| { | |
| "best_metric": 0.8600206611570248, | |
| "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM/NMM_Classification_base_V10/checkpoint-90", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 105, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.08638334274292, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.8429, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 15, | |
| "train_accuracy": 0.828215987294865, | |
| "train_auc_class_0": 0.9164869255677786, | |
| "train_auc_class_1": 0.770497463263411, | |
| "train_auc_class_2": 0.8879816559016815, | |
| "train_auc_overall": 0.858322014910957, | |
| "train_loss": 0.4563606083393097, | |
| "train_runtime": 687.587, | |
| "train_samples_per_second": 10.989, | |
| "train_steps_per_second": 0.087 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8274793388429752, | |
| "eval_auc_class_0": 0.9340616414835164, | |
| "eval_auc_class_1": 0.7507519271533845, | |
| "eval_auc_class_2": 0.8937217290626166, | |
| "eval_auc_overall": 0.8595117658998391, | |
| "eval_loss": 0.49912166595458984, | |
| "eval_runtime": 208.8157, | |
| "eval_samples_per_second": 9.271, | |
| "eval_steps_per_second": 0.077, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.5998913049697876, | |
| "learning_rate": 4.5212765957446815e-05, | |
| "loss": 0.4716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.4967057704925537, | |
| "learning_rate": 3.9893617021276594e-05, | |
| "loss": 0.3887, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 30, | |
| "train_accuracy": 0.8553467443091582, | |
| "train_auc_class_0": 0.9472708924769339, | |
| "train_auc_class_1": 0.9283657851250956, | |
| "train_auc_class_2": 0.9247901532600991, | |
| "train_auc_overall": 0.9334756102873761, | |
| "train_loss": 0.35952258110046387, | |
| "train_runtime": 685.7612, | |
| "train_samples_per_second": 11.018, | |
| "train_steps_per_second": 0.087 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8502066115702479, | |
| "eval_auc_class_0": 0.9477621336996336, | |
| "eval_auc_class_1": 0.9035008683616039, | |
| "eval_auc_class_2": 0.9096346486873113, | |
| "eval_auc_overall": 0.9202992169161829, | |
| "eval_loss": 0.3957720398902893, | |
| "eval_runtime": 208.9311, | |
| "eval_samples_per_second": 9.266, | |
| "eval_steps_per_second": 0.077, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.716306209564209, | |
| "learning_rate": 3.4574468085106386e-05, | |
| "loss": 0.3533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 45, | |
| "train_accuracy": 0.8750661725780836, | |
| "train_auc_class_0": 0.9582223466702152, | |
| "train_auc_class_1": 0.9392220276138971, | |
| "train_auc_class_2": 0.9390688589921182, | |
| "train_auc_overall": 0.9455044110920768, | |
| "train_loss": 0.3131944239139557, | |
| "train_runtime": 681.8829, | |
| "train_samples_per_second": 11.081, | |
| "train_steps_per_second": 0.088 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8589876033057852, | |
| "eval_auc_class_0": 0.9578196543040294, | |
| "eval_auc_class_1": 0.9092855930322143, | |
| "eval_auc_class_2": 0.920674647298944, | |
| "eval_auc_overall": 0.9292599648783959, | |
| "eval_loss": 0.37213757634162903, | |
| "eval_runtime": 207.6482, | |
| "eval_samples_per_second": 9.323, | |
| "eval_steps_per_second": 0.077, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 1.727489948272705, | |
| "learning_rate": 2.925531914893617e-05, | |
| "loss": 0.3208, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 10.33216381072998, | |
| "learning_rate": 2.393617021276596e-05, | |
| "loss": 0.3092, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 60, | |
| "train_accuracy": 0.8848597141344626, | |
| "train_auc_class_0": 0.9659353652856636, | |
| "train_auc_class_1": 0.9407955383480827, | |
| "train_auc_class_2": 0.946874731546507, | |
| "train_auc_overall": 0.9512018783934177, | |
| "train_loss": 0.29102450609207153, | |
| "train_runtime": 680.3084, | |
| "train_samples_per_second": 11.107, | |
| "train_steps_per_second": 0.088 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8579545454545454, | |
| "eval_auc_class_0": 0.9606026785714286, | |
| "eval_auc_class_1": 0.9083715281858423, | |
| "eval_auc_class_2": 0.9231885836547031, | |
| "eval_auc_overall": 0.9307209301373248, | |
| "eval_loss": 0.37202903628349304, | |
| "eval_runtime": 208.7004, | |
| "eval_samples_per_second": 9.276, | |
| "eval_steps_per_second": 0.077, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 2.016211748123169, | |
| "learning_rate": 1.8617021276595745e-05, | |
| "loss": 0.2891, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 75, | |
| "train_accuracy": 0.8913446267866596, | |
| "train_auc_class_0": 0.9681433160338301, | |
| "train_auc_class_1": 0.9542337553261225, | |
| "train_auc_class_2": 0.9506045992123575, | |
| "train_auc_overall": 0.9576605568574367, | |
| "train_loss": 0.2791108191013336, | |
| "train_runtime": 690.7325, | |
| "train_samples_per_second": 10.939, | |
| "train_steps_per_second": 0.087 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8584710743801653, | |
| "eval_auc_class_0": 0.9613524496336998, | |
| "eval_auc_class_1": 0.9090984273731954, | |
| "eval_auc_class_2": 0.9242633286351978, | |
| "eval_auc_overall": 0.9315714018806975, | |
| "eval_loss": 0.36684560775756836, | |
| "eval_runtime": 211.7912, | |
| "eval_samples_per_second": 9.141, | |
| "eval_steps_per_second": 0.076, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 2.7578961849212646, | |
| "learning_rate": 1.3297872340425532e-05, | |
| "loss": 0.301, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 2.526148557662964, | |
| "learning_rate": 7.97872340425532e-06, | |
| "loss": 0.2852, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 90, | |
| "train_accuracy": 0.8955796717840127, | |
| "train_auc_class_0": 0.9719376552519517, | |
| "train_auc_class_1": 0.9603400183000109, | |
| "train_auc_class_2": 0.9560110428344394, | |
| "train_auc_overall": 0.9627629054621339, | |
| "train_loss": 0.2651444673538208, | |
| "train_runtime": 689.8251, | |
| "train_samples_per_second": 10.954, | |
| "train_steps_per_second": 0.087 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8600206611570248, | |
| "eval_auc_class_0": 0.9623798076923077, | |
| "eval_auc_class_1": 0.9106044580248364, | |
| "eval_auc_class_2": 0.9252550195053197, | |
| "eval_auc_overall": 0.932746428407488, | |
| "eval_loss": 0.358356237411499, | |
| "eval_runtime": 209.7236, | |
| "eval_samples_per_second": 9.231, | |
| "eval_steps_per_second": 0.076, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 1.6473604440689087, | |
| "learning_rate": 2.6595744680851065e-06, | |
| "loss": 0.2804, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 105, | |
| "train_accuracy": 0.8926680783483325, | |
| "train_auc_class_0": 0.9692773945765316, | |
| "train_auc_class_1": 0.9595504889107397, | |
| "train_auc_class_2": 0.9538150093690271, | |
| "train_auc_overall": 0.9608809642854328, | |
| "train_loss": 0.2725497782230377, | |
| "train_runtime": 674.8314, | |
| "train_samples_per_second": 11.197, | |
| "train_steps_per_second": 0.089 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8600206611570248, | |
| "eval_auc_class_0": 0.9628448374542126, | |
| "eval_auc_class_1": 0.90828447439095, | |
| "eval_auc_class_2": 0.924919084223066, | |
| "eval_auc_overall": 0.9320161320227428, | |
| "eval_loss": 0.3619421422481537, | |
| "eval_runtime": 204.9165, | |
| "eval_samples_per_second": 9.448, | |
| "eval_steps_per_second": 0.078, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 105, | |
| "total_flos": 4.143902092898771e+18, | |
| "train_loss": 0.37870263712746755, | |
| "train_runtime": 11542.069, | |
| "train_samples_per_second": 4.583, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 105, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 4.143902092898771e+18, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |