| { | |
| "best_metric": 0.9188888888888889, | |
| "best_model_checkpoint": "mobilevit-small-finetuned-eurosat/checkpoint-570", | |
| "epoch": 3.0, | |
| "global_step": 570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 2.3115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 2.2951, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 2.2701, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 2.2287, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 2.1695, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 2.0969, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 1.987, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 1.8718, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 1.7596, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 1.6574, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 1.5207, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 1.4859, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 1.4098, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 1.3537, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 1.249, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 1.2234, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 1.1733, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 1.1108, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.065, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8385185185185186, | |
| "eval_loss": 0.8779304027557373, | |
| "eval_runtime": 9.9337, | |
| "eval_samples_per_second": 271.801, | |
| "eval_steps_per_second": 8.557, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 1.0287, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.0188, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.9827, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.9519, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.9056, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.9143, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.8873, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.8584, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.8038, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.7724, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.7812, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.749, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.7807, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.7363, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.7279, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.6973, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.71, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.6696, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.636, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9011111111111111, | |
| "eval_loss": 0.46177834272384644, | |
| "eval_runtime": 9.8533, | |
| "eval_samples_per_second": 274.02, | |
| "eval_steps_per_second": 8.627, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.6611, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.6538, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.6373, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.6213, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.6398, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.6546, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.6051, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.6243, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.6282, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.6237, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.5836, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.6009, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.6011, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.5992, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.6049, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.6019, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.5464, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.6014, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5761, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9188888888888889, | |
| "eval_loss": 0.3837963044643402, | |
| "eval_runtime": 9.8305, | |
| "eval_samples_per_second": 274.654, | |
| "eval_steps_per_second": 8.647, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 5.381051647021056e+17, | |
| "train_loss": 1.0441436089967426, | |
| "train_runtime": 655.2315, | |
| "train_samples_per_second": 111.258, | |
| "train_steps_per_second": 0.87 | |
| } | |
| ], | |
| "max_steps": 570, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.381051647021056e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |