| { | |
| "best_metric": 0.9691358024691358, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-342", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 342, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 4.784806251525879, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.2537, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 7.325711727142334, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.9328, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 12.205706596374512, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.3033, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 21.546316146850586, | |
| "learning_rate": 4.9185667752443e-05, | |
| "loss": 0.7435, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "grad_norm": 11.416431427001953, | |
| "learning_rate": 4.755700325732899e-05, | |
| "loss": 0.5723, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 13.339532852172852, | |
| "learning_rate": 4.592833876221499e-05, | |
| "loss": 0.4688, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6140350877192983, | |
| "grad_norm": 18.226308822631836, | |
| "learning_rate": 4.429967426710098e-05, | |
| "loss": 0.4296, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 24.142580032348633, | |
| "learning_rate": 4.2671009771986977e-05, | |
| "loss": 0.3557, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 18.747182846069336, | |
| "learning_rate": 4.104234527687297e-05, | |
| "loss": 0.3364, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 9.604598999023438, | |
| "learning_rate": 3.941368078175896e-05, | |
| "loss": 0.379, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9649122807017544, | |
| "grad_norm": 9.6405668258667, | |
| "learning_rate": 3.778501628664495e-05, | |
| "loss": 0.2967, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9271604938271605, | |
| "eval_loss": 0.20734398066997528, | |
| "eval_runtime": 4.5343, | |
| "eval_samples_per_second": 357.28, | |
| "eval_steps_per_second": 11.248, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 10.606453895568848, | |
| "learning_rate": 3.615635179153095e-05, | |
| "loss": 0.2506, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1403508771929824, | |
| "grad_norm": 13.219770431518555, | |
| "learning_rate": 3.452768729641694e-05, | |
| "loss": 0.2646, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2280701754385965, | |
| "grad_norm": 14.424461364746094, | |
| "learning_rate": 3.289902280130293e-05, | |
| "loss": 0.3161, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 16.468141555786133, | |
| "learning_rate": 3.127035830618892e-05, | |
| "loss": 0.2296, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4035087719298245, | |
| "grad_norm": 18.474872589111328, | |
| "learning_rate": 2.9641693811074923e-05, | |
| "loss": 0.252, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.4912280701754386, | |
| "grad_norm": 8.512451171875, | |
| "learning_rate": 2.8013029315960915e-05, | |
| "loss": 0.2526, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 10.639461517333984, | |
| "learning_rate": 2.6384364820846906e-05, | |
| "loss": 0.2218, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 10.84925651550293, | |
| "learning_rate": 2.47557003257329e-05, | |
| "loss": 0.2246, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "grad_norm": 7.055878162384033, | |
| "learning_rate": 2.3127035830618892e-05, | |
| "loss": 0.2181, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 10.151970863342285, | |
| "learning_rate": 2.149837133550489e-05, | |
| "loss": 0.2336, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9298245614035088, | |
| "grad_norm": 10.90556812286377, | |
| "learning_rate": 1.986970684039088e-05, | |
| "loss": 0.2175, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9617283950617284, | |
| "eval_loss": 0.1142377108335495, | |
| "eval_runtime": 4.4649, | |
| "eval_samples_per_second": 362.828, | |
| "eval_steps_per_second": 11.422, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.017543859649123, | |
| "grad_norm": 7.411689281463623, | |
| "learning_rate": 1.8241042345276872e-05, | |
| "loss": 0.2493, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 6.981323719024658, | |
| "learning_rate": 1.6612377850162867e-05, | |
| "loss": 0.1832, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.192982456140351, | |
| "grad_norm": 17.770326614379883, | |
| "learning_rate": 1.4983713355048862e-05, | |
| "loss": 0.1862, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.280701754385965, | |
| "grad_norm": 14.688613891601562, | |
| "learning_rate": 1.3355048859934855e-05, | |
| "loss": 0.1725, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 9.546713829040527, | |
| "learning_rate": 1.1726384364820847e-05, | |
| "loss": 0.2187, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.456140350877193, | |
| "grad_norm": 13.742387771606445, | |
| "learning_rate": 1.009771986970684e-05, | |
| "loss": 0.211, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.543859649122807, | |
| "grad_norm": 10.309969902038574, | |
| "learning_rate": 8.469055374592833e-06, | |
| "loss": 0.1776, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 11.343367576599121, | |
| "learning_rate": 6.840390879478828e-06, | |
| "loss": 0.1828, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.719298245614035, | |
| "grad_norm": 12.15509033203125, | |
| "learning_rate": 5.211726384364822e-06, | |
| "loss": 0.1565, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.807017543859649, | |
| "grad_norm": 13.258170127868652, | |
| "learning_rate": 3.5830618892508147e-06, | |
| "loss": 0.1601, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 13.760292053222656, | |
| "learning_rate": 1.9543973941368076e-06, | |
| "loss": 0.1777, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.982456140350877, | |
| "grad_norm": 10.578232765197754, | |
| "learning_rate": 3.2573289902280136e-07, | |
| "loss": 0.1881, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9691358024691358, | |
| "eval_loss": 0.08843858540058136, | |
| "eval_runtime": 4.4533, | |
| "eval_samples_per_second": 363.776, | |
| "eval_steps_per_second": 11.452, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 342, | |
| "total_flos": 1.0874439903456461e+18, | |
| "train_loss": 0.41079250579340415, | |
| "train_runtime": 248.8888, | |
| "train_samples_per_second": 175.741, | |
| "train_steps_per_second": 1.374 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 342, | |
| "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": 1.0874439903456461e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |