365, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.1161, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.16701428592205048, | |
| "eval_runtime": 11.2363, | |
| "eval_samples_per_second": 11.392, | |
| "eval_steps_per_second": 0.356, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.16373871266841888, | |
| "eval_runtime": 11.6774, | |
| "eval_samples_per_second": 10.961, | |
| "eval_steps_per_second": 0.343, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.12978079915046692, | |
| "eval_runtime": 11.0841, | |
| "eval_samples_per_second": 11.548, | |
| "eval_steps_per_second": 0.361, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.1053, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.11624787002801895, | |
| "eval_runtime": 11.6132, | |
| "eval_samples_per_second": 11.022, | |
| "eval_steps_per_second": 0.344, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.13526399433612823, | |
| "eval_runtime": 11.0555, | |
| "eval_samples_per_second": 11.578, | |
| "eval_steps_per_second": 0.362, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.0839, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9609375, | |
| "eval_loss": 0.12107539176940918, | |
| "eval_runtime": 11.0588, | |
| "eval_samples_per_second": 11.574, | |
| "eval_steps_per_second": 0.362, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9609375, | |
| "eval_loss": 0.11126996576786041, | |
| "eval_runtime": 11.181, | |
| "eval_samples_per_second": 11.448, | |
| "eval_steps_per_second": 0.358, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9609375, | |
| "eval_loss": 0.11446654796600342, | |
| "eval_runtime": 10.8152, | |
| "eval_samples_per_second": 11.835, | |
| "eval_steps_per_second": 0.37, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.0689, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1238832175731659, | |
| "eval_runtime": 11.2676, | |
| "eval_samples_per_second": 11.36, | |
| "eval_steps_per_second": 0.355, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1279521882534027, | |
| "eval_runtime": 10.0825, | |
| "eval_samples_per_second": 12.695, | |
| "eval_steps_per_second": 0.397, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0581, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.15327975153923035, | |
| "eval_runtime": 10.9213, | |
| "eval_samples_per_second": 11.72, | |
| "eval_steps_per_second": 0.366, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9609375, | |
| "eval_loss": 0.13229623436927795, | |
| "eval_runtime": 11.6242, | |
| "eval_samples_per_second": 11.011, | |
| "eval_steps_per_second": 0.344, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1327400803565979, | |
| "eval_runtime": 11.4822, | |
| "eval_samples_per_second": 11.148, | |
| "eval_steps_per_second": 0.348, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.0545, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.15285906195640564, | |
| "eval_runtime": 11.5375, | |
| "eval_samples_per_second": 11.094, | |
| "eval_steps_per_second": 0.347, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1356508731842041, | |
| "eval_runtime": 11.2408, | |
| "eval_samples_per_second": 11.387, | |
| "eval_steps_per_second": 0.356, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.046, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.13333538174629211, | |
| "eval_runtime": 11.6542, | |
| "eval_samples_per_second": 10.983, | |
| "eval_steps_per_second": 0.343, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.14664225280284882, | |
| "eval_runtime": 11.0398, | |
| "eval_samples_per_second": 11.594, | |
| "eval_steps_per_second": 0.362, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.13004614412784576, | |
| "eval_runtime": 11.0794, | |
| "eval_samples_per_second": 11.553, | |
| "eval_steps_per_second": 0.361, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.0421, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9609375, | |
| "eval_loss": 0.10774001479148865, | |
| "eval_runtime": 11.5664, | |
| "eval_samples_per_second": 11.067, | |
| "eval_steps_per_second": 0.346, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9609375, | |
| "eval_loss": 0.09847689419984818, | |
| "eval_runtime": 11.1305, | |
| "eval_samples_per_second": 11.5, | |
| "eval_steps_per_second": 0.359, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0371, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.11860589683055878, | |
| "eval_runtime": 11.1207, | |
| "eval_samples_per_second": 11.51, | |
| "eval_steps_per_second": 0.36, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1123187392950058, | |
| "eval_runtime": 11.7828, | |
| "eval_samples_per_second": 10.863, | |
| "eval_steps_per_second": 0.339, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.11436556279659271, | |
| "eval_runtime": 11.7664, | |
| "eval_samples_per_second": 10.878, | |
| "eval_steps_per_second": 0.34, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.0348, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.12758083641529083, | |
| "eval_runtime": 11.1627, | |
| "eval_samples_per_second": 11.467, | |
| "eval_steps_per_second": 0.358, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.14878937602043152, | |
| "eval_runtime": 11.0243, | |
| "eval_samples_per_second": 11.611, | |
| "eval_steps_per_second": 0.363, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0211, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.155960351228714, | |
| "eval_runtime": 11.5378, | |
| "eval_samples_per_second": 11.094, | |
| "eval_steps_per_second": 0.347, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1477176994085312, | |
| "eval_runtime": 11.1115, | |
| "eval_samples_per_second": 11.52, | |
| "eval_steps_per_second": 0.36, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1488116979598999, | |
| "eval_runtime": 11.3254, | |
| "eval_samples_per_second": 11.302, | |
| "eval_steps_per_second": 0.353, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.0274, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.14666207134723663, | |
| "eval_runtime": 11.771, | |
| "eval_samples_per_second": 10.874, | |
| "eval_steps_per_second": 0.34, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.14005045592784882, | |
| "eval_runtime": 10.9158, | |
| "eval_samples_per_second": 11.726, | |
| "eval_steps_per_second": 0.366, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0259, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.953125, | |
| "eval_loss": 0.1378861665725708, | |
| "eval_runtime": 11.2497, | |
| "eval_samples_per_second": 11.378, | |
| "eval_steps_per_second": 0.356, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 160, | |
| "total_flos": 5.0805641487089664e+17, | |
| "train_loss": 0.10081802383065223, | |
| "train_runtime": 2771.0512, | |
| "train_samples_per_second": 7.376, | |
| "train_steps_per_second": 0.058 | |
| } | |
| ], | |
| "max_steps": 160, | |
| "num_train_epochs": 40, | |
| "total_flos": 5.0805641487089664e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |