| { | |
| "best_metric": 0.9792592592592593, | |
| "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": 4.343901634216309, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 2.3068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 6.9181928634643555, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 2.1013, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 15.276274681091309, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.7038, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 11.972685813903809, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.1111, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 18.04628562927246, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.6855, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 26.95036506652832, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.5126, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 13.101174354553223, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 0.4391, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 16.37429428100586, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 0.3862, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 18.389183044433594, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.3387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 6.9733428955078125, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 0.3674, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 9.850255012512207, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 0.3474, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 9.4562406539917, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.2886, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 24.102073669433594, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 0.2931, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 11.236126899719238, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 0.2734, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 11.777973175048828, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.3085, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 14.830010414123535, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 0.2942, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 11.80654525756836, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 0.2448, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 13.162323951721191, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.216, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 26.420730590820312, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2486, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9596296296296296, | |
| "eval_loss": 0.11904598772525787, | |
| "eval_runtime": 16.7449, | |
| "eval_samples_per_second": 161.244, | |
| "eval_steps_per_second": 5.076, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 9.718153953552246, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 0.2131, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 6.288980484008789, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.2227, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 8.807621955871582, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.2247, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 11.854440689086914, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.276, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 10.865113258361816, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.2259, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 7.972955226898193, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.2183, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 7.044989109039307, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.226, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 7.572982311248779, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.2109, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 7.762623310089111, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.1976, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 8.442371368408203, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.1926, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 8.82628345489502, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.1771, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 14.203849792480469, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.2011, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 16.233551025390625, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.1875, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 10.250910758972168, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.186, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 7.864058494567871, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.1623, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 19.014820098876953, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.1957, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 9.105624198913574, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.1778, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 10.166816711425781, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.2045, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.262903213500977, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1564, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9755555555555555, | |
| "eval_loss": 0.06939271837472916, | |
| "eval_runtime": 16.5041, | |
| "eval_samples_per_second": 163.596, | |
| "eval_steps_per_second": 5.15, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 10.945294380187988, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.1945, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 12.293395042419434, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.1737, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 9.197681427001953, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.1518, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 5.952602386474609, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.1616, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 7.829499244689941, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.1672, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 4.569563388824463, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.1373, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 8.25244140625, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.1531, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 5.240682125091553, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.1674, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 10.285263061523438, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.1773, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 7.376901626586914, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.1604, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 11.308797836303711, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.146, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 3.549391269683838, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.1464, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 5.578386306762695, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.133, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 8.859381675720215, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.147, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 8.507740020751953, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.1392, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 6.85144567489624, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.1505, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 16.25189781188965, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.1209, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 6.5484137535095215, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.148, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 7.504970073699951, | |
| "learning_rate": 0.0, | |
| "loss": 0.1244, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_loss": 0.06017439067363739, | |
| "eval_runtime": 17.0791, | |
| "eval_samples_per_second": 158.088, | |
| "eval_steps_per_second": 4.977, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 1.8124066505760768e+18, | |
| "train_loss": 0.33724165422874586, | |
| "train_runtime": 1116.074, | |
| "train_samples_per_second": 65.318, | |
| "train_steps_per_second": 0.511 | |
| } | |
| ], | |
| "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 | |
| } | |