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: 2
	output_dir: sweep/ablation3/outputs/8d85ad63fd410d0e6b29d6d846d389fb
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 86153797
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 0
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0491763364  0.0946544999  0.0466649090  0.0516877637  0.0480164334  0.0426296867  0.1360201511  0.1460957179  0.0951773954  0.0952380952  0.0000000000  4.5114688873  2.1692652702  0             1.6376495361 
0.0899142713  0.6367309707  0.0901660954  0.0896624473  0.7550391578  0.7534668721  0.6010705290  0.5793450882  0.5895474825  0.5773809524  3.0226700252  2.7109581717  2.4381909370  300           0.1617517749 
0.2000007508  0.7321277150  0.1943052992  0.2056962025  0.8138400308  0.8068823832  0.7238664987  0.6964735516  0.6940726577  0.6930272109  6.0453400504  2.3922287583  2.4381909370  600           0.1826086903 
0.2371799149  0.7477681180  0.2275243870  0.2468354430  0.8288612145  0.8284540318  0.7641687657  0.7090680101  0.7355003187  0.7057823129  9.0680100756  2.2734514483  2.4381909370  900           0.1843749420 
0.2738319310  0.7682234980  0.2586343264  0.2890295359  0.8478623700  0.8428351310  0.7836901763  0.7254408060  0.7586573189  0.7363945578  12.090680100  2.1945777758  2.4381909370  1200          0.1800509429 
0.3044193110  0.7886095887  0.2839441076  0.3248945148  0.8587751958  0.8597842835  0.8035264484  0.7594458438  0.7875504568  0.7465986395  15.113350125  2.1117152325  2.4381909370  1500          0.1839172641 
0.3278865074  0.8005384760  0.3087266016  0.3470464135  0.8686609321  0.8602978942  0.8132871537  0.7607052897  0.8049713193  0.7806122449  18.136020151  2.0242597381  2.4381909370  1800          0.1828578870 
0.3550445745  0.8122224843  0.3419456894  0.3681434599  0.8809860059  0.8705701079  0.8353274559  0.7846347607  0.8202676864  0.7814625850  21.158690176  1.9488313429  2.4381909370  2100          0.1865246797 
0.3604498236  0.8200956456  0.3485367783  0.3723628692  0.8804724612  0.8772470467  0.8532745592  0.7896725441  0.8304652645  0.7933673469  24.181360201  1.8838382586  2.4381909370  2400          0.1927744484 
0.3783803663  0.8298035302  0.3633008173  0.3934599156  0.8895878803  0.8870056497  0.8652392947  0.8047858942  0.8421499894  0.7976190476  27.204030226  1.8043456169  2.4381909370  2700          0.1886546397 
0.3848407458  0.8441772531  0.3677827577  0.4018987342  0.8966491206  0.8941961993  0.8787783375  0.8211586902  0.8540471638  0.8171768707  30.226700251  1.7576212196  2.4381909370  3000          0.1934191656 
0.3988158008  0.8446155162  0.3809649354  0.4166666667  0.8992168443  0.8921417565  0.8935768262  0.8236775819  0.8682812832  0.8180272109  33.249370277  1.6863579186  2.4381909370  3300          0.1899618220 
0.4072535070  0.8529956997  0.3894015291  0.4251054852  0.9058929259  0.8911145352  0.8942065491  0.8387909320  0.8776290631  0.8290816327  36.272040302  1.6604972136  2.4381909370  3600          0.1872794525 
0.4123949734  0.8562991438  0.3965199051  0.4282700422  0.9110283733  0.8988186954  0.9023929471  0.8324937028  0.8837900999  0.8375850340  39.294710327  1.5307369824  5.3981270790  3900          0.1980790218 
0.4085715857  0.8545720125  0.3930925389  0.4240506329  0.9130825523  0.9013867488  0.9102644836  0.8400503778  0.8846398980  0.8222789116  42.317380352  1.1921931430  5.3981270790  4200          0.2264711428 
0.4048800197  0.8644498091  0.3899288162  0.4198312236  0.9186031583  0.9013867488  0.9093198992  0.8501259446  0.8927129807  0.8418367347  45.340050377  1.1658097982  5.3981270790  4500          0.2236038081 
0.4030340977  0.8675014050  0.3894015291  0.4166666667  0.9198870202  0.9060092450  0.9181360202  0.8614609572  0.8927129807  0.8350340136  48.362720403  1.1526651418  5.3981270790  4800          0.2230481108 
0.4019793844  0.8653463396  0.3883469549  0.4156118143  0.9210424958  0.9070364664  0.9231738035  0.8488664987  0.8958997238  0.8401360544  50.377833753  1.1347441474  5.3981270790  5000          0.2228646398 
