| { | |
| "best_metric": 0.9895561357702349, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-mixed-bottoms/checkpoint-610", | |
| "epoch": 9.907192575406032, | |
| "global_step": 610, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.975124378109453e-05, | |
| "loss": 0.5548, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.8922056384742954e-05, | |
| "loss": 0.3681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.8092868988391376e-05, | |
| "loss": 0.3048, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.7263681592039805e-05, | |
| "loss": 0.2445, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.643449419568823e-05, | |
| "loss": 0.209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.560530679933665e-05, | |
| "loss": 0.1816, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9451697127937336, | |
| "eval_loss": 0.12642310559749603, | |
| "eval_runtime": 24.4251, | |
| "eval_samples_per_second": 15.681, | |
| "eval_steps_per_second": 1.965, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.477611940298508e-05, | |
| "loss": 0.1838, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.39469320066335e-05, | |
| "loss": 0.1684, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.311774461028192e-05, | |
| "loss": 0.2074, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.228855721393035e-05, | |
| "loss": 0.144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.145936981757877e-05, | |
| "loss": 0.1467, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.0630182421227194e-05, | |
| "loss": 0.1673, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9399477806788512, | |
| "eval_loss": 0.14775583148002625, | |
| "eval_runtime": 5.0443, | |
| "eval_samples_per_second": 75.928, | |
| "eval_steps_per_second": 9.516, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.980099502487562e-05, | |
| "loss": 0.1147, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.8971807628524045e-05, | |
| "loss": 0.1403, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.8142620232172474e-05, | |
| "loss": 0.152, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3.73134328358209e-05, | |
| "loss": 0.1594, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.6484245439469325e-05, | |
| "loss": 0.1423, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.565505804311775e-05, | |
| "loss": 0.125, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9738903394255874, | |
| "eval_loss": 0.06674866378307343, | |
| "eval_runtime": 4.4641, | |
| "eval_samples_per_second": 85.796, | |
| "eval_steps_per_second": 10.752, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.4825870646766175e-05, | |
| "loss": 0.1046, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.39966832504146e-05, | |
| "loss": 0.124, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.316749585406302e-05, | |
| "loss": 0.093, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.233830845771145e-05, | |
| "loss": 0.1084, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.150912106135987e-05, | |
| "loss": 0.1076, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 3.067993366500829e-05, | |
| "loss": 0.1034, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9817232375979112, | |
| "eval_loss": 0.05531755089759827, | |
| "eval_runtime": 4.4942, | |
| "eval_samples_per_second": 85.221, | |
| "eval_steps_per_second": 10.68, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.9850746268656714e-05, | |
| "loss": 0.1161, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 2.9021558872305143e-05, | |
| "loss": 0.0833, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 2.8192371475953565e-05, | |
| "loss": 0.0546, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 2.736318407960199e-05, | |
| "loss": 0.0777, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 2.653399668325042e-05, | |
| "loss": 0.064, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.570480928689884e-05, | |
| "loss": 0.0843, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9843342036553525, | |
| "eval_loss": 0.03356986492872238, | |
| "eval_runtime": 4.4121, | |
| "eval_samples_per_second": 86.806, | |
| "eval_steps_per_second": 10.879, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 2.4875621890547266e-05, | |
| "loss": 0.13, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 2.4046434494195688e-05, | |
| "loss": 0.0658, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 2.3217247097844114e-05, | |
| "loss": 0.0632, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 2.238805970149254e-05, | |
| "loss": 0.0878, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2.155887230514096e-05, | |
| "loss": 0.0493, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 2.0729684908789386e-05, | |
| "loss": 0.0744, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.9843342036553525, | |
| "eval_loss": 0.039609070867300034, | |
| "eval_runtime": 4.388, | |
| "eval_samples_per_second": 87.284, | |
| "eval_steps_per_second": 10.939, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.990049751243781e-05, | |
| "loss": 0.0987, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 1.9071310116086237e-05, | |
| "loss": 0.0885, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.8242122719734662e-05, | |
| "loss": 0.0541, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.7412935323383088e-05, | |
| "loss": 0.0499, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 1.658374792703151e-05, | |
| "loss": 0.053, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.5754560530679935e-05, | |
| "loss": 0.058, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 1.4925373134328357e-05, | |
| "loss": 0.0702, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.97911227154047, | |
| "eval_loss": 0.06899962574243546, | |
| "eval_runtime": 4.5228, | |
| "eval_samples_per_second": 84.682, | |
| "eval_steps_per_second": 10.613, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 1.4096185737976782e-05, | |
| "loss": 0.0678, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.326699834162521e-05, | |
| "loss": 0.06, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.2437810945273633e-05, | |
| "loss": 0.0527, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.1608623548922057e-05, | |
| "loss": 0.0462, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 1.077943615257048e-05, | |
| "loss": 0.0682, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 9.950248756218906e-06, | |
| "loss": 0.063, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.9843342036553525, | |
| "eval_loss": 0.03944966197013855, | |
| "eval_runtime": 4.9394, | |
| "eval_samples_per_second": 77.54, | |
| "eval_steps_per_second": 9.718, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.121061359867331e-06, | |
| "loss": 0.0879, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 8.291873963515755e-06, | |
| "loss": 0.081, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 7.4626865671641785e-06, | |
| "loss": 0.0488, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 6.633499170812605e-06, | |
| "loss": 0.0692, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 5.804311774461028e-06, | |
| "loss": 0.0384, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 4.975124378109453e-06, | |
| "loss": 0.0497, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9869451697127938, | |
| "eval_loss": 0.03008684515953064, | |
| "eval_runtime": 4.4989, | |
| "eval_samples_per_second": 85.132, | |
| "eval_steps_per_second": 10.669, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.145936981757877e-06, | |
| "loss": 0.0456, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 3.3167495854063024e-06, | |
| "loss": 0.0874, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 2.4875621890547264e-06, | |
| "loss": 0.0569, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 1.6583747927031512e-06, | |
| "loss": 0.0613, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 8.291873963515756e-07, | |
| "loss": 0.0389, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.0502, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.9895561357702349, | |
| "eval_loss": 0.029892772436141968, | |
| "eval_runtime": 5.862, | |
| "eval_samples_per_second": 65.336, | |
| "eval_steps_per_second": 8.188, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "step": 610, | |
| "total_flos": 8.479620642524774e+17, | |
| "train_loss": 0.11231542806156346, | |
| "train_runtime": 1101.7928, | |
| "train_samples_per_second": 31.249, | |
| "train_steps_per_second": 0.554 | |
| } | |
| ], | |
| "max_steps": 610, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.479620642524774e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |