| { | |
| "best_metric": 0.9762962962962963, | |
| "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": 10.07322883605957, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 2.3374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 10.487809181213379, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 2.1161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 10.640003204345703, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.7137, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 15.871726989746094, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.1784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 15.640707969665527, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.7137, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 26.434770584106445, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.5603, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 13.86310863494873, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 0.4388, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 18.491966247558594, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 0.4186, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 10.696781158447266, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.4082, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 9.022970199584961, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 0.4058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 19.369293212890625, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 0.3426, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 11.921838760375977, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.319, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 16.04024314880371, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 0.3306, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 15.93685531616211, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 0.3204, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 11.990812301635742, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.288, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 15.536012649536133, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 0.2752, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 21.573360443115234, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 0.2691, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 19.456798553466797, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.2432, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 19.001985549926758, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2668, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.11669822782278061, | |
| "eval_runtime": 7.088, | |
| "eval_samples_per_second": 380.928, | |
| "eval_steps_per_second": 11.992, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 13.948786735534668, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 0.2478, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 11.453539848327637, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.2428, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 15.829312324523926, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.2646, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 16.091705322265625, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.2344, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 15.259565353393555, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.2393, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 9.776266098022461, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.2096, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 8.243420600891113, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.2136, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 12.557851791381836, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.2205, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 6.686116695404053, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.2136, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 8.7385835647583, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.1874, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 7.542112350463867, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.1838, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 11.214144706726074, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.1712, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 12.230096817016602, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.1769, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 16.084087371826172, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.1868, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 9.98460578918457, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.1532, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 7.164748668670654, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.1914, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 6.831585884094238, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.1717, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 5.868771076202393, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.1739, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.242668151855469, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1794, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9711111111111111, | |
| "eval_loss": 0.08373595029115677, | |
| "eval_runtime": 6.9635, | |
| "eval_samples_per_second": 387.733, | |
| "eval_steps_per_second": 12.206, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 6.042212009429932, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.1923, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 12.779237747192383, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.1782, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 9.20972728729248, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.1746, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 11.71999454498291, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.1713, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 7.5859694480896, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.1496, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 7.21168327331543, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.1613, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 6.680172920227051, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.1684, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 8.575725555419922, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.1223, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 6.606026649475098, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.1504, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 6.449505805969238, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.1747, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 7.1262526512146, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.1329, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 7.452645778656006, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.1303, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 8.39587116241455, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.1594, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 5.80369758605957, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.1394, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 5.9063873291015625, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.1825, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 7.986870288848877, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.1679, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 8.07669448852539, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.1801, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 11.537545204162598, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.1647, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 9.79477596282959, | |
| "learning_rate": 0.0, | |
| "loss": 0.1539, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_loss": 0.06411673873662949, | |
| "eval_runtime": 7.2052, | |
| "eval_samples_per_second": 374.73, | |
| "eval_steps_per_second": 11.797, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 1.8124066505760768e+18, | |
| "train_loss": 0.3484558000899198, | |
| "train_runtime": 391.3626, | |
| "train_samples_per_second": 186.272, | |
| "train_steps_per_second": 1.456 | |
| } | |
| ], | |
| "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 | |
| } | |