Environment:
	Python: 3.10.11
	PyTorch: 2.0.1
	Torchvision: 0.15.2
	CUDA: 11.7
	CUDNN: 8500
	NumPy: 1.24.3
	PIL: 9.4.0
	Testing environment: [0]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: TerraIncognita
	holdout_fraction: 0.2
	hparams: {
    "resnet18": false,
    "resnet_dropout": 0,
    "nonlinear_classifier": false,
    "data_augmentation": true,
    "clip_backbone": "ViT-B/32",
    "student_model": "resnet",
    "SMA": true,
    "batch_size": 32
}
	hparams_seed: 1
	output_dir: sweep/ablation3/outputs/5d7f002897a949a4a03b579df5508465
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 643417070
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 2
	uda_holdout_fraction: 0
	visualize: False
Not saving models
HParams:
	SMA: True
	batch_size: 32
	class_balanced: False
	clip_backbone: ViT-B/32
	data_augmentation: True
	lambda1: 0.6109302038716249
	lambda2: 0.5117744391412766
	last_k_epoch: 0.31317984427858747
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.002688876693512
	weight_decay: 1e-06
	worst_case_p: 0.25
using normal transform
using augment transform
using augment transform
using augment transform
using device:  cuda
Using ViT-B/32...
constructing student model
using resnet 50
Using SMA
n_steps 5001
checkpoint_freq 300
agg_test_acc  agg_val_acc   env0_in_acc   env0_out_acc  env1_in_acc   env1_out_acc  env2_in_acc   env2_out_acc  env3_in_acc   env3_out_acc  epoch         loss          mem_gb        step          step_time    
0.0700065410  0.1197107182  0.0703928289  0.0696202532  0.0929515984  0.0888546482  0.1489294710  0.1435768262  0.1287444232  0.1267006803  0.0000000000  4.4812097549  2.0074815750  0             1.4015476704 
0.4072529508  0.6548368408  0.3936198260  0.4208860759  0.7668506869  0.7550077042  0.6054785894  0.6083123426  0.6029318037  0.6011904762  3.0226700252  2.6562275426  2.2567677498  300           0.1533805490 
0.4109434043  0.7319082606  0.4052201424  0.4166666667  0.8262934908  0.8053415511  0.7216624685  0.6939546599  0.7104312726  0.6964285714  6.0453400504  2.3540004230  2.2567677498  600           0.1742432189 
0.4137106883  0.7643256830  0.4181386765  0.4092827004  0.8473488253  0.8289676425  0.7692065491  0.7216624685  0.7510091353  0.7423469388  9.0680100756  2.2637749120  2.2567677498  900           0.1781586591 
0.4126565312  0.7837562828  0.4128658054  0.4124472574  0.8583900372  0.8392398562  0.7843198992  0.7569269521  0.7731038878  0.7551020408  12.090680100  2.1908439239  2.2567677498  1200          0.1812311649 
0.4221486725  0.7944067463  0.4244661218  0.4198312236  0.8723841315  0.8387262455  0.8010075567  0.7783375315  0.7926492458  0.7661564626  15.113350125  2.1081768739  2.2567677498  1500          0.1784666053 
0.4377054499  0.8127208573  0.4418665964  0.4335443038  0.8737963795  0.8582434515  0.8195843829  0.8010075567  0.8132568515  0.7789115646  18.136020151  2.0556725903  2.2567677498  1800          0.1815988231 
0.4541858140  0.8117605997  0.4547851305  0.4535864979  0.8838105020  0.8556753980  0.8463476071  0.7921914358  0.8274909709  0.7874149660  21.158690176  1.9600452093  2.2567677498  2100          0.1854575721 
0.4651286901  0.8285425277  0.4640126549  0.4662447257  0.8898446527  0.8751926040  0.8624055416  0.8085642317  0.8317399618  0.8018707483  24.181360201  1.8963126842  2.2567677498  2400          0.1835047317 
0.4719845349  0.8315398145  0.4692855260  0.4746835443  0.8984465272  0.8726245506  0.8690176322  0.8022670025  0.8483110261  0.8197278912  27.204030226  1.8353657663  2.2567677498  2700          0.1801987298 
0.4889917690  0.8396679110  0.4864223570  0.4915611814  0.9002439338  0.8864920390  0.8879093199  0.8110831234  0.8548969620  0.8214285714  30.226700251  1.7785216947  2.2567677498  3000          0.1788439775 
0.4999342279  0.8559706564  0.4988136040  0.5010548523  0.9047374503  0.8818695429  0.8948362720  0.8476070529  0.8740174209  0.8384353741  33.249370277  1.6980615465  2.2567677498  3300          0.1777597817 
0.5024391198  0.8569049932  0.5017136831  0.5031645570  0.9087174220  0.8900873138  0.9023929471  0.8387909320  0.8757170172  0.8418367347  36.272040302  1.3705202069  5.3975014687  3600          0.2010368919 
0.4990107802  0.8580009737  0.5022409702  0.4957805907  0.9121838490  0.8875192604  0.9099496222  0.8463476071  0.8891013384  0.8401360544  39.294710327  1.0776343300  5.3975014687  3900          0.2158698153 
0.4990105021  0.8710760296  0.5043501186  0.4936708861  0.9182179997  0.9019003595  0.9134130982  0.8652392947  0.8891013384  0.8460884354  42.317380352  1.0419306439  5.3975014687  4200          0.2168378925 
0.4998019890  0.8694976563  0.5017136831  0.4978902954  0.9202721787  0.8962506420  0.9184508816  0.8602015113  0.8954748247  0.8520408163  45.340050377  1.0314849778  5.3975014687  4500          0.2191242743 
0.5034938330  0.8703211647  0.5027682573  0.5042194093  0.9212992682  0.8952234206  0.9269521411  0.8526448363  0.9024856597  0.8630952381  48.362720403  1.0209159380  5.3975014687  4800          0.2186745501 
0.5056033986  0.8691800203  0.5038228315  0.5073839662  0.9246373090  0.9008731382  0.9329345088  0.8639798489  0.9054599533  0.8426870748  50.377833753  0.9996058047  5.3975014687  5000          0.2168335629 
