| { | |
| "best_metric": 0.9751851851851852, | |
| "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": 25.331281661987305, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 2.3146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 22.777584075927734, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 2.1316, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 35.167728424072266, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.7412, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 50.544654846191406, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.1409, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 42.26691818237305, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.6409, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 62.795013427734375, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.4925, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 74.10350799560547, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 0.4294, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 57.520381927490234, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 0.3551, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 85.2412109375, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.3986, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 39.69451904296875, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 0.3416, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 50.52515411376953, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 0.288, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 49.90411376953125, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.3292, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 44.21970748901367, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 0.282, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 53.848785400390625, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 0.3295, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 52.132633209228516, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.2575, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 61.904090881347656, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 0.2749, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 45.89011001586914, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 0.2857, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 55.151885986328125, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.2516, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 31.136672973632812, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2641, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9648148148148148, | |
| "eval_loss": 0.11399760097265244, | |
| "eval_runtime": 10.4627, | |
| "eval_samples_per_second": 258.06, | |
| "eval_steps_per_second": 8.124, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 29.735261917114258, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 0.2183, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 45.95719528198242, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.2101, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 19.06963348388672, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.2348, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 46.60264205932617, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.2256, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 52.50438690185547, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.2478, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 87.65154266357422, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.2053, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 32.65109634399414, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.2068, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 43.79768371582031, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.1919, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 46.49777603149414, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.199, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 52.9705810546875, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.1831, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 31.81144905090332, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.1882, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 22.147905349731445, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.205, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 40.582096099853516, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.1492, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 36.78301239013672, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.199, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 33.54383850097656, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.2252, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 54.70939254760742, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.2071, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 47.02043914794922, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.18, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 33.6547737121582, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.1592, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 62.884403228759766, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1767, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9707407407407408, | |
| "eval_loss": 0.09272177517414093, | |
| "eval_runtime": 16.0299, | |
| "eval_samples_per_second": 168.435, | |
| "eval_steps_per_second": 5.303, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 26.965408325195312, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.1468, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 32.16286087036133, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.1865, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 51.20572280883789, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.1589, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 27.62449836730957, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.1346, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 32.83967971801758, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.1762, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 25.56181526184082, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.1783, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 32.022979736328125, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.1467, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 41.31597137451172, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.1512, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 18.268918991088867, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.1407, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 37.31849670410156, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.1628, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 40.869140625, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.1479, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 37.81879806518555, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.1601, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 35.789310455322266, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.1199, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 46.275150299072266, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.144, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 22.838579177856445, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.1331, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 16.464527130126953, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.1236, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 23.072799682617188, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.1296, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 34.00244140625, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.1641, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 54.73069763183594, | |
| "learning_rate": 0.0, | |
| "loss": 0.1124, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9751851851851852, | |
| "eval_loss": 0.08017868548631668, | |
| "eval_runtime": 10.3773, | |
| "eval_samples_per_second": 260.182, | |
| "eval_steps_per_second": 8.191, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 1.8124066505760768e+18, | |
| "train_loss": 0.3364640083229333, | |
| "train_runtime": 644.3617, | |
| "train_samples_per_second": 113.135, | |
| "train_steps_per_second": 0.885 | |
| } | |
| ], | |
| "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 | |
| } | |