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: [3]
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: 0
	output_dir: sweep/ablation3/outputs/53b44500aa1eb91aad9c1ae2b72b07c4
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1921043760
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
using augment transform
using augment transform
using augment transform
using normal 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    
0.0840519764  0.0678698792  0.1001845505  0.1044303797  0.0100141225  0.0097586030  0.0919395466  0.0894206549  0.0796685787  0.0884353741  0.0000000000  4.0755252838  2.3339076042  0             1.4735286236 
0.3644658626  0.7633634113  0.8552596889  0.8343881857  0.7868789318  0.7781201849  0.7087531486  0.6775818640  0.3683875080  0.3605442177  3.0226700252  2.3865278252  2.5989842415  300           0.1656127032 
0.4113264329  0.8241343692  0.9137885579  0.8797468354  0.8479907562  0.8269131998  0.7969143577  0.7657430730  0.4136392607  0.4090136054  6.0453400504  1.9836485207  2.5989842415  600           0.1877278980 
0.4314075214  0.8457945496  0.9309253889  0.8997890295  0.8684041597  0.8454031844  0.8318639798  0.7921914358  0.4393456554  0.4234693878  9.0680100756  1.8281425567  2.5989842415  900           0.1861769716 
0.4559554699  0.8578925870  0.9419984181  0.9082278481  0.8748234690  0.8531073446  0.8539042821  0.8123425693  0.4569789675  0.4549319728  12.090680100  1.6403990209  2.5989842415  1200          0.1845820300 
0.4757211359  0.8655901858  0.9533350910  0.9061181435  0.8902298113  0.8669748331  0.8696473552  0.8236775819  0.4718504355  0.4795918367  15.113350125  1.5487007884  2.5989842415  1500          0.1859303673 
0.4820976030  0.8797809252  0.9580806749  0.9240506329  0.8948517140  0.8777606574  0.8831863980  0.8375314861  0.4752496282  0.4889455782  18.136020151  1.4599928399  2.5989842415  1800          0.1858597430 
0.4865606693  0.8845694814  0.9601898234  0.9272151899  0.9040955193  0.8839239856  0.9020780856  0.8425692695  0.4790737200  0.4940476190  21.158690176  1.4432294293  2.5989842415  2100          0.1850707110 
0.4908104731  0.8857672908  0.9686264171  0.9303797468  0.9082038773  0.8931689779  0.9115239295  0.8337531486  0.4850223072  0.4965986395  24.181360201  1.4322618194  2.5989842415  2400          0.1836815000 
0.4941042539  0.8918933165  0.9709992091  0.9303797468  0.9177044550  0.8926553672  0.9153022670  0.8526448363  0.4890588485  0.4991496599  27.204030226  1.3690185463  2.5989842415  2700          0.1830459086 
0.4942104787  0.8998044448  0.9731083575  0.9419831224  0.9195018616  0.8947098100  0.9219143577  0.8627204030  0.4892712981  0.4991496599  30.226700251  1.3486707469  2.5989842415  3000          0.1834824157 
0.4933590547  0.9033321372  0.9744265753  0.9398734177  0.9193734754  0.8998459168  0.9291561713  0.8702770781  0.4926704908  0.4940476190  33.249370277  1.3238746468  2.5989842415  3300          0.1861945669 
0.4937842247  0.9104591712  0.9778539415  0.9419831224  0.9250224676  0.9065228557  0.9310453401  0.8828715365  0.4926704908  0.4948979592  36.272040302  1.3105960536  2.5989842415  3600          0.1883541965 
0.4950597349  0.9195503038  0.9794358028  0.9514767932  0.9274618051  0.9142270159  0.9417506297  0.8929471033  0.4926704908  0.4974489796  39.294710327  1.1379275493  5.3942589760  3900          0.2029561702 
0.4916591873  0.9123714593  0.9812813077  0.9504219409  0.9290024393  0.9101181305  0.9496221662  0.8765743073  0.4901210962  0.4931972789  42.317380352  0.9269280271  5.3942589760  4200          0.2176706338 
0.4926165652  0.9209731608  0.9825995254  0.9556962025  0.9331107973  0.9167950693  0.9493073048  0.8904282116  0.4877841513  0.4974489796  45.340050377  0.9184707856  5.3942589760  4500          0.2171944094 
0.4876215621  0.9163388055  0.9818085948  0.9556962025  0.9343946591  0.9142270159  0.9493073048  0.8790931990  0.4854472063  0.4897959184  48.362720403  0.8988502955  5.3942589760  4800          0.2150837986 
0.4860279195  0.9172230697  0.9820722383  0.9556962025  0.9382462447  0.9080636877  0.9502518892  0.8879093199  0.4831102613  0.4889455782  50.377833753  0.8954263589  5.3942589760  5000          0.2155396187 
