| { | |
| "best_metric": 0.9898089171974522, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-mobile-eye-tracking-dataset-v2/checkpoint-221", | |
| "epoch": 9.898305084745763, | |
| "global_step": 730, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.849315068493151e-06, | |
| "loss": 0.0366, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 0.0367, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0547945205479453e-05, | |
| "loss": 0.0341, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 0.0396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.424657534246575e-05, | |
| "loss": 0.0338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 0.0298, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.794520547945205e-05, | |
| "loss": 0.024, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9808917197452229, | |
| "eval_loss": 0.0768975093960762, | |
| "eval_runtime": 10.9295, | |
| "eval_samples_per_second": 71.824, | |
| "eval_steps_per_second": 3.019, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.9467275494672755e-05, | |
| "loss": 0.0206, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.8706240487062404e-05, | |
| "loss": 0.0219, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.794520547945205e-05, | |
| "loss": 0.0167, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.71841704718417e-05, | |
| "loss": 0.0314, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.642313546423136e-05, | |
| "loss": 0.0304, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.5662100456621006e-05, | |
| "loss": 0.017, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.4901065449010655e-05, | |
| "loss": 0.0236, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.9745222929936306, | |
| "eval_loss": 0.11105378717184067, | |
| "eval_runtime": 10.6001, | |
| "eval_samples_per_second": 74.056, | |
| "eval_steps_per_second": 3.113, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.41400304414003e-05, | |
| "loss": 0.022, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.337899543378995e-05, | |
| "loss": 0.0184, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.26179604261796e-05, | |
| "loss": 0.0321, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.1856925418569256e-05, | |
| "loss": 0.015, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 0.0114, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.0334855403348554e-05, | |
| "loss": 0.0155, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.95738203957382e-05, | |
| "loss": 0.0165, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.881278538812785e-05, | |
| "loss": 0.0172, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9898089171974522, | |
| "eval_loss": 0.05419470742344856, | |
| "eval_runtime": 11.1217, | |
| "eval_samples_per_second": 70.583, | |
| "eval_steps_per_second": 2.967, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.80517503805175e-05, | |
| "loss": 0.0086, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.7290715372907156e-05, | |
| "loss": 0.0145, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.6529680365296805e-05, | |
| "loss": 0.0082, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.5768645357686453e-05, | |
| "loss": 0.0087, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 3.50076103500761e-05, | |
| "loss": 0.0072, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.424657534246575e-05, | |
| "loss": 0.0171, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.34855403348554e-05, | |
| "loss": 0.0114, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9885350318471338, | |
| "eval_loss": 0.06302983313798904, | |
| "eval_runtime": 10.6941, | |
| "eval_samples_per_second": 73.405, | |
| "eval_steps_per_second": 3.086, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 3.2724505327245055e-05, | |
| "loss": 0.0063, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.1963470319634704e-05, | |
| "loss": 0.006, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 3.120243531202435e-05, | |
| "loss": 0.0102, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.0441400304414e-05, | |
| "loss": 0.0054, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.9680365296803654e-05, | |
| "loss": 0.0074, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.8919330289193303e-05, | |
| "loss": 0.0108, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.815829528158295e-05, | |
| "loss": 0.0051, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9859872611464968, | |
| "eval_loss": 0.0673714205622673, | |
| "eval_runtime": 10.7583, | |
| "eval_samples_per_second": 72.967, | |
| "eval_steps_per_second": 3.067, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 0.005, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 2.6636225266362252e-05, | |
| "loss": 0.0048, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.58751902587519e-05, | |
| "loss": 0.0084, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.5114155251141553e-05, | |
| "loss": 0.0049, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 2.4353120243531202e-05, | |
| "loss": 0.0045, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 2.359208523592085e-05, | |
| "loss": 0.0043, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 2.2831050228310503e-05, | |
| "loss": 0.0097, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 2.207001522070015e-05, | |
| "loss": 0.0044, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.9885350318471338, | |
| "eval_loss": 0.06396039575338364, | |
| "eval_runtime": 10.7469, | |
| "eval_samples_per_second": 73.044, | |
| "eval_steps_per_second": 3.071, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 2.13089802130898e-05, | |
| "loss": 0.0053, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 2.0547945205479453e-05, | |
| "loss": 0.0041, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 1.97869101978691e-05, | |
| "loss": 0.004, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.902587519025875e-05, | |
| "loss": 0.004, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.8264840182648402e-05, | |
| "loss": 0.0039, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.750380517503805e-05, | |
| "loss": 0.0091, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.67427701674277e-05, | |
| "loss": 0.0037, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9885350318471338, | |
| "eval_loss": 0.06461471319198608, | |
| "eval_runtime": 10.6595, | |
| "eval_samples_per_second": 73.643, | |
| "eval_steps_per_second": 3.096, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.5981735159817352e-05, | |
| "loss": 0.0085, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.5220700152207e-05, | |
| "loss": 0.0037, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.4459665144596651e-05, | |
| "loss": 0.0036, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 0.0036, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.293759512937595e-05, | |
| "loss": 0.0035, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 1.2176560121765601e-05, | |
| "loss": 0.0035, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 1.1415525114155251e-05, | |
| "loss": 0.0034, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.06544901065449e-05, | |
| "loss": 0.0034, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9885350318471338, | |
| "eval_loss": 0.06516698002815247, | |
| "eval_runtime": 10.6581, | |
| "eval_samples_per_second": 73.653, | |
| "eval_steps_per_second": 3.096, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.89345509893455e-06, | |
| "loss": 0.0034, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 9.132420091324201e-06, | |
| "loss": 0.0033, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.37138508371385e-06, | |
| "loss": 0.0033, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 7.6103500761035e-06, | |
| "loss": 0.0033, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 6.849315068493151e-06, | |
| "loss": 0.008, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 6.0882800608828005e-06, | |
| "loss": 0.0033, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 5.32724505327245e-06, | |
| "loss": 0.0032, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.9885350318471338, | |
| "eval_loss": 0.06558429449796677, | |
| "eval_runtime": 10.7487, | |
| "eval_samples_per_second": 73.032, | |
| "eval_steps_per_second": 3.07, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 4.566210045662101e-06, | |
| "loss": 0.0031, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 3.80517503805175e-06, | |
| "loss": 0.0033, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.0441400304414002e-06, | |
| "loss": 0.0032, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 2.2831050228310503e-06, | |
| "loss": 0.0031, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 1.5220700152207001e-06, | |
| "loss": 0.0032, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 7.610350076103501e-07, | |
| "loss": 0.0076, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0, | |
| "loss": 0.0032, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_accuracy": 0.9885350318471338, | |
| "eval_loss": 0.06568808108568192, | |
| "eval_runtime": 10.6014, | |
| "eval_samples_per_second": 74.047, | |
| "eval_steps_per_second": 3.113, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "step": 730, | |
| "total_flos": 5.416738622139802e+18, | |
| "train_loss": 0.011492813212720498, | |
| "train_runtime": 2907.1139, | |
| "train_samples_per_second": 24.285, | |
| "train_steps_per_second": 0.251 | |
| } | |
| ], | |
| "max_steps": 730, | |
| "num_train_epochs": 10, | |
| "total_flos": 5.416738622139802e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |