| { | |
| "best_metric": 0.8866264991906878, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-220", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 3.2964470386505127, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.2322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 2.9043655395507812, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.2604, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8392282958199357, | |
| "eval_f1": 0.8332760485475542, | |
| "eval_loss": 0.2333919107913971, | |
| "eval_precision": 0.8374611693960878, | |
| "eval_recall": 0.8392282958199357, | |
| "eval_runtime": 15.9334, | |
| "eval_samples_per_second": 19.519, | |
| "eval_steps_per_second": 0.628, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 56.99660873413086, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.2223, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 18.48450469970703, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.2492, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8263665594855305, | |
| "eval_f1": 0.8232255290144138, | |
| "eval_loss": 0.2620704472064972, | |
| "eval_precision": 0.8228686443399579, | |
| "eval_recall": 0.8263665594855305, | |
| "eval_runtime": 15.7143, | |
| "eval_samples_per_second": 19.791, | |
| "eval_steps_per_second": 0.636, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 6.249089241027832, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.2374, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 34.324771881103516, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.2373, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8617363344051447, | |
| "eval_f1": 0.8625935578100142, | |
| "eval_loss": 0.23337994515895844, | |
| "eval_precision": 0.8639282703997218, | |
| "eval_recall": 0.8617363344051447, | |
| "eval_runtime": 16.0907, | |
| "eval_samples_per_second": 19.328, | |
| "eval_steps_per_second": 0.621, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.1818181818181817, | |
| "grad_norm": 12.280445098876953, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.2634, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 4.722353935241699, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.2623, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8810289389067524, | |
| "eval_f1": 0.88319217217326, | |
| "eval_loss": 0.2036450058221817, | |
| "eval_precision": 0.8908256857340293, | |
| "eval_recall": 0.8810289389067524, | |
| "eval_runtime": 16.3075, | |
| "eval_samples_per_second": 19.071, | |
| "eval_steps_per_second": 0.613, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.090909090909091, | |
| "grad_norm": 11.214787483215332, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.2246, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 13.322309494018555, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.232, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 8.625347137451172, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2378, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.819935691318328, | |
| "eval_f1": 0.8172812345261152, | |
| "eval_loss": 0.2944244146347046, | |
| "eval_precision": 0.8165197977946229, | |
| "eval_recall": 0.819935691318328, | |
| "eval_runtime": 16.454, | |
| "eval_samples_per_second": 18.901, | |
| "eval_steps_per_second": 0.608, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 5.456847667694092, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.2711, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.909090909090909, | |
| "grad_norm": 11.77868938446045, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.221, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8681672025723473, | |
| "eval_f1": 0.8700951269031074, | |
| "eval_loss": 0.20269730687141418, | |
| "eval_precision": 0.8751993658233878, | |
| "eval_recall": 0.8681672025723473, | |
| "eval_runtime": 15.757, | |
| "eval_samples_per_second": 19.737, | |
| "eval_steps_per_second": 0.635, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 10.365585327148438, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.2205, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.818181818181818, | |
| "grad_norm": 3.4123003482818604, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.2339, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8585209003215434, | |
| "eval_f1": 0.8577414571643612, | |
| "eval_loss": 0.2290601134300232, | |
| "eval_precision": 0.8572771006256387, | |
| "eval_recall": 0.8585209003215434, | |
| "eval_runtime": 15.7364, | |
| "eval_samples_per_second": 19.763, | |
| "eval_steps_per_second": 0.635, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 6.866532325744629, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.2274, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.7272727272727275, | |
| "grad_norm": 28.103683471679688, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.2215, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8681672025723473, | |
| "eval_f1": 0.868338573836183, | |
| "eval_loss": 0.2732490599155426, | |
| "eval_precision": 0.8685295263564022, | |
| "eval_recall": 0.8681672025723473, | |
| "eval_runtime": 17.2464, | |
| "eval_samples_per_second": 18.033, | |
| "eval_steps_per_second": 0.58, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 8.181818181818182, | |
| "grad_norm": 7.824560642242432, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.2202, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.636363636363637, | |
| "grad_norm": 1.545398473739624, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.2162, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8681672025723473, | |
| "eval_f1": 0.8692844166638126, | |
| "eval_loss": 0.2260492444038391, | |
| "eval_precision": 0.8713400647093587, | |
| "eval_recall": 0.8681672025723473, | |
| "eval_runtime": 15.7507, | |
| "eval_samples_per_second": 19.745, | |
| "eval_steps_per_second": 0.635, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 2.2911288738250732, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.2224, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.545454545454545, | |
| "grad_norm": 3.872638463973999, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2126, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.078859567642212, | |
| "learning_rate": 0.0, | |
| "loss": 0.2226, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8842443729903537, | |
| "eval_f1": 0.8866264991906878, | |
| "eval_loss": 0.20013029873371124, | |
| "eval_precision": 0.8965561746996403, | |
| "eval_recall": 0.8842443729903537, | |
| "eval_runtime": 16.6583, | |
| "eval_samples_per_second": 18.669, | |
| "eval_steps_per_second": 0.6, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 220, | |
| "total_flos": 6.954705718242509e+17, | |
| "train_loss": 0.23402113264257257, | |
| "train_runtime": 1621.2514, | |
| "train_samples_per_second": 17.258, | |
| "train_steps_per_second": 0.136 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 6.954705718242509e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |