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: 3
	output_dir: sweep/ablation3/outputs/b300e65925e0b1beea5fa596d5be7130
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 490590885
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	weight_decay: 0.0001
	worst_case_p: 0.2
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    
0.0887292658  0.1136002657  0.0772475613  0.1002109705  0.0455770959  0.0457113508  0.1766372796  0.1649874055  0.1174845974  0.1301020408  0.0000000000  4.3860387802  1.7946186066  0             1.4542882442 
0.1909032405  0.5832092231  0.1898233588  0.1919831224  0.7026575940  0.7005649718  0.5141687657  0.5201511335  0.5328234544  0.5289115646  3.0226700252  2.8113573289  2.0921902657  300           0.1476536099 
0.2303218453  0.7042327931  0.2391247034  0.2215189873  0.7952240339  0.7678479712  0.6876574307  0.6637279597  0.6925855109  0.6811224490  6.0453400504  2.4799691780  2.0921902657  600           0.1741040850 
0.2093606532  0.7372254929  0.2088056947  0.2099156118  0.8139684170  0.7945557268  0.7216624685  0.6977329975  0.7229657956  0.7193877551  9.0680100756  2.4040213513  2.0921902657  900           0.1790898816 
0.1997359948  0.7545599876  0.2022146059  0.1972573840  0.8334831172  0.8068823832  0.7430730479  0.7204030227  0.7459103463  0.7363945578  12.090680100  2.3405447364  2.0921902657  1200          0.1755174494 
0.2108101365  0.7680801603  0.2159240707  0.2056962025  0.8442675568  0.8299948639  0.7644836272  0.7191435768  0.7686424474  0.7551020408  15.113350125  2.2825987717  2.0921902657  1500          0.1760119979 
0.2416612991  0.7858460644  0.2407065647  0.2426160338  0.8500449352  0.8294812532  0.7855793451  0.7670025189  0.7826641173  0.7610544218  18.136020151  2.2411426230  2.0921902657  1800          0.1765176487 
0.2475938353  0.7940095261  0.2483522278  0.2468354430  0.8623700090  0.8469440164  0.8066750630  0.7493702771  0.7981729339  0.7857142857  21.158690176  2.1651950856  2.0921902657  2100          0.1789552665 
0.2759396889  0.7969136632  0.2733983654  0.2784810127  0.8716138144  0.8479712378  0.8158060453  0.7468513854  0.8124070533  0.7959183673  24.181360201  2.1232110906  2.0921902657  2400          0.1785846829 
0.2918920706  0.8061773420  0.2905351964  0.2932489451  0.8766208756  0.8556753980  0.8249370277  0.7720403023  0.8304652645  0.7908163265  27.204030226  2.0649778096  2.0921902657  2700          0.1748970699 
0.3033625120  0.8216825261  0.2987081466  0.3080168776  0.8822698678  0.8659476117  0.8372166247  0.7972292191  0.8413001912  0.8018707483  30.226700251  2.0280964355  2.0921902657  3000          0.1794000522 
0.3181283587  0.8231935551  0.3145267598  0.3217299578  0.8849659777  0.8674884438  0.8485516373  0.7959697733  0.8455491821  0.8061224490  33.249370277  1.9809078586  2.0921902657  3300          0.1783622368 
0.3259069559  0.8313367473  0.3216451358  0.3301687764  0.8947233278  0.8736517720  0.8554785894  0.7972292191  0.8631824942  0.8231292517  36.272040302  1.9307791559  2.0921902657  3600          0.1766045920 
0.3375085237  0.8437900704  0.3353546006  0.3396624473  0.8953652587  0.8777606574  0.8775188917  0.8236775819  0.8650945400  0.8299319728  39.294710327  1.8754912202  2.0921902657  3900          0.1773313642 
0.3438369424  0.8458310973  0.3406274717  0.3470464135  0.9024264989  0.8834103749  0.8828715365  0.8198992443  0.8776290631  0.8341836735  42.317380352  1.3581053189  5.4002118111  4200          0.2098106829 
0.3472647258  0.8550012458  0.3443184814  0.3502109705  0.9067916292  0.8911145352  0.8822418136  0.8337531486  0.8765668154  0.8401360544  45.340050377  1.0899197630  5.4002118111  4500          0.2226314449 
0.3517473614  0.8583609177  0.3480094912  0.3554852321  0.9091025806  0.8798151002  0.8920025189  0.8576826196  0.8884639898  0.8375850340  48.362720403  1.0486523396  5.4002118111  4800          0.2207196712 
0.3534613226  0.8625870782  0.3493277089  0.3575949367  0.9126973938  0.8890600924  0.9039672544  0.8551637280  0.8886764393  0.8435374150  50.377833753  1.0270670223  5.4002118111  5000          0.2185491073 
