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/9f2cd315f6e0f633333b139c3af98d8a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1746633891
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 1
	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: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	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    
0.0130525808  0.0845251279  0.0092275244  0.0168776371  0.0124534600  0.0190035953  0.1202770781  0.1095717884  0.1355428086  0.1250000000  0.0000000000  4.0280761719  2.1692652702  0             1.5035977364 
0.2076462748  0.6442387040  0.2106511996  0.2046413502  0.6860957761  0.6861838726  0.6105163728  0.6385390428  0.6377735288  0.6079931973  3.0226700252  2.5870606033  2.4381909370  300           0.1609669503 
0.2599893929  0.7486598553  0.2404429212  0.2795358650  0.8201309539  0.8186954289  0.7440176322  0.7342569270  0.7355003187  0.6930272109  6.0453400504  2.3026287119  2.4381909370  600           0.1808802740 
0.3236675153  0.7679174561  0.3055628790  0.3417721519  0.8356656824  0.8346173600  0.7695214106  0.7531486146  0.7714042915  0.7159863946  9.0680100756  2.1778834363  2.4381909370  900           0.1804050867 
0.3541225173  0.7920202176  0.3348273135  0.3734177215  0.8537681345  0.8500256805  0.7975440806  0.7921914358  0.7964733376  0.7338435374  12.090680100  2.0679547528  2.4381909370  1200          0.1821590288 
0.3767993393  0.8044071073  0.3538096494  0.3997890295  0.8660932084  0.8567026194  0.8214735516  0.8022670025  0.8141066497  0.7542517007  15.113350125  1.9879889083  2.4381909370  1500          0.1878580840 
0.4065948153  0.8283573781  0.3849195887  0.4282700422  0.8768776480  0.8710837185  0.8494962217  0.8299748111  0.8262162736  0.7840136054  18.136020151  1.9148580821  2.4381909370  1800          0.1841506028 
0.4278209024  0.8313753150  0.4062747166  0.4493670886  0.8818847092  0.8834103749  0.8570528967  0.8198992443  0.8451242830  0.7908163265  21.158690176  1.8090087255  2.4381909370  2100          0.1842369644 
0.4446963147  0.8407925185  0.4231479040  0.4662447257  0.8879188599  0.8787878788  0.8794080605  0.8425692695  0.8553218611  0.8010204082  24.181360201  1.7356716518  2.4381909370  2400          0.1826775829 
0.4572211912  0.8504926650  0.4344845769  0.4799578059  0.8961355758  0.8906009245  0.8869647355  0.8539042821  0.8646696410  0.8069727891  27.204030226  1.6555763292  2.4381909370  2700          0.1819874152 
0.4713273728  0.8570849614  0.4532032692  0.4894514768  0.9013994094  0.8972778634  0.8976700252  0.8602015113  0.8738049713  0.8137755102  30.226700251  1.6007620855  2.4381909370  3000          0.1858896859 
0.4738319865  0.8572370714  0.4582124967  0.4894514768  0.9057645397  0.8947098100  0.9153022670  0.8564231738  0.8820905035  0.8205782313  33.249370277  1.2168397735  5.3981270790  3300          0.2143590275 
0.4781825223  0.8600745099  0.4637490113  0.4926160338  0.9082038773  0.8967642527  0.9241183879  0.8501259446  0.8878266412  0.8333333333  36.272040302  1.0201705168  5.3981270790  3600          0.2193052999 
0.4775231353  0.8672143411  0.4645399420  0.4905063291  0.9114135319  0.8988186954  0.9149874055  0.8652392947  0.8975993202  0.8375850340  39.294710327  0.9974648666  5.3981270790  3900          0.2241196950 
0.4759409959  0.8668320671  0.4634853678  0.4883966245  0.9178328412  0.8998459168  0.9291561713  0.8690176322  0.8986615679  0.8316326531  42.317380352  0.9778836366  5.3981270790  4200          0.2226031407 
0.4759411349  0.8721515018  0.4624307936  0.4894514768  0.9177044550  0.9060092450  0.9323047859  0.8677581864  0.8973868706  0.8426870748  45.340050377  0.9638633168  5.3981270790  4500          0.2212176768 
0.4755455306  0.8782962403  0.4626944371  0.4883966245  0.9209141096  0.9049820236  0.9354534005  0.8753148615  0.9099213937  0.8545918367  48.362720403  0.9573823977  5.3981270790  4800          0.2214789176 
0.4760729567  0.8790447817  0.4626944371  0.4894514768  0.9219411991  0.9039548023  0.9357682620  0.8853904282  0.9116209900  0.8477891156  50.377833753  0.9428047565  5.3981270790  5000          0.2219511414 
