| { | |
| "best_metric": 0.8581712564304036, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-66", | |
| "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": 6.432889938354492, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.6765, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 8.764992713928223, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6784565916398714, | |
| "eval_f1": 0.5484840645057965, | |
| "eval_loss": 0.5874345302581787, | |
| "eval_precision": 0.4603033467395912, | |
| "eval_recall": 0.6784565916398714, | |
| "eval_runtime": 293.1777, | |
| "eval_samples_per_second": 1.061, | |
| "eval_steps_per_second": 0.034, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 7.319944381713867, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.4587, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 11.48066520690918, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3711, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7781350482315113, | |
| "eval_f1": 0.7395292980112433, | |
| "eval_loss": 0.4134717881679535, | |
| "eval_precision": 0.8169282951542143, | |
| "eval_recall": 0.7781350482315113, | |
| "eval_runtime": 15.8701, | |
| "eval_samples_per_second": 19.597, | |
| "eval_steps_per_second": 0.63, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 36.77213668823242, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.3655, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 14.163016319274902, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.2961, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8553054662379421, | |
| "eval_f1": 0.8581712564304036, | |
| "eval_loss": 0.2815697491168976, | |
| "eval_precision": 0.8675973805921082, | |
| "eval_recall": 0.8553054662379421, | |
| "eval_runtime": 16.8336, | |
| "eval_samples_per_second": 18.475, | |
| "eval_steps_per_second": 0.594, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.1818181818181817, | |
| "grad_norm": 10.475957870483398, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.2839, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 7.20914888381958, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.2576, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7942122186495176, | |
| "eval_f1": 0.7857181245354792, | |
| "eval_loss": 0.2898705303668976, | |
| "eval_precision": 0.7883531432398468, | |
| "eval_recall": 0.7942122186495176, | |
| "eval_runtime": 16.0846, | |
| "eval_samples_per_second": 19.335, | |
| "eval_steps_per_second": 0.622, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.090909090909091, | |
| "grad_norm": 8.099700927734375, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.2458, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 16.755117416381836, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.2473, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 14.67806339263916, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.261, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8102893890675241, | |
| "eval_f1": 0.8036576399029299, | |
| "eval_loss": 0.24693283438682556, | |
| "eval_precision": 0.8056915007838585, | |
| "eval_recall": 0.8102893890675241, | |
| "eval_runtime": 16.5305, | |
| "eval_samples_per_second": 18.814, | |
| "eval_steps_per_second": 0.605, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 19.368623733520508, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.2877, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.909090909090909, | |
| "grad_norm": 5.459014892578125, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.2559, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8360128617363344, | |
| "eval_f1": 0.8179357935850551, | |
| "eval_loss": 0.25484344363212585, | |
| "eval_precision": 0.8632228058178503, | |
| "eval_recall": 0.8360128617363344, | |
| "eval_runtime": 16.2848, | |
| "eval_samples_per_second": 19.098, | |
| "eval_steps_per_second": 0.614, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 3.7228970527648926, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.2382, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.818181818181818, | |
| "grad_norm": 7.972034454345703, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.2249, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8135048231511254, | |
| "eval_f1": 0.7881662757619652, | |
| "eval_loss": 0.2835286557674408, | |
| "eval_precision": 0.8478531476110869, | |
| "eval_recall": 0.8135048231511254, | |
| "eval_runtime": 17.1131, | |
| "eval_samples_per_second": 18.173, | |
| "eval_steps_per_second": 0.584, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 4.717079162597656, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.2424, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.7272727272727275, | |
| "grad_norm": 3.11995267868042, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.2242, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8295819935691319, | |
| "eval_f1": 0.8262048489829058, | |
| "eval_loss": 0.23345188796520233, | |
| "eval_precision": 0.8261307807855373, | |
| "eval_recall": 0.8295819935691319, | |
| "eval_runtime": 17.7042, | |
| "eval_samples_per_second": 17.566, | |
| "eval_steps_per_second": 0.565, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 8.181818181818182, | |
| "grad_norm": 8.103911399841309, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.229, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.636363636363637, | |
| "grad_norm": 5.379126071929932, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.2215, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8520900321543409, | |
| "eval_f1": 0.8531774023903234, | |
| "eval_loss": 0.22933121025562286, | |
| "eval_precision": 0.8549399751110901, | |
| "eval_recall": 0.8520900321543409, | |
| "eval_runtime": 16.8963, | |
| "eval_samples_per_second": 18.406, | |
| "eval_steps_per_second": 0.592, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 18.202444076538086, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.2223, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.545454545454545, | |
| "grad_norm": 2.7657723426818848, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2159, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 8.540946006774902, | |
| "learning_rate": 0.0, | |
| "loss": 0.2269, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.842443729903537, | |
| "eval_f1": 0.8393214641540072, | |
| "eval_loss": 0.2212739735841751, | |
| "eval_precision": 0.8395802314162165, | |
| "eval_recall": 0.842443729903537, | |
| "eval_runtime": 16.6465, | |
| "eval_samples_per_second": 18.683, | |
| "eval_steps_per_second": 0.601, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 220, | |
| "total_flos": 6.954705718242509e+17, | |
| "train_loss": 0.3014452880079096, | |
| "train_runtime": 4522.4246, | |
| "train_samples_per_second": 6.187, | |
| "train_steps_per_second": 0.049 | |
| } | |
| ], | |
| "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 | |
| } | |