| { | |
| "best_metric": 0.9781481481481481, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-570", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 6.441094398498535, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 2.2771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 7.560100078582764, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 2.0756, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 8.593420028686523, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.6159, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 15.930532455444336, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.0891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 9.635261535644531, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.7175, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 29.617084503173828, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.5415, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 12.889870643615723, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 0.3873, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 28.610116958618164, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 0.3935, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 12.129476547241211, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.407, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 8.134405136108398, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 0.403, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 16.965028762817383, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 0.3666, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 20.727378845214844, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.3315, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 10.648832321166992, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 0.3185, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 15.240333557128906, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 0.3092, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 12.595602035522461, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.2781, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 23.477523803710938, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 0.3165, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 12.806583404541016, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 0.2604, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 12.278985023498535, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.2268, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 16.98476791381836, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2614, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9644444444444444, | |
| "eval_loss": 0.11767604947090149, | |
| "eval_runtime": 17.0429, | |
| "eval_samples_per_second": 158.424, | |
| "eval_steps_per_second": 4.987, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 22.68017578125, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 0.2571, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 8.888700485229492, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.2413, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 15.368131637573242, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.2676, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 12.329680442810059, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.223, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 18.98630714416504, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.2213, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 8.994136810302734, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.2417, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 17.037776947021484, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.2054, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 6.9045610427856445, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.217, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 8.878619194030762, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.2074, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 9.569494247436523, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.2046, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 10.316445350646973, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.1704, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 14.888699531555176, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.1674, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 11.373708724975586, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.1637, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 13.694819450378418, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.1904, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 11.21845817565918, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.1539, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 9.454412460327148, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.1953, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 11.822175979614258, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.1608, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 18.53520393371582, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.1849, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.514893531799316, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1862, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9748148148148148, | |
| "eval_loss": 0.07534925639629364, | |
| "eval_runtime": 17.2506, | |
| "eval_samples_per_second": 156.516, | |
| "eval_steps_per_second": 4.927, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 7.307323932647705, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.1862, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 12.584000587463379, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.1865, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 11.615283966064453, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.1706, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 14.084049224853516, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.1775, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 7.380066394805908, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.1578, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 5.233687877655029, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.1548, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 6.7702765464782715, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.1618, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 10.425500869750977, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.1174, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 9.966532707214355, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.1395, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 8.691372871398926, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.168, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 8.912318229675293, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.1366, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 8.191598892211914, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.128, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 11.146318435668945, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.1428, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 9.236715316772461, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.1347, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 6.167862892150879, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.172, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 11.211396217346191, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.162, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 12.20263385772705, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.1697, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 6.672098159790039, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.1561, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 11.088051795959473, | |
| "learning_rate": 0.0, | |
| "loss": 0.1673, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9781481481481481, | |
| "eval_loss": 0.062276002019643784, | |
| "eval_runtime": 17.726, | |
| "eval_samples_per_second": 152.319, | |
| "eval_steps_per_second": 4.795, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 1.8124066505760768e+18, | |
| "train_loss": 0.3407971503441794, | |
| "train_runtime": 1163.8701, | |
| "train_samples_per_second": 62.636, | |
| "train_steps_per_second": 0.49 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 570, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8124066505760768e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |